Datasets:

---

clinicalnlplab

/

CochranePLS_train

like 0

Follow

Clinical NLP Lab 38

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Four studies randomising 163 people could be included in the review. It is not clear if brief family intervention reduces the utilisation of health services by patients, as most results are equivocal at long term and only one study reported data for the primary outcomes of interest of hospital admission (n = 30, 1 RCT, RR 0.50, 95% CI 0.22 to 1.11, very low quality evidence). Data for relapse are also equivocal by medium term (n = 40, 1 RCT, RR 0.50, 95% CI 0.10 to 2.43, low quality evidence). However, data for the family outcome of understanding of family member significantly favoured brief family intervention (n = 70, 1 RCT, MD 14.90, 95% CI 7.20 to 22.60, very low quality evidence). No study reported data for other outcomes of interest including days in hospital; adverse events; medication compliance; quality of life or satisfaction with care; or any economic outcomes. The findings of this review are not outstanding due to the size and quality of studies providing data; the analysed outcomes were also minimal, with no meta-analysis possible. All outcomes in the 'Summary of findings' table were rated low or very low quality evidence. However, the importance of brief family intervention should not be dismissed outright, with the present state of demand and resources available. The designs of such brief interventions could be modified to be more effective with larger studies, which may then have enough power to inform clinical practice.\nOutput:\n" }, { "from": "agent", "value": "This review investigates the effects of brief family intervention for people with schizophrenia, compared to standard or usual care. A search of the Cochrane Schizophrenia Group's trial register was carried out in July 2012. Four randomised studies, with a total of 163 participants were included. Results were limited, so it is not clear if brief family intervention reduces admission to hospital, decreases people using health services and reduces relapse for people with schizophrenia. The review found some evidence that brief family intervention might increase the understanding of family members about mental illness. However, all main findings are not strong and based on low or very low quality evidence. Despite this, the authors of the review suggest that brief family intervention should not be completely dismissed, as it is in a current state of demand and there are usually resources or local services available for people with mental health problems and their families to participate in as a part of recovery. The authors also suggest that brief family intervention could be improved to be more effective but this would depend on larger and better studies of brief family intervention being carried out, which would help guide good practice and lead to better outcomes for people with schizophrenia. This plain language summary has been written by a consumer, Ben Gray, from RETHINK." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included two randomised controlled trials with a total of 80 participants in this review. 1. Early versus delayed open appendicectomy for appendiceal phlegmon Forty participants (paediatric and adults) with appendiceal phlegmon were randomised either to early appendicectomy (appendicectomy as soon as appendiceal mass resolved within the same admission) (n = 20), or to delayed appendicectomy (initial conservative treatment followed by interval appendicectomy six weeks later) (n = 20). The trial was at high risk of bias. There was no mortality in either group. There is insufficient evidence to determine the effect of using either early or delayed open appendicectomy onoverall morbidity (RR 13.00; 95% CI 0.78 to 216.39; very low-quality evidence), the proportion of participants who developed wound infection (RR 9.00; 95% CI 0.52 to 156.91; very low quality evidence) or faecal fistula (RR 3.00; 95% CI 0.13 to 69.52; very low quality evidence). The quality of evidence for increased length of hospital stay and time away from normal activities in the early appendicectomy group (MD 6.70 days; 95% CI 2.76 to 10.64, and MD 5.00 days; 95% CI 1.52 to 8.48, respectively) is very low quality evidence. The trial reported neither quality of life nor pain outcomes. 2. Early versus delayed laparoscopic appendicectomy for appendiceal abscess Forty paediatric participants with appendiceal abscess were randomised either to early appendicectomy (emergent laparoscopic appendicectomy) (n = 20) or to delayed appendicectomy (initial conservative treatment followed by interval laparoscopic appendicectomy 10 weeks later) (n = 20). The trial was at high risk of bias. The trial did not report on overall morbidity or complications. There was no mortality in either group. We do not have sufficient evidence to determine the effects of using either early or delayed laparoscopic appendicectomy for outcomes relating to hospital stay between the groups (MD −0.20 days; 95% CI −3.54 to 3.14; very low quality of evidence). Health-related quality of life was measured with the Pediatric Quality of Life Scale-Version 4.0 questionnaire (a scale of 0 to 100 with higher values indicating a better quality of life). Health-related quality of life score measured at 12 weeks after appendicectomy was higher in the early appendicectomy group than in the delayed appendicectomy group (MD 12.40 points; 95% CI 9.78 to 15.02) but the quality of evidence was very low. This trial reported neither the pain nor the time away from normal activities. It is unclear whether early appendicectomy prevents complications compared to delayed appendicectomy for people with appendiceal phlegmon or abscess. The evidence indicating increased length of hospital stay and time away from normal activities in people with early open appendicectomy is of very low quality. The evidence for better health-related quality of life following early laparoscopic appendicectomy compared with delayed appendicectomy is based on very low quality evidence. For both comparisons addressed in this review, data are sparse, and we cannot rule out significant benefits or harms of early versus delayed appendicectomy. Further trials on this topic are urgently needed and should specify a set of criteria for use of antibiotics, percutaneous drainage of the appendiceal abscess prior to surgery and resolution of the appendiceal phlegmon or abscess. Future trials should include outcomes such as time away from normal activities, quality of life and the length of hospital stay.\nOutput:\n" }, { "from": "agent", "value": "We searched for all relevant randomised controlled trials up to 23 August 2016. We identified two trials involving 80 participants. One compared early versus delayed open appendicectomy in 40 children and adults with appendiceal phlegmon. The other trial compared early versus delayed keyhole (laparoscopic) appendicectomy (where surgery is performed through a very small incision) in 40 children with appendiceal abscess. Studies took place in the USA and India. The age of the individuals in the trials varied between 1 year and 84 years, and 27.5% were females. Both two studies were small and had a number of limitations so we cannot be certain about how the effects of the two surgical approaches compare. From one trial in children and adults comparing open with delayed appendicectomy, there was insufficient evidence to show the effect of using either approach on the overall complication rate or the proportion of participants who developed wound infection. Our certainty in a longer stay in hospital stay and time away from normal activities with open appendicectomy is very low. There were no deaths in the study. Quality of life, and pain were not reported in this trial. The other trial in children with appendiceal abscess receiving either early or delayed keyhole appendicectomy did not report on overall complication rates. The trial did not provide enough evidence to show the effect of using either approach on the length of hospital stay among participants. We have very low certainty that children who had early keyhole appendicectomy had better quality of life compared with children who had delayed keyhole appendicectomy. The study did not report if there were any deaths, and did not provide information on pain, or time away from normal activities. At present the benefits and harms of early versus delayed appendicectomy are not well understood because the current information is based upon very low quality evidence. Both trials were at a high risk of bias. Overall, we judged the quality of the evidence to be very low. Thus, further well-designed trials are urgently needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 69 trials with 4860 participants: 2404 given epidural analgesia and 2456 receiving comparators (systemic analgesia, peripheral nerve block, intrapleural analgesia, or wound infiltration). The mean (or median) age of participants varied between 43.5 years and 74.6 years. Surgeries performed were coronary artery bypass grafting or valvular procedures and surgeries for congenital heart disease. We judged that no trials were at low risk of bias for all domains, and that all trials were at unclear/high risk of bias for blinding of participants and personnel taking care of study participants. Epidural analgesia versus systemic analgesia Trials show there may be no difference in mortality at 0 to 30 days (risk difference (RD) 0.00, 95% confidence interval (CI) −0.01 to 0.01; 38 trials with 3418 participants; low-quality evidence), and there may be a reduction in myocardial infarction at 0 to 30 days (RD −0.01, 95% CI −0.02 to 0.00; 26 trials with 2713 participants; low-quality evidence). Epidural analgesia may reduce the risk of 0 to 30 days respiratory depression (RD −0.03, 95% CI −0.05 to −0.01; 21 trials with 1736 participants; low-quality evidence). There is probably little or no difference in risk of pneumonia at 0 to 30 days (RD −0.03, 95% CI −0.07 to 0.01; 10 trials with 1107 participants; moderate-quality evidence), and epidural analgesia probably reduces the risk of atrial fibrillation or atrial flutter at 0 to 2 weeks (RD −0.06, 95% CI −0.10 to −0.01; 18 trials with 2431 participants; moderate-quality evidence). There may be no difference in cerebrovascular accidents at 0 to 30 days (RD −0.00, 95% CI −0.01 to 0.01; 18 trials with 2232 participants; very low-quality evidence), and none of the included trials reported any epidural haematoma events at 0 to 30 days (53 trials with 3982 participants; low-quality evidence). Epidural analgesia probably reduces the duration of tracheal intubation by the equivalent of 2.4 hours (standardized mean difference (SMD) −0.78, 95% CI −1.01 to −0.55; 40 trials with 3353 participants; moderate-quality evidence). Epidural analgesia reduces pain at rest and on movement up to 72 hours after surgery. At six to eight hours, researchers noted a reduction in pain, equivalent to a reduction of 1 point on a 0 to 10 pain scale (SMD −1.35, 95% CI −1.98 to −0.72; 10 trials with 502 participants; moderate-quality evidence). Epidural analgesia may increase risk of hypotension (RD 0.21, 95% CI 0.09 to 0.33; 17 trials with 870 participants; low-quality evidence) but may make little or no difference in the need for infusion of inotropics or vasopressors (RD 0.00, 95% CI −0.06 to 0.07; 23 trials with 1821 participants; low-quality evidence). Epidural analgesia versus other comparators Fewer studies compared epidural analgesia versus peripheral nerve blocks (four studies), intrapleural analgesia (one study), and wound infiltration (one study). Investigators provided no data for pulmonary complications, atrial fibrillation or flutter, or for any of the comparisons. When reported, other outcomes for these comparisons (mortality, myocardial infarction, neurological complications, duration of tracheal intubation, pain, and haemodynamic support) were uncertain due to the small numbers of trials and participants. Compared with systemic analgesia, epidural analgesia may reduce the risk of myocardial infarction, respiratory depression, and atrial fibrillation/atrial flutter, as well as the duration of tracheal intubation and pain, in adults undergoing cardiac surgery. There may be little or no difference in mortality, pneumonia, and epidural haematoma, and effects on cerebrovascular accident are uncertain. Evidence is insufficient to show the effects of epidural analgesia compared with peripheral nerve blocks, intrapleural analgesia, or wound infiltration.\nOutput:\n" }, { "from": "agent", "value": "We included randomized controlled trials involving adults undergoing any type of cardiac surgery under general anaesthesia with or without cardiopulmonary bypass where researchers compared epidural pain relief around the time of surgery against other forms of pain relief. Surgeries performed were coronary artery bypass grafting or valvular procedures and surgeries for congenital heart disease. The average age of participants was between 43 and 75 years. Outcomes were measured up to one year after surgery. We included 69 studies with 4860 participants. Where stated, the studies were funded by governmental resources (five studies), charity (eight), institutional resources (23), or in part by the industry (two). In all, 31 trials did not mention the source of funding. The evidence is current to November 2018. When researchers compared epidural analgesia versus systemic pain relief (e.g. by an analgesic given directly into a vein), they could not detect any difference in the number of deaths in the first 30 days after surgery (38 studies, 3418 participants). There might be a difference in the number of people experiencing heart attacks (26 studies, 2713 participants). These findings were supported by low-quality evidence. We found a small reduction in the risk of respiratory depression with epidural pain relief (21 studies, 1736 participants), but not in the risk of pneumonia (10 studies, 1107 participants) (low- or moderate-quality evidence). The reduced risk of respiratory depression was more obvious when cardiopulmonary bypass was needed for cardiac surgery. Epidural analgesia reduced the risk of atrial fibrillation or atrial flutter early in recovery at zero to two weeks (18 studies, 2431 participants; moderate-quality evidence). The number of cerebrovascular accidents was not clearly different (18 studies, 2232 participants), and no lasting neurological complications or epidural haematomas were reported (53 studies, 3982 participants; very low- or low-quality evidence). Although epidural analgesia may have reduced the duration of tracheal intubation, this was noted mainly in older studies, and clinical practices have changed since that time (40 trials, 3353 participants; moderate-quality evidence). We found only six studies that compared epidural pain relief versus application of local anaesthetic on the body surface to produce peripheral nerve blocks directly into the space around the lungs (intrapleural analgesia) and onto the surgical wound (wound infiltration). These studies provided low- or very low-quality evidence and did not report on many of the outcomes for this review. Study authors reported no heart attacks and no epidural haematomas. We rated the quality of evidence as moderate, low, or very low. We included too few participants in our review to rule out any differences in the number of patient deaths between epidural analgesia and systemic analgesia, nor to see any increase in epidural haematomas." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: A total of 26 trials (among which six had a cross-over design) were included. Among the 6950 randomly assigned participants, 54% (range 0 to100%) were female, mean age was 35 years (range 26 to 45.1), and the mean number of recurrences per year was 11 (range 6.3 to 17.8). Duration of treatment was two to 12 months. Risk of bias was considered high for half of the studies and unclear for the other half. A total of 14 trials compared acyclovir versus placebo, four trials compared valacyclovir versus placebo and 2 trials compared valacyclovir versus no treatment. Three trials compared famciclovir versus placebo. Two trials compared valacyclovir versus famciclovir and one trial compared acyclovir versus valacyclovir versus placebo. We analyzed data from 22 trials for the outcome: risk of having at least one clinical recurrence. We could not obtain the outcome data for four trials. In placebo-controlled trials, there was a low quality evidence that the risk of having at least one clinical recurrence was reduced with acyclovir (nine parallel-group trials, n = 2049; pooled RR 0.48, 95% confidence interval (CI) 0.39 to 0.58), valacyclovir (four trials, n = 1788; pooled RR 0.41, 95% CI 0.24 to 0.69), or famciclovir (two trials, n = 732; pooled RR 0.57, 95% CI 0.50 to 0.64). The six cross-over trials showed larger treatment effects on average than the parallel-group trials. We found evidence of a small-study effect for acyclovir placebo-controlled trials (adjusted pooled RR 0.61, 95% CI 0.49 to 0.75). In analyzing parallel-group trials by daily dose, no clear evidence was found of a dose-response relationship for any drug. In head-to-head trials, the risk of having at least one recurrence was increased with valacyclovir rather than acyclovir (one trial, n = 1345; RR 1.16, 95% CI 1.01 to 1.34) and was not significantly different from that seen with famciclovir as compared with valacyclovir (one trial, n = 320; RR 1.18, 95% CI 0.86 to 1.63). We included 16 parallel-arm trials in a network meta-analysis and we were unable to determine which of the drugs was most effective in reducing the risk of at least one clinical recurrence (after adjustment for small-study effects, pooled RR 0.83, 95% CI 0.61 to 1.11 for valacyclovir vs acyclovir; pooled RR 1.04, 95% CI, 0.71 to 1.49 for famciclovir vs acyclovir; and pooled RR 1.26, 95% CI 0.89 to 1.75 for famciclovir vs valacyclovir). Safety data were sought but were reported as total numbers of adverse events. Owing to risk of bias and inconsistency, there is low quality evidence that suppressive antiviral therapy with acyclovir, valacyclovir or famciclovir in pacients experiencing at least four recurrences of genital herpes per year decreases the number of pacients with at least one recurrence as compared with placebo. Network meta-analysis of the few direct comparisons and the indirect comparisons did not show superiority of one drug over another.\nOutput:\n" }, { "from": "agent", "value": "A total of 26 trials including 6950 patients were included in this review. Fifty-four percent of these patients were female, mean age was 35 years, and mean number of recurrences per year before entry into the trials was 11. Duration of treatment in trials ranged from two to 12 months. A total of 14 trials compared acyclovir versus placebo. Four trials compared valacyclovir versus placebo and two trials compared valacyclovir versus no treatment. Three trials compared famciclovir versus placebo. Two trials compared valacyclovir versus famciclovir, and one trial compared acyclovir versus valacyclovir versus placebo. Among the 26 included trials, 22 declared pharmaceutical company funding. The last search for studies was carried out in February 2014. Suppressive antiviral therapy with acyclovir, valacyclovir, or famciclovir in patients experiencing at least four recurrences per year decreases the number of patients having at least one recurrence compared with placebo. There is no evidence that suggests that any of these drugs is superior to the others. Althought the three antiviral drugs showed better results compared with placebo, we are uncertain as to how much a difference there are likely to make, because of issues with the conduct and reporting of studies, and inconsistency of their results. The quality of the evidence is low and we think that the size of the effects is likely to change with more research. Because few studies compared the three drugs against one other, we are moderately confident in the fact that there is no difference between the three drugs in terms of effectiveness." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The evidence from five trials, involving 952 participants, does not suggest a protective effect of maternal dietary antigen avoidance during pregnancy on the incidence of atopic eczema during the first 18 months of life. Data on allergic rhinitis or conjunctivitis, or both, and urticaria are limited to a single trial each and are insufficient to draw meaningful inferences. Longer-term atopic outcomes have not been reported. The restricted diet during pregnancy was associated with a slightly but statistically significantly lower mean gestational weight gain, a non-significantly higher risk of preterm birth, and a non-significant reduction in mean birthweight. The evidence from two trials, involving 523 participants, did not observe a significant protective effect of maternal antigen avoidance during lactation on the incidence of atopic eczema during the first 18 months or on positive skin-prick tests to cow milk, egg, or peanut antigen at one, two, or seven years. One crossover trial involving 17 lactating mothers of infants with established atopic eczema found that maternal dietary antigen avoidance was associated with a non-significant reduction in eczema severity. Prescription of an antigen avoidance diet to a high-risk woman during pregnancy is unlikely to reduce substantially her child's risk of atopic diseases, and such a diet may adversely affect maternal or fetal nutrition, or both. Prescription of an antigen avoidance diet to a high-risk woman during lactation may reduce her child's risk of developing atopic eczema, but better trials are needed. Dietary antigen avoidance by lactating mothers of infants with atopic eczema may reduce the severity of the eczema, but larger trials are needed.\nOutput:\n" }, { "from": "agent", "value": "We included five trials, involving 952 participants. Trials of mothers' avoidance of milk, eggs, and other potentially 'antigenic' foods during pregnancy or breastfeeding, or both, provide inadequate evidence about whether such avoidance helps prevent atopic eczema or asthma in the child. Women who avoided eating these foods gained significantly less weight during pregnancy in the one trial reporting on this outcome, raising the possibility of adverse nutritional effects on the mother or fetus. Finally, one small trial reported an inconclusive response of breastfed infants with atopic eczema when their mothers avoided consumption of cow milk and egg." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Data from 52 trials and 9387 patients were included. The results for modern regimens containing cisplatin favoured chemotherapy in all comparisons and reached conventional levels of significance when used with radical radiotherapy and with supportive care. Trials comparing surgery with surgery plus chemotherapy gave a hazard ratio of 0.87 (13% reduction in the risk of death, equivalent to an absolute benefit of 5% at 5 years). Trials comparing radical radiotherapy with radical radiotherapy plus chemotherapy gave a hazard ratio 0.87 (13% reduction in the risk of death equivalent to an absolute benefit of 4% at 2 years), and trials comparing supportive care with supportive care plus chemotherapy gave a hazard ratio of 0.73 (27% reduction in the risk of death equivalent to a 10% improvement in survival at one year). The essential drugs needed to achieve these effects were not identified. No difference in the size of effect was seen in any subgroup of patients. In all but the radical radiotherapy setting, older trials using long term alkylating agents tended to show a detrimental effect of chemotherapy. This effect reached conventional significance in the adjuvant surgical comparison. At the outset of this meta-analysis there was considerable pessimism about the role of chemotherapy in the treatment of non-small cell lung cancer. These results offer hope of progress and suggest that chemotherapy may have a role in treating this disease.\nOutput:\n" }, { "from": "agent", "value": "Trials have tried giving chemotherapy (drugs) after these standard treatments to find out whether it can help people to live longer. This review found that giving chemotherapy after either radiotherapy or supportive care did seem to help patients live longer. Giving chemotherapy after radiotherapy to 1000 patients would mean that an extra 40 patients would be expected to be alive 2 years later, than if the chemotherapy was not given. Giving chemotherapy after supportive care to 1000 patients would mean that 100 more would be expected to be alive 2 years later, than if the chemotherapy was not given. Chemotherapy after surgery may also help patients live longer although the evidence to support this is less clear." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Five trials involving 836 participants randomised to peritoneal closure (410 participants) and no peritoneal closure (426 participants) were included in this review. All the trials were at high risk of bias. All the trials included participants undergoing laparotomy (open surgery). Four of the five trials used catgut or chromic catgut for peritoneal closure. Three trials involved vertical incisions and two trials involved transverse incisions. None of the trials reported 30-day mortality. There was no significant difference in the one-year mortality between the two groups (RR 1.11; 95% CI 0.56 to 2.19) in the only trial that reported this outcome. The only serious peri-operative adverse event reported was burst abdomen, which was reported by three trials. Overall, 10/663 (1.5%) of participants developed burst abdomen. There was no significant difference in the proportion of participants who developed burst abdomen between the two groups (RR 0.71; 95% CI 0.22 to 2.35). The same three trials reported the proportion of participants who developed incisional hernia. Details of the follow-up period were only available for one trial, and so we were unable to calculate the incidence rate. Overall, 17/663 (2.5%) of participants developed incisional hernia. There was no significant difference in the proportion of participants who developed incisional hernia between the two groups (RR 0.92; 95% CI 0.37 to 2.28). None of the trials reported quality of life; the incidence rate of, or proportion of participants who developed, intestinal obstruction due to adhesions; or re-operation due to incisional hernia or adhesions. Only one trial reported the length of hospital stay, and this trial did not include readmissions in its calculations. There was no significant difference in the length of hospital stay between the two groups (MD 0.40 days; 95% CI -0.51 to 1.31). There is no evidence for any short-term or long-term advantage in peritoneal closure for non-obstetric operations. If further trials are performed on this topic, they should have an adequate period of follow-up and adequate measures should be taken to ensure that the results are not subject to bias.\nOutput:\n" }, { "from": "agent", "value": "We identified five trials involving 836 participants who had open abdominal operations. Peritoneal closure was done in 410 participants and not done in 426. All trials had a high risk of bias. Only one trial reported the proportion of participants who died up to one year after the operation, and there was no significant difference between the closure and non-closure groups. Three trials reported major wound breakdown (burst abdomen), which requires emergency surgery. Overall, 10/663 participants (1.5%) developed burst abdomen, with no significant difference in proportions between the two groups. Three trials reported minor wound breakdown (incisional hernia), that may require surgery. Overall, 17/663 participants (2.5%) developed incisional hernia; again there was no significant difference between the two groups. None of the trials reported on important outcomes, such as quality of life; the occurrence of intestinal obstruction (caused by intestines sticking to themselves and the abdominal wall (adhesions)); or the proportion of participants who had surgery to fix incisional hernia or adhesions. Only one trial reported length of hospital stay, and showed no significant difference between the groups, but did not include readmissions in its calculations. There does not appear to be any evidence for a short-term or long-term advantage in peritoneal closure in operations not related to childbirth. However, the trials were at high risk of bias, which can lead to false conclusions. Interestingly, our findings are similar to those of another research group who performed a similar review for operations related to childbirth." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included three studies involving 470 participants. These trials were of limited comparability evaluating an OHC education training programme, a decontamination gel and a ventilator-associated pneumonia bundle of care augmented with an OHC component by comparing them to a deferred intervention, a placebo gel or standard care respectively. The OHC educational intervention demonstrated a significant reduction in denture plaque scores up to six months (P < 0.00001) after the intervention but not dental plaque. Staff knowledge (P = 0.0008) and attitudes (P = 0.0001) towards oral care also improved. The decontamination gel reduced the incidence of pneumonia amongst the intervention group (P = 0.03). Based on two trials involving a small number of stroke survivors, OHC interventions can improve staff knowledge and attitudes, the cleanliness of patients' dentures and reduce the incidence of pneumonia. Improvements in the cleanliness of patients teeth were not observed. Further evidence relating to staff-led oral care interventions is severely lacking.\nOutput:\n" }, { "from": "agent", "value": "This review of three studies involving 470 participants found little evidence of how this care is best delivered. Information on a small number of nursing home residents who had a stroke (67 participants from a larger trial) showed that training nursing staff improved their knowledge of oral care and resulted in improved oral hygiene in their patients. Another trial demonstrated the beneficial impact of a decontamination gel on the incidence of pneumonia amongst patients in a stroke ward. However, there was no other information on how best to provide oral hygiene and more studies are urgently needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Fifteen studies (733 patients) were suitable for analysis. All studies were small and had variable methodology. Fish oil did not significantly affect patient or graft survival, acute rejection rates, or calcineurin inhibitor toxicity when compared to placebo. Overall SCr was significantly lower in the fish oil group compared to placebo (5 studies, 237 participants: MD -30.63 µmol/L, 95% CI -59.74 to -1.53; I2 = 88%). In the subgroup analysis, this was only significant in the long-course (six months or more) group (4 studies, 157 participants: MD -37.41 µmol/L, 95% CI -69.89 to -4.94; I2 = 82%). Fish oil treatment was associated with a lower diastolic blood pressure (4 studies, 200 participants: MD -4.53 mm Hg, 95% CI -7.60 to -1.45) compared to placebo. Patients receiving fish oil for more than six months had a modest increase in HDL (5 studies, 178 participants: MD 0.12 mmol/L, 95% CI 0.03 to 0.21; I2 = 47%) compared to placebo. Fish oil effects on lipids were not significantly different from low-dose statins. There was insufficient data to analyse cardiovascular outcomes. Fishy aftertaste and gastrointestinal upset were common but did not result in significant patient drop-out. There is insufficient evidence from currently available RCTs to recommend fish oil therapy to improve kidney function, rejection rates, patient survival or graft survival. The improvements in HDL cholesterol and diastolic blood pressure were too modest to recommend routine use. To determine a benefit in clinical outcomes, future RCTs will need to be adequately powered with these outcomes in mind.\nOutput:\n" }, { "from": "agent", "value": "This review set out to assess any benefit or harm in using fish oil to reduce the risk of kidney damage and heart disease in people who have had a kidney transplant and are receiving standard drugs to prevent rejection. Information from 15 studies was used and showed that fish oils provide a slight improvement in HDL cholesterol and diastolic blood pressure. These studies did not provide enough information on the differences in the risk of death, heart disease, kidney transplant rejection or kidney function between patients receiving fish oils and those receiving placebo. There appeared to be no harmful effects of taking fish oil. The benefits of taking fish oil after a kidney transplant are a mild improvement in some heart disease risk factors. There was not enough information to show any benefit in preventing heart disease or reduction in kidney function. Larger, better studies are needed before regular use of fish oil can be recommended." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 16 studies (involving 13,123 participants) in this systematic review, two of which were of high quality. These two studies showed that nicotine sublingual tablet and varenicline increased the quit rate over placebo (risk ratio (RR) 2.60 (95% confidence interval (CI) 1.29 to 5.24) and RR 3.34 (95% CI 1.88 to 5.92)). Pooled results of two studies also showed a positive effect of bupropion compared with placebo (RR 2.03 (95% CI 1.26 to 3.28)). When pooling these four studies, we found high-quality evidence for the effectiveness of pharmacotherapy plus high-intensity behavioural treatment compared with placebo plus high-intensity behavioural treatment (RR 2.53 (95% CI 1.83 to 3.50)). Furthermore, we found some evidence that high-intensity behavioural treatment increased abstinence rates when compared with usual care (RR 25.38 (95% CI 8.03 to 80.22)) or low-intensity behavioural treatment (RR 2.18 (95% CI 1.05 to 4.49)). Finally, the results showed effectiveness of various combinations of psychosocial and pharmacological interventions. We found high-quality evidence in a meta-analysis including four (1,540 participants) of the 16 included studies that a combination of behavioural treatment and pharmacotherapy is effective in helping smokers with COPD to quit smoking. Furthermore, we conclude that there is no convincing evidence for preferring any particular form of behavioural or pharmacological treatment.\nOutput:\n" }, { "from": "agent", "value": "We looked for studies that included adult men and women who were current smokers and had a diagnosis of COPD. We included studies that assessed the effectiveness of any behavioural support or medication, or both as an aid to quit smoking. We included studies that compared different types of treatment or compared treatment to stop smoking with no treatment or 'usual care'. We only included studies that reported how many people had stopped smoking after at least six months of follow-up. We carried out the most recent search for studies in March 2016. We found high-quality evidence from a collection of four (1,540 participants) of the total 16 included studies (13,123 participants) in this review. Overall, we found evidence that smokers with COPD who receive a combination of high-intensity behavioural support and medication are more than twice as likely to quit as people who receive behavioural support alone. We found no clear evidence that one particular form of behavioural support or medication is better than another. It is still unclear whether smokers with COPD are different from smokers without COPD with regard to which treatments work best to help them stop smoking. We are quite confident in the finding that a combination of behavioural support and medication works better than behavioural support alone. However, we were not able to combine the results of many of the studies because the treatments or the outcomes of the studies were too different from each other." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Seven randomised, controlled trials encompassing 842 patients undergoing SGIA versus DGIA were retrieved from the electronic databases. There were 408 patients in the SGIA group and 432 patients in the DGIA group. All included studies were small, with sample sizes ranging from 60 to 172. There was no heterogeneity among the included trials. Therefore, in the fixed effects model, incidence of anastomotic dehiscence, peri-operative complications and mortality was statistically equivalent between two techniques of GIA. Average hospital stay following SGIA and DGIA was also comparable. However, SGIA was superior in terms of shorter operative time. Sensitivity analysis of relatively good quality and poor quality trials supported same conclusion. SGIA can be performed quicker as compared to double layer GIA. SGIA is comparable to DGIA in terms of anastomotic leak, peri-operative complications, mortality and hospital stay. SGIA may routinely be used for GIA following bowel resection. However, since this conclusion is derived from smaller number of patients recruited in relatively moderate quality trials, further trials should be aimed to reduce the limitations of this review.\nOutput:\n" }, { "from": "agent", "value": "This review concludes that single layer anastomosis is comparable to double layer anastomosis in terms of anastomotic leak, peri-operative complications, death rate and hospital stay. Single layer anastomosis consumes shorter operative time as compared to double layer. Therefore, single layer anastomosis may routinely be used for the anastomosis of gastrointestinal tract following bowel resection. However, since this conclusion is derived from smaller number of patients recruited in relatively moderate quality trials, further trials should be aimed to reduce the limitations of this review." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 13 studies, with a total 467 participants, testing a range of different interventions. Outcome measures included 36 measures of sensory impairment and 13 measures of upper limb function. All but two studies had unclear or high risk of bias. While there is insufficient evidence to reach conclusions about the effects of interventions included in this review, three studies provided preliminary evidence for the effects of some specific interventions, including mirror therapy for improving detection of light touch, pressure and temperature pain; a thermal stimulation intervention for improving rate of recovery of sensation; and intermittent pneumatic compression intervention for improving tactile and kinesthetic sensation. We could not perform meta-analysis due to a high degree of clinical heterogeneity in both interventions and outcomes. Multiple interventions for upper limb sensory impairment after stroke are described but there is insufficient evidence to support or refute their effectiveness in improving sensory impairment, upper limb function, or participants' functional status and participation. There is a need for more well-designed, better reported studies of sensory rehabilitation.\nOutput:\n" }, { "from": "agent", "value": "We found 13 studies involving 467 participants that tested different treatments for sensory loss. There is limited evidence that these treatments may be effective. No more than one study examined each particular intervention, frequently the studies were of poor quality and lacked sufficient information. Further research is needed before clear recommendations can be made." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included one trial with a total of 60 children with a diagnosis of ASD who randomly received hyperbaric oxygen therapy or a sham treatment. Using GRADE criteria, we rated the quality of the evidence as low because of the small sample size and wide confidence intervals (CIs). Other problems included selection bias and short duration or follow-up. Overall, study authors reported no improvement in social interaction and communication, behavioral problems, communication and linguistic abilities, or cognitive function. With regard to the safety of hyperbaric oxygen therapy (adverse events), they reported minor-grade ear barotrauma events. Investigators found significant differences between groups in total number of side effect events (Peto odds ratio (OR) 3.87, 95% CI 1.53 to 9.82) and in the number of children who experienced side effects (Peto OR 4.40, 95% CI 1.33 to 14.48). To date, there is no evidence that hyperbaric oxygen therapy improves core symptoms and associated symptoms of ASD. It is important to note that adverse effects (minor-grade ear barotrauma events) can occur. Given the absence of evidence of effectiveness and the limited biological plausibility and possible adverse effects, the need for future RCTs of hyperbaric oxygen therapy must be carefully considered.\nOutput:\n" }, { "from": "agent", "value": "We searched electronic databases and identified randomized controlled trials (in which participants are randomly allocated to one of two or more treatment groups) consisting of participants who received high-pressure oxygen therapy or room air or no treatment as a control. The evidence is current up to December 2015. We found a single, small study of 60 children that evaluated high-pressure oxygen therapy for ASD. There was no evidence that high-pressure oxygen therapy improved social interaction, behavioral problems, speech or language communication, or mental function in children with ASD. However, children who received high-pressure (hyperbaric) oxygen therapy showed an increased occurrence of ear barotrauma events when compared with those in the control group. The quality of the evidence is low. Evidence is insufficient to confirm that high-pressure oxygen is an effective treatment for individuals with ASD." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 25 RCTs (1688 participants) in this review (23 trials combined within meta-analyses). In 18 studies, participants underwent total knee arthroplasty (TKA), whereas seven trials investigated patients undergoing arthroscopic knee surgery. We identified 11 studies awaiting classification and 11 ongoing studies. We investigated the following comparisons. ACB versus sham treatment We included eight trials for this comparison. We found no significant differences in postoperative pain intensity at rest (2 hours: standardized mean difference (SMD) -0.56, 95% confidence interval (CI) -1.20 to 0.07, 4 trials, 208 participants, low-quality evidence; 24 hours: SMD -0.49, 95% CI -1.05 to 0.07, 6 trials, 272 participants, low-quality evidence) or during movement (2 hours: SMD -0.59, 95% CI -1.5 to 0.33; 3 trials, 160 participants, very low-quality evidence; 24 hours: SMD 0.03, 95% CI -0.26 to 0.32, 4 trials, 184 participants, low-quality evidence). Furthermore, they noted no evidence of a difference in postoperative nausea between groups (24 hours: risk ratio (RR) 1.91, 95% CI 0.48 to 7.58, 3 trials, 121 participants, low-quality evidence). One trial reported that no accidental falls occurred 24 hours postoperatively (low-quality evidence). ACB versus femoral nerve block We included 15 RCTs for this comparison. We found no evidence of a difference in postoperative pain intensity at rest (2 hours: SMD -0.74, 95% CI -1.76 to 0.28, 5 trials, 298 participants, low-quality evidence; 24 hours: SMD 0.04, 95% CI -0.09 to 0.18, 12 trials, 868 participants, high-quality evidence) or during movement (2 hours: SMD -0.47, 95% CI -1.86 to 0.93, 2 trials, 88 participants, very low-quality evidence; 24 hours: SMD 0.56, 95% CI -0.00 to 1.12, 9 trials, 576 participants, very low-quality evidence). They noted no evidence of a difference in postoperative nausea (24 hours: RR 1.22, 95% CI 0.42 to 3.54, 2 trials, 138 participants, low-quality evidence) and no evidence that the rate of accidental falls during postoperative care was significantly different between groups (24 hours: RR 0.20, 95% CI 0.04 to 1.15, 3 trials, 172 participants, low-quality evidence). We are currently uncertain whether patients treated with ACB suffer from lower pain intensity at rest and during movement, fewer opioid-related adverse events, and fewer accidental falls during postoperative care compared to patients receiving sham treatment. The same holds true for the comparison of ACB versus femoral nerve block focusing on postoperative pain intensity. The overall evidence level was mostly low or very low, so further research might change the conclusion. The 11 studies awaiting classification and the 11 ongoing studies, once assessed, may alter the conclusions of this review.\nOutput:\n" }, { "from": "agent", "value": "We included 25 clinical studies in which people are randomly put into one of two or more treatment groups (called 'randomized controlled trials'), with results reported from a total of 1688 participants (929 females, 759 males). Participants were 29 to 72 years old. Eight trials compared participants receiving adductor canal block against patients receiving saline. A total of 15 RCTs compared adductor canal block versus femoral nerve block. The evidence is current to October 2018. No trial was funded by industry. We are uncertain whether patients treated with adductor canal block have lower pain intensity at rest or during movement (e.g. walking) compared with those who received only saline. It is unclear whether rates of adverse events after taking opioids (e.g. nausea) or after accidental falls during postoperative care are lower. It is also uncertain whether patients receiving adductor canal block show different postoperative pain intensity at rest and during movement compared to those treated with femoral nerve block. We noted no differences in adverse events after taking opioids and after accidental falls. We rated the quality of evidence for many outcomes as low or very low. In contrast, we rated pain at rest (at 24 hours) as high-quality evidence." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 14 studies with 923 participants in this review. Studies took place in Australia, Canada, the UK, and the USA. Six of the 14 included studies were funded by government agencies and one was funded by a university grant. The rest were funded by charitable foundations or trusts. Each study compared phonics training alone, or in conjunction with one other reading-related skill, to either no training (i.e. treatment as usual) or alterative training (e.g. maths). Participants were English-speaking children or adolescents, of low and middle socioeconomic status, whose reading was one year, one grade, or one standard deviation below the level expected for their age or grade for no known reason. Phonics training varied between studies in intensity (up to four hours per week), duration (up to seven months), training group size (individual and small groups), and delivery (human and computer). We measured the effect of phonics training on seven primary outcomes (mixed/regular word reading accuracy, non-word reading accuracy, irregular word reading accuracy, mixed/regular word reading fluency, non-word reading fluency, reading comprehension, and spelling). We judged all studies to be at low risk of bias for most risk criteria, and used the GRADE approach to assess the quality of the evidence. There was low-quality evidence that phonics training may have improved poor readers' accuracy for reading real and novel words that follow the letter-sound rules (standardised mean difference (SMD) 0.51, 95% confidence interval (CI) 0.13 to 0.90; 11 studies, 701 participants), and their accuracy for reading words that did not follow these rules (SMD 0.67, 95% CI 0.26 to 1.07; 10 studies, 682 participants). There was moderate-quality evidence that phonics training probably improved English-speaking poor readers' fluency for reading words that followed the letter-sounds rules (SMD 0.45, 95% CI 0.19 to 0.72; 4 studies, 224 participants), and non-word reading fluency (SMD 0.39, 95% CI 0.10 to 0.68; 3 studies, 188 participants), as well as their accuracy for reading words that did not follow these rules (SMD 0.84, 95% CI 0.30 to 1.39; 4 studies, 294 participants). In addition, there was low-quality evidence that phonics training may have improved poor readers' spelling (SMD 0.47, 95% CI –0.07 to 1.01; 3 studies, 158 participants), but only slightly improve their reading comprehension (SMD 0.28, 95% CI –0.07 to 0.62; 5 studies, 343 participants). Phonics training appears to be effective for improving literacy-related skills, particularly reading fluency of words and non-words, and accuracy of reading irregular words. More studies are needed to improve the precision of outcomes, including word and non-word reading accuracy, reading comprehension, spelling, letter-sound knowledge, and phonological output. More data are also needed to determine if phonics training in English-speaking poor readers is moderated by factors such as training type, intensity, duration, group size, or administrator.\nOutput:\n" }, { "from": "agent", "value": "The search, updated in May 2018, identified 14 studies that tested phonics training in 923 English-speaking poor readers. The studies took place in Australia, Canada, the UK, and the USA. Six of the 14 included studies were funded by government agencies and one was funded by a university grant. The rest were funded by charitable foundations or trusts. Each study compared phonics training alone, or with one other reading-related skill, to either no training (i.e. treatment as usual) or alterative training (e.g. maths). Participants were English-speaking children or adolescents, of low and middle socioeconomic status, whose reading was one year, one grade, or one standard deviation (distance from the average) below the level expected for their age or grade for no known reason. Phonics training varied between studies in frequency (up to four hours per week), duration (up to seven months), training group size (individual and small groups), and delivery (human and computer). We measured the effect of phonics training on poor readers' ability to read words and novel words (non-words) accurately and fluently, as well as their comprehension of text, and their knowledge of letter-sound rules (letter-sound knowledge) and speech sounds (phonological output). We found that phonics training in English-speaking poor readers probably improved irregular word reading accuracy, mixed/regular word reading fluency, and non-word reading fluency. It may also have improved mixed/regular word reading accuracy, non-word reading accuracy, reading comprehension, spelling, letter-sound knowledge, and phonological output. The overall quality of the evidence ranged from low to moderate. This was primarily due to large differences in the size of phonics-training effects between studies. More studies are needed to improve the precision of the outcomes. The evidence suggests that phonics training can improve literacy in English-speaking poor readers. The positive effects of phonics training on all reading-related outcomes suggests that phonics training is not harmful for poor readers." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The review included five studies with 430 participants. Studies varied in the preparations of valproate, mean doses (480 mg/day to 1000 mg/day), duration of treatment (three weeks to six weeks), and outcome measures used. The studies were generally well conducted although some methodological information was missing and one study was at high risk of attrition bias. The quality of evidence related to our primary efficacy outcome of agitation varied from moderate to very low. We found moderate-quality evidence from two studies that measured behaviour with the total Brief Psychiatric Rating Scale (BPRS) score (range 0 to 108) and with the BPRS agitation factor (range 0 to 18). They found that there was probably little or no effect of valproate treatment over six weeks (total BPRS: mean difference (MD) 0.23, 95% confidence interval (CI) –2.14 to 2.59; 202 participants, 2 studies; BPRS agitation factor: MD –0.67, 95% CI –1.49 to 0.15; 202 participants, 2 studies). Very low-quality evidence from three studies which measured agitation with the Cohen-Mansfield Agitation Index (CMAI) were consistent with a lack of effect of valproate treatment on agitation. There was variable quality evidence on other behaviour outcomes reported in single studies of no difference between groups or a benefit for the placebo group. Three studies, which measured cognitive function using the Mini-Mental State Examination (MMSE), found little or no effect of valproate over six weeks, but we were uncertain about this result because the quality of the evidence was very low. Two studies that assessed functional ability using the Physical Self-Maintenance Scale (PSMS) (range 6 to 30) found that there was probably slightly worse function in the valproate-treated group, which was of uncertain clinical importance (MD 1.19, 95% CI 0.40 to 1.98; 203 participants, 2 studies; moderate-quality evidence). Analysis of adverse effects and serious adverse events (SAE) indicated a higher incidence in valproate-treated participants. A meta-analysis of three studies showed that there may have been a higher rate of adverse effects among valproate-treated participants than among controls (odds ratio (OR) 2.02, 95% CI 1.30 to 3.14; 381 participants, 3 studies, low-quality evidence). Pooled analysis of the number of SAE for the two studies that reported such data indicated that participants treated with valproate preparations were more likely to experience SAEs (OR 4.77, 95% CI 1.00 to 22.74; 228 participants, 2 studies), but the very low quality of the data made it difficult to draw any firm conclusions regarding SAEs. Individual adverse events that were more frequent in the valproate-treated group included sedation, gastrointestinal symptoms (nausea, vomiting, and diarrhoea), and urinary tract infections. This updated review corroborates earlier findings that valproate preparations are probably ineffective in treating agitation in people with dementia, but are associated with a higher rate of adverse effects, and possibly of SAEs. On the basis of this evidence, valproate therapy cannot be recommended for management of agitation in dementia. Further research may not be justified, particularly in light of the increased risk of adverse effects in this often frail group of people. Research would be better focused on effective non-pharmacological interventions for this patient group, or, for those situations where medication may be needed, further investigation of how to use other medications as effectively and safely as possible.\nOutput:\n" }, { "from": "agent", "value": "Studies measured agitated behaviour with various scales and the reliability of the evidence for the different scales ranged from moderate to very low. Overall, we found no evidence that valproate preparations improved behaviour, or specifically, agitated behaviour. We found that valproate preparations probably had little or no effect on participants' ability to perform daily activities. We could not be sure whether they had an effect on cognition (thinking and remembering) because the reliability of the evidence was very low. We found low-reliability evidence from three studies that participants taking valproate may be more likely than those taking placebo to experience harmful effects. We could not be as certain about differences in serious harms, such as serious illness or admission to hospital, but data from two studies suggested that these may be more common in the participants taking valproate. Some of the side effects associated with valproate were sleepiness, feeling sick, being sick, watery stools, and urinary tract infections. We only identified five relatively small studies for inclusion in this review. They varied in their methods, type of medicine and its dose, duration of treatment, and scales used to make measurements. This limited our ability to pool data across studies. However, we could be moderately confident in the conclusion that valproate preparations do not improve agitated behaviour in dementia. They may also be associated with harmful effects." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included six trials with 596 participants in this review. All studies had a randomised controlled parallel group design, with two conducted in the UK, three in the US and one in Israel. Meta-analyses were performed to pool data on response and remission from studies comparing antidepressants with placebo. No meta-analyses could be conducted for other comparisons due to the small number of trials identified. Four studies compared selective serotonin reuptake inhibitors (SSRIs) with placebo (two using sertraline, one using paroxetine and one using fluoxetine; 233 participants in total). In two of these studies both the experimental and placebo groups also received psychological therapy. Pooled risk ratios based on data from three of these studies (146 participants) showed that women randomised to SSRIs had higher rates of response and remission than those randomised to placebo (response: RR 1.43, 95% CI 1.01 to 2.03; remission: RR 1.79, 95% CI 1.08 to 2.98); the fourth study did not report data on response or remission. One study (254 participants) compared antidepressant treatment with treatment as usual (for the first four weeks) followed by listening visits. The study found significantly higher rates of improvement in the antidepressant group than treatment-as-usual group after the first four weeks, but no difference between antidepressants and listening visits at the later follow-up. In addition, one study comparing sertraline with nortriptyline (a tricyclic antidepressant) found no difference in effectiveness (109 participants). Side effects were experienced by a substantial proportion of women, but there was no evidence of a meaningful difference in the number of adverse effects between treatment arms in any study. There were very limited data on adverse effects experienced by breastfed infants, with no long-term follow-up. All but one of the studies were assessed as being at high or uncertain risk of attrition bias and selective outcome reporting. In particular, one of the placebo-controlled studies had over 50% drop-out. The evidence base for this review was very limited, with a small number of studies and little information on a number of important outcomes, particularly regarding potential effects on the child. Risk of bias, for example from high attrition rates, as well as low representativeness of participants (e.g. exclusion of women with severe or chronic depression in several trials) also limit the conclusions that can be drawn. Pooled estimates for response and remission found that SSRIs were significantly more effective than placebo for women with postnatal depression. However the quality of evidence contributing to this comparison was assessed as very low owing to the small sample size for this comparison (146 participants from three studies), the risk of bias in included studes and the inclusion of one study where all participants in both study arms additionally received psychological therapy. There was insufficient evidence to conclude whether, and for whom, antidepressant or psychological/psychosocial treatments are more effective, or whether some antidepressants are more effective or better tolerated than others. There is also inadequate evidence on whether the benefits of antidepressants persist beyond eight weeks or whether they have short- or long-term adverse effects on breastfeeding infants. Professionals treating women with severe depression in the postnatal period will need to draw on other evidence, including trials among general adult populations and observational studies of antidepressant safety when breastfeeding (although the potential for confounding in non-randomised studies must be considered). More RCTs are needed with larger sample sizes and longer follow-up, including assessment of the impact on the child and safety of breastfeeding. Further larger-scale trials comparing antidepressants with alternative treatment modalities are also required.\nOutput:\n" }, { "from": "agent", "value": "The quality of evidence from this review was assessed as being very low quality due to the small number of studies, risk of bias in the included studies (in particular, high proportions of participants dropped out) and the fact that many studies excluded women with chronic (i.e. long lasting) or severe depression, or both. We were able to combine data from three studies comparing a type of commonly used antidepressant called selective serotonin reuptake inhibitors (SSRIs) with placebo. The results showed that women with postnatal depression who were given SSRIs were more likely to improve or recover than those given placebo. We were unable to combine the data from studies comparing antidepressants with other treatments or treatment as usual due to the very small number of studies identified for these comparisons. There was insufficient evidence to conclude whether, and for whom, antidepressant or psychosocial/psychological treatments are more effective, or whether some antidepressants are more effective or better tolerated (or both) than others. Conclusions were also limited by the lack of data on long-term follow-up, the safety of breastfeeding or child outcomes. Larger studies need to be done, and treatment decisions for women with postnatal depression will need to use evidence from other sources such as trials in general adult populations and observational studies of antidepressant safety in the postnatal period. The review authors recommend that future studies in this area should include women with severe postnatal depression, long-term follow-up on psychiatric symptoms and quality of life in mothers who have been treated for postnatal depression. In addition, more evidence is needed on outcomes for infants, particularly with regards to the safety of breastfeeding and effect of treatment for postnatal depression on the maternal-infant relationship." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Seven trials involving a total of 266 participants were included. Four trials studied the effects of NSAIDs in chronic CMO while the other three examined the effect of NSAIDs in acute CMO. Of the studies examining chronic CMO, one study enrolled 120 participants, but the remainder had 34 or fewer participants. Four different NSAIDs were used and administered in different ways. Indomethacin was used orally and was found to be ineffective for chronic CMO in one trial. Topical fenoprofen appeared effective but not statistically significantly so for chronic CMO in another small trial. Treatment with topical 0.5% ketorolac for chronic CMO was found to be effective in two trials. Three trials examined the effect of topical NSAIDs on acute CMO. The comparisons among these studies were of an NSAID to placebo, prednisolone or another NSAID. The study design differed between the studies in other important aspects thus they could not be combined in a meta-analysis. This review found two trials which showed that topical NSAID (0.5% ketorolac tromethamine ophthalmic solution) has a positive effect on chronic CMO and two trials which revealed no significant difference between comparative groups. As such, the effects of NSAIDs in acute and chronic CMO remain unclear and needs further investigation.\nOutput:\n" }, { "from": "agent", "value": "This review included seven randomised controlled trials with a total of 266 participants. Four trials studied the effects of non-steroidal anti-inflammatory agents (NSAIDs) in chronic CMO while the other three examined the effect of NSAIDs in acute CMO. This review found two trials which showed that topical NSAID (0.5% ketorolac tromethamine ophthalmic solution) has a positive effect on chronic CMO and a third trial which was supportive of this finding (albeit not statistically significantly so). One study suggested no effect and our review suggests further work is needed for a more conclusive decision regarding use of NSAIDS in chronic CMO. Similarly, the effects of NSAIDs in acute CMO remain unclear and this too needs further investigation." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Three studies with 606 participants compared mirtazapine with placebo (but not other drugs) over seven to 13 weeks. Two studies were at unclear or high risk of bias in six or seven of eight domains. We judged the evidence for all outcomes to be low- or very low-quality because of poor study quality, indirectness, imprecision, risk of publication bias, and sometimes low numbers of events. There was no difference between mirtazapine and placebo for any primary outcome: participant-reported pain relief of 50% or greater (22% versus 16%; RD 0.05, 95% confidence interval (CI) -0.01 to 0.12; three studies with 591 participants; low-quality evidence); no data available for PGIC; only a single serious adverse event for evaluation of safety (RD -0.00, 95% CI -0.01 to 0.02; three studies with 606 participants; very low-quality evidence); and tolerability as frequency of dropouts due to adverse events (3% versus 2%; RD 0.00, 95% CI -0.02 to 0.03; three studies with 606 participants; low-quality evidence). Mirtazapine showed a clinically-relevant benefit compared to placebo for some secondary outcomes: participant-reported pain relief of 30% or greater (47% versus 34%; RD 0.13, 95% CI 0.05 to 0.21; number needed to treat for an additional beneficial outcome (NNTB) 8, 95% CI 5 to 20; three studies with 591 participants; low-quality evidence); participant-reported mean pain intensity (SMD -0.29, 95% CI -0.46 to -0.13; three studies with 591 participants; low-quality evidence); and participant-reported sleep problems (SMD -0.23, 95% CI -0.39 to -0.06; three studies with 573 participants; low-quality evidence). There was no benefit for improvement of participant-reported improvement of HRQoL of 20% or greater (58% versus 50%; RD 0.08, 95% CI -0.01 to 0.16; three studies with 586 participants; low-quality evidence); participant-reported fatigue (SMD -0.02, 95% CI -0.19 to 0.16; two studies with 533 participants; low-quality evidence); participant-reported negative mood (SMD -0.67, 95% CI -1.44 to 0.10; three studies with 588 participants; low-quality evidence); or withdrawals due to lack of efficacy (1.5% versus 0.1%; RD 0.01, 95% CI -0.01 to 0.02; three studies with 605 participants; very low-quality evidence). There was no difference between mirtazapine and placebo for participants reporting any adverse event (76% versus 59%; RD 0.12, 95 CI -0.01 to 0.26; three studies with 606 participants; low-quality evidence). There was a clinically-relevant harm with mirtazapine compared to placebo: in the number of participants with somnolence (42% versus 14%; RD 0.24, 95% CI 0.18 to 0.30; number needed to treat for an additional harmful outcome (NNTH) 5, 95% CI 3 to 6; three studies with 606 participants; low-quality evidence); weight gain (19% versus 1%; RD 0.17, 95% CI 0.11 to 0.23; NNTH 6, 95% CI 5 to 10; three studies with 606 participants; low-quality evidence); and elevated alanine aminotransferase (13% versus 2%; RD 0.13, 95% CI 0.04 to 0.22; NNTH 8, 95% CI 5 to 25; two studies with 566 participants; low-quality evidence). Studies demonstrated no benefit of mirtazapine over placebo for pain relief of 50% or greater, PGIC, improvement of HRQoL of 20% or greater, or reduction of fatigue or negative mood. Clinically-relevant benefits were shown for pain relief of 30% or greater, reduction of mean pain intensity, and sleep problems. Somnolence, weight gain, and elevated alanine aminotransferase were more frequent with mirtazapine than placebo. The quality of evidence was low or very low, with two of three studies of questionable quality and issues over indirectness and risk of publication bias. On balance, any potential benefits of mirtazapine in fibromyalgia were outweighed by its potential harms, though, a small minority of people with fibromyalgia might experience substantial symptom relief without clinically-relevant adverse events.\nOutput:\n" }, { "from": "agent", "value": "In July 2018 we searched for clinical trials where mirtazapine was used to treat fibromyalgia in adults. We found three studies with 606 participants. Studies were seven to 13 weeks long. They compared mirtazapine 15 mg to 45 mg daily against a fake medication (placebo). There was no difference between mirtazapine and placebo for any primary outcome: mirtazapine and placebo reduced pain by 50% in two of 10 people (low-quality evidence). Only one single serious adverse event was available for evaluation of safety (very low-quality evidence). Three of 10 participants with mirtazapine and two of 10 participants with placebo dropped out of the trial due to side effects (low-quality evidence). Mirtazapine reduced pain by 30% or more in five out of 10 people, compared with three out of 10 with placebo (low-quality evidence). It was also better for average pain intensity (low-quality evidence) and sleep problems (low-quality evidence). Mirtazapine was not better than placebo in reducing fatigue, depression, or improving health-related quality of life (low-quality evidence). Mirtazapine and placebo were no different in how many participants experienced a side effect (low-quality evidence). People dropped out at the same rate with mirtazapine and placebo or because they felt the drug did not work (low-quality evidence). For some side effects, mirtazapine was worse than placebo. This was true for drowsiness (4 out of 10 with mirtazapine, 1 out of 10 with placebo), weight gain (2 out of 10 with mirtazapine, 0 out of 10 with placebo), and high liver enzymes (1 out of 10 with mirtazapine, 0 out of 10 with placebo) (low-quality evidence). Two of the studies were of poor quality. We rated the quality of the evidence using four levels: very low, low, moderate, or high. Very low-quality evidence means that we are very uncertain about the results. High quality evidence means that we are very confident in the results. We judged that the evidence was mostly of low-quality, which means that while the research provides some indication of the likely effect, the true effect may be substantially different. The main issues were poor study quality, decisions about the types of people included in the studies, risk of important information not being published, and sometimes low numbers of events." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Six treatment trials involving 1906 children with clinical influenza and 450 children with influenza diagnosed on rapid near-patient influenza testing were included. Of these 2356 children, 1255 had laboratory-confirmed influenza. Three prophylaxis trials involving 863 children exposed to influenza were also included. In children with laboratory-confirmed influenza oseltamivir reduced median duration of illness by 36 hours (26%, P < 0.001). One trial of oseltamivir in children with asthma who had laboratory-confirmed influenza showed only a small reduction in illness duration (10.4 hours, 8%), which was not statistically significant (P = 0.542). Laninamivir octanoate 20 mg reduced symptom duration by 2.8 days (60%, P < 0.001) in children with oseltamivir-resistant influenza A/H1N1. Zanamivir reduced median duration of illness by 1.3 days (24%, P < 0.001). Oseltamivir significantly reduced acute otitis media in children aged one to five years with laboratory-confirmed influenza (risk difference (RD) -0.14, 95% confidence interval (CI) -0.24 to -0.04). Prophylaxis with either zanamivir or oseltamivir was associated with an 8% absolute reduction in developing influenza after the introduction of a case into a household (RD -0.08, 95% CI -0.12 to -0.05, P < 0.001). The adverse event profile of zanamivir was no worse than placebo but vomiting was more commonly associated with oseltamivir (number needed to harm = 17, 95% CI 10 to 34). The adverse event profiles of laninamivir octanoate and oseltamivir were similar. Oseltamivir and zanamivir appear to have modest benefit in reducing duration of illness in children with influenza. However, our analysis was limited by small sample sizes and an inability to pool data from different studies. In addition, the inclusion of data from published trials only may have resulted in significant publication bias. Based on published trial data, oseltamivir reduces the incidence of acute otitis media in children aged one to five years but is associated with a significantly increased risk of vomiting. One study demonstrated that laninamivir octanoate was more effective than oseltamivir in shortening duration of illness in children with oseltamivir-resistant influenza A/H1N1. The benefit of oseltamivir and zanamivir in preventing the transmission of influenza in households is modest and based on weak evidence. However, the clinical efficacy of neuraminidase inhibitors in 'at risk' children is still uncertain. Larger high-quality trials are needed with sufficient power to determine the efficacy of neuraminidase inhibitors in preventing serious complications of influenza (such as pneumonia or hospital admission), particularly in 'at risk' groups.\nOutput:\n" }, { "from": "agent", "value": "This update reviews the randomised controlled trial evidence of a class of drugs called the neuraminidase inhibitors in treating and preventing influenza in children. Neuraminidase inhibitors work against influenza by preventing viruses from being released from infected cells and subsequently infecting further cells. Oseltamivir (Tamiflu), an oral medication, and zanamivir (Relenza), an inhaled medication, are currently licensed, whilst laninamivir is undergoing Phase III clinical trials. Neuraminidase inhibitors are usually prescribed to patients presenting with flu-like symptoms during epidemic periods to reduce symptoms or prevent spread of the virus. We included six treatment trials involving 1906 children with clinically suspected influenza and 450 children with influenza diagnosed on rapid influenza testing. Of these 2356 children, 1255 had proven influenza infection confirmed on laboratory testing. We also included three trials of neuraminidase inhibitors for the prevention of influenza, which involved 863 children who had been exposed to influenza. This review found that treatment with neuraminidase inhibitors was only associated with modest clinical benefit in children with proven influenza. Treatment with oseltamivir or zanamivir shortened the duration of illness in healthy children by about one day. One trial demonstrated that the new neuraminidase inhibitor drug laninamivir reduces duration of illness by almost three days in children with oseltamivir-resistant influenza. The effect of neuraminidase inhibitors in preventing transmission of influenza was also modest; 13 children would need to be treated to prevent one additional case. Neuraminidase inhibitors are generally well tolerated but there will be one extra case of vomiting for every 17 children treated with oseltamivir. Other side effects such as diarrhoea and nausea were no more common in children treated with neuraminidase inhibitors compared to placebo. There is currently no high-quality evidence to support targeted treatment of 'at risk' children (with underlying chronic medical conditions) with neuraminidase inhibitors." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Eighteen trials were included, involving a total of 10,049 participants. Trials differed considerably in their inclusion criteria, outcomes measured, and type of lipid-lowering therapy used. Only one trial (PQRST) reported a detrimental effect of active treatment on blood lipid/lipoprotein levels. The pooled results from all eligible trials indicated that lipid-lowering therapy had no statistically significant effect on overall mortality (Odds Ratio (OR) 0.86; 95% Confidence Interval (CI) 0.49 to 1.50) or on total cardiovascular events (OR 0.8; 95% CI 0.59 to 1.09). However, subgroup analysis which excluded PQRST showed that lipid-lowering therapy significantly reduced the risk of total cardiovascular events (OR 0.74; CI 0.55 to 0.98). This was primarily due to a positive effect on total coronary events (OR 0.76; 95% CI 0.67 to 0.87). Greatest evidence of effectiveness came from the use of simvastatin in people with a blood cholesterol ≥ 3.5 mmol/litre (HPS). Pooling of the results from several small trials on a range of different lipid-lowering agents indicated an improvement in total walking distance (Mean Difference (MD) 152 m; 95% CI 32.11 to 271.88) and pain-free walking distance (WMD 89.76 m; 95% CI 30.05 to 149.47) but no significant impact on ankle brachial index (WMD 0.04; 95% CI -0.01 to 0.09). Lipid-lowering therapy is effective in reducing cardiovascular mortality and morbidity in people with PAD. It may also improve local symptoms. Until further evidence on the relative effectiveness of different lipid-lowering agents is available, use of a statin in people with PAD and a blood cholesterol level ≥ 3.5 mmol/litre is most indicated.\nOutput:\n" }, { "from": "agent", "value": "Eighteen randomised controlled trials were included in the review, involving a total of 10,049 participants (78% were men) from seven different countries. The trials compared lipid-lowering therapy with placebo or usual treatment for at least 90 days. They differed considerably in the inclusion criteria, outcomes measured, and type of lipid-lowering therapy used. Lipid-lowering therapies improved walking distance. The effect of lipid-lowering therapy on death from any cause in people with peripheral artery disease was inconclusive. Using drugs to lower blood lipids had a beneficial effect on the incidence of total cardiovascular events, due primarily to an overall reduction in coronary events (OR 0.8; 95% Confidence Interval 0.7 to 0.9). The only type of drug for which consistent, clear evidence of a beneficial effect on total cardiovascular events, total coronary events and stroke was available, was the statins. The greatest evidence was with simvastatin in people with a blood cholesterol level of at least 3.5 mmol/litre. The evidence on side effects was inconclusive in these trials." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 35 RCTs analysing 3102 participants. Thirteen studies were at low risk of bias, 12 studies were at unclear risk of bias, and 10 studies were at high risk of bias. Our main findings were regarding keratinocyte growth factor (KGF) and are summarised as follows. There might be a reduction in the risk of moderate to severe oral mucositis in adults receiving bone marrow/stem cell transplantation after conditioning therapy for haematological cancers (RR 0.89, 95% CI 0.80 to 0.99; 6 studies; 852 participants; low-quality evidence). We would need to treat 11 adults with KGF in order to prevent one additional adult from developing this outcome (95% CI 6 to 112). There might be a reduction in the risk of severe oral mucositis in this population, but there is also some possibility of an increase in risk (RR 0.85, 95% CI 0.65 to 1.11; 6 studies; 852 participants; low-quality evidence). We would need to treat 10 adults with KGF in order to prevent one additional adult from developing this outcome (95% CI 5 to prevent the outcome to 14 to cause the outcome). There is probably a reduction in the risk of moderate to severe oral mucositis in adults receiving radiotherapy to the head and neck with cisplatin or fluorouracil (RR 0.91, 95% CI 0.83 to 1.00; 3 studies; 471 participants; moderate-quality evidence). We would need to treat 12 adults with KGF in order to prevent one additional adult from developing this outcome (95% CI 7 to infinity). It is very likely that there is a reduction in the risk of severe oral mucositis in this population (RR 0.79, 95% CI 0.69 to 0.90; 3 studies; 471 participants; high-quality evidence). We would need to treat 7 adults with KGF in order to prevent one additional adult from developing this outcome (95% CI 5 to 15). It is likely that there is a reduction in the risk of moderate to severe oral mucositis in adults receiving chemotherapy alone for mixed solid and haematological cancers (RR 0.56, 95% CI 0.45 to 0.70; 4 studies; 344 participants; moderate-quality evidence). We would need to treat 4 adults with KGF in order to prevent one additional adult from developing this outcome (95% CI 3 to 6). There might be a reduction in the risk of severe oral mucositis in this population (RR 0.30, 95% CI 0.14 to 0.65; 3 studies; 263 participants; low -quality evidence). We would need to treat 10 adults with KGF in order to prevent one additional adult from developing this outcome (95% CI 8 to 19). Due to the low volume of evidence, single-study comparisons and insufficient sample sizes, we found no compelling evidence of a benefit for any other cytokines or growth factors and there was no evidence on children. There did not appear to be any serious adverse effects of any of the interventions assessed in this review. We are confident that KGF is beneficial in the prevention of oral mucositis in adults who are receiving: a) radiotherapy to the head and neck with cisplatin or fluorouracil; or b) chemotherapy alone for mixed solid and haematological cancers. We are less confident about a benefit for KGF in adults receiving bone marrow/stem cell transplant after conditioning therapy for haematological cancers because of multiple factors involved in that population, such as whether or not they received total body irradiation (TBI) and whether the transplant was autologous (the patients' own cells) or allogeneic (cells from a donor). KGF appears to be a relatively safe intervention. Due to limited research, we are not confident that there are any beneficial effects of other cytokines and growth factors. There is currently insufficient evidence to draw any conclusions about the use of cytokines and growth factors in children.\nOutput:\n" }, { "from": "agent", "value": "Authors from Cochrane Oral Health carried out this review of existing studies and the evidence is current up to 10 May 2017. It includes 35 studies (published between 1993 and 2017) with 3102 participants, all patients being treated for cancer, aged from 1 to 87 years old. Review authors included studies comparing cytokines and growth factors for the prevention of oral mucositis. The studies were carried out all over the world and often featured multiple sites, although most took place in high-income countries. The main findings were regarding keratinocyte growth factor (KGF). KGF is likely to reduce the risk of oral mucositis in adults who are receiving either radiotherapy to the head and neck with chemotherapy (cisplatin or fluorouracil), or chemotherapy alone for mixed solid and blood cancers. KGF may also reduce the risk of oral mucositis in adults receiving bone marrow/stem cell transplant after conditioning therapy for blood cancers, but these results are less clear because of multiple complicating factors. KGF appears to be a relatively safe intervention. There did not appear to be any serious adverse effects of any of the interventions assessed in this review. Due to limited research, review authors are uncertain of any beneficial effects of other cytokines and growth factors. There is currently insufficient evidence to draw any conclusions about the use of cytokines and growth factors in children. For reducing oral mucositis in adults receiving radiotherapy to the head and neck with chemotherapy, review authors rated the evidence for KGF as moderate to high quality. For reducing oral mucositis in adults receiving chemotherapy alone for mixed solid and blood cancers, they rated the evidence for KGF as low to moderate quality. This evidence was downgraded due to there not being enough data and because some results have not yet been published. For reducing oral mucositis in adults receiving bone marrow/stem cell transplant after conditioning therapy for blood cancers, they rated the evidence for KGF as low quality because results were not similar across the studies and some results have not yet been published. Evidence on side effects of KGF was poorly reported and inconsistent." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Six trials with 151 Japanese patients were included. All trials had high risk of bias. Four trials compared bezafibrate plus UDCA with no intervention plus UDCA (referenced as bezafibrate versus no intervention in the remaining text), and two trials compared bezafibrate with UDCA. No patient died and no patient developed liver-related complications in any of the included trials. Bezafibrate was without significant effects on the occurrence of adverse events compared with no intervention (5/32 (16%) versus 0/28 (0%)) (RR 5.40, 95% CI 0.69 to 42.32; 3 trials with 60 patients; I² = 0%) or with UDCA (2/32 (6%) versus 0/37 (0%)) (RR 6.19, 95% CI 0.31 to 122.05; 2 trials with 69 patients; I² = 0%). Bezafibrate significantly decreased the activity of serum alkaline phosphatases compared with no intervention (MD -186.04 U/L, 95% CI -249.03 to -123.04; 4 trials with 79 patients; I² = 34%) and when compared with UDCA (MD -162.90 U/L, 95% CI -199.68 to -126.12; 2 trials with 48 patients; I² = 0%). These results were supported by trial sequential analyses. Bezafibrate compared with no intervention significantly decreased plasma immunoglobulin M (MD -164.00 mg/dl, 95% CI -259.47 to -68.53; 3 trials with 50 patients; I² = 46%) and serum bilirubin concentration (MD -0.19 mg/dl, 95% CI -0.38 to -0.00; 2 trials with 34 patients; I² = 0%). However, the latter two results were not supported by trial sequential analyses. Bezafibrate compared with no intervention had no significant effect on the activity of serum gamma-glutamyltransferase (MD -1.22 U/L, 95% CI -11.97 to 9.52; 4 trials with 79 patients; I² = 42%) and serum alanine aminotransferase (MD -5.61 U/L, 95% CI -24.50 to 13.27; 2 trials with 35 patients; I² = 34%). Bezafibrate compared with UDCA had no significant effect on the activity of serum gamma-glutamyltransferase (MD 38.44 U/L, 95% CI -180.67 to 257.55; 2 trials with 49 patients; I² = 89%), serum alanine aminotransferase (MD -2.34 U/L, 95% CI -34.73 to 30.06; 2 trials with 49 patients; I² = 95%), and plasma immunoglobulin M concentration (MD -20.23 mg/dl, 95% CI -218.71 to 178.25; 2 trials with 41 patients; I² = 90%) in random-effects model meta-analyses, but bezafibrate significantly decreased the activity of serum gamma-glutamyltransferase (MD -58.18, 95% CI -76.49 to -39.88; 2 trials with 49 patients; I² = 89%), serum alanine aminotransferase (MD -13.94, 95% CI -18.78 to -9.09; 2 trials with 49 patients; I² = 95%), and plasma immunoglobulin M concentration (MD -99.90, 95% CI -130.72 to -69.07; 2 trials with 41 patients; I² = 90%) in fixed-effect model meta-analyses. One patient had bezafibrate withdrawn due to an adverse event compared to no intervention (RD 0.03, 95% CI -0.09 to 0.16; 2 trials with 60 patients; I² = 0%). This systematic review did not demonstrate any effect of bezafibrate versus no intervention on mortality, liver-related morbidity, adverse events, and pruritus in patients with primary biliary cirrhosis. Furthermore, we found no significant effects of bezafibrate on mortality, liver-related morbidity, or adverse events when compared with ursodeoxycholic acid, None of the trials assessed quality of life or fatigue. The data seem to indicate a possible positive intervention effect of bezafibrate on some liver biochemistry measures compared with the control group, but the observed effects could be due to systematic errors or random errors. We need more randomised clinical trials on the effects of bezafibrate on primary biliary cirrhosis with low risks of systematic errors and random errors.\nOutput:\n" }, { "from": "agent", "value": "There are studies suggesting that bezafibrate, alone or in combination with ursodeoxycholic acid, is effective in treatment of primary biliary cirrhosis. Mechanisms through which bezafibrate improves lipid serum concentration balance and prevents biliary cell damage still need to be fully understood. This review evaluates all data on the benefits and harms of bezafibrate for patients with primary biliary cirrhosis in randomised clinical trials. The findings of this review are based on six randomised clinical trials with 151 Japanese patients. Bezafibrate was compared with no intervention in four trials (with co-intervention of ursodeoxycholic acid in both the bezafibrate and control groups) and with ursodeoxycholic acid in two trials. The primary findings of the review are that bezafibrate has no statistically significant effects on mortality, liver-related morbidity, adverse events, and quality of life of patients with primary biliary cirrhosis. A possible positive intervention effect of bezafibrate versus no intervention on liver biochemistry measures can be real but could also be due to systematic errors or random errors. The benefits and harms of bezafibrate for patients with primary biliary cirrhosis need further assessment in randomised clinical trials comparing bezafibrate with placebo. Such trials ought to be conducted with impeccable methodology to reduce the risks of random errors and sufficiently large patient groups to reduce the risks of random errors." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Eight randomized trials, including 9598 patients, tested adjusted-dose warfarin versus aspirin (in dosages ranging from 75 to 325 mg/day) in AF patients without prior stroke or TIA. The mean overall follow up was 1.9 years/participant. Oral anticoagulants were associated with lower risk of all stroke (odds ratio (OR) 0.68, 95% confidence interval (CI) 0.54 to 0.85), ischemic stroke (OR 0.53, 95% CI 0.41 to 0.68) and systemic emboli (OR 0.48, 95% CI 0.25 to 0.90). All disabling or fatal strokes (OR 0.71, 95% CI 0.59 to 1.04) and myocardial infarction (OR 0.69, 95% CI 0.47 to 1.01) were substantially but not significantly reduced by oral anticoagulants. Vascular death (OR 0.93, 95% CI 0.75 to 1.15) and all cause mortality (OR 0.99, 95% CI 0.83 to 1.18), were similar with these treatments. Intracranial hemorrhages (OR 1.98, 95% CI 1.20 to 3.28) were increased by oral anticoagulant therapy. Adjusted-dose warfarin and related oral anticoagulants reduce stroke, disabling stroke and other major vascular events for those with non-valvular AF by about one third when compared with antiplatelet therapy.\nOutput:\n" }, { "from": "agent", "value": "Atrial fibrillation (AF) is an irregularity of the heartbeat that leads to blood clots forming in the upper chambers of the heart (the atria). These clots can break free and travel through the bloodstream to the brain and cause a stroke. Drugs that slow clotting, such as oral anticoagulants (warfarin and other coumarin derivates) and antiplatelet agents (aspirin and others), reduce the risk of stroke in patients with atrial fibrillation. In this review of eight randomized trials, including 9598 patients, oral anticoagulants are shown to reduce the risk of stroke in patients with non-valvular AF and with no prior stroke or transient ischemic attack by one-third when compared with antiplatelet agents alone. Antiplatelet agents reduce stroke by about 20% in AF patients compared with no therapy, offering a less efficacious therapeutic option for those deemed not eligible for anticoagulation therapy. The threshold of absolute benefit that warrants anticoagulation remains controversial and depends on patient's preferences and availability of optimal anticoagulation monitoring." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included seven studies involving 2492 participants. Peer support telephone calls were associated with an increase in mammography screening, with 49% of women in the intervention group and 34% of women in the control group receiving a mammogram since the start of the intervention (P </ = 0.001). In another study, peer telephone support calls were found to maintain mammography screening uptake for baseline adherent women (P = 0.029). Peer support telephone calls for post myocardial infarction patients were associated at six months with a change in diet in the intervention and usual care groups of 54% and 44% respectively (P = 0.03). In another study for post myocardial infarction patients there were no significant differences between groups for self-efficacy, health status and mental health outcomes. Peer support telephone calls were associated with greater continuation of breastfeeding in mothers at 3 months post partum (P = 0.01). Peer support telephone calls were associated with reduced depressive symptoms in mothers with postnatal depression (Edinburgh Postnatal Depression Scale (EPDS) > 12). The peer support intervention significantly decreased depressive symptomatology at the 4-week assessment (odds ratio (OR) 6.23 (95% confidence interval (CI) 1.15 to 33.77; P = 0.02)) and 8-week assessment (OR 6.23 (95% CI 1.40 to 27.84; P = 0.01). One study investigated the use of peer support for patients with poorly controlled diabetes. There were no significant differences between groups for self-efficacy, HbA1C, cholesterol level and body mass index. Whilst this review provides some evidence that peer support telephone calls can be effective for certain health-related concerns, few of the studies were of high quality and so results should be interpreted cautiously. There were many methodological limitations thus limiting the generalisability of findings. Overall, there is a need for further well designed randomised controlled studies to clarify the cost and clinical effectiveness of peer support telephone calls for improvement in health and health-related behaviour.\nOutput:\n" }, { "from": "agent", "value": "Seven randomised controlled trials conducted in the USA, UK, Canada and Australia related to a range of conditions and target populations. They provided some evidence of efficacy. Peer support telephone calls may increase mammography screening in women over 40 years, may help patients change their diet and cease smoking after a heart attack; and may help reduce depressive symptoms among mothers with postnatal depression. Findings need to be interpreted cautiously. There is a need for well designed randomised controlled studies to clarify which elements of peer telephone interventions work best to improve health and health-related behaviour." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: One cross-over randomised controlled trial met the inclusion criteria. The trial was performed in 210 patients with moderate to severe asthma and compared the use of the LAMA tiotropium bromide with double dose beclomethasone (an ICS) using a cross-over design and 14-week treatment periods. Compared with people taking a double dose of ICS, fewer people taking a LAMA add-on had an exacerbation requiring treatment with OCS (odds ratio (OR) 0.57, 95% confidence interval (CI) 0.22 to 1.43) or an exacerbation resulting in emergency department admission (OR 0.49, 95% CI 0.09 to 2.77), but the confidence intervals for both outcomes did not exclude the possibility that double dose ICS was more effective. Serious adverse events and exacerbations requiring hospitalisation occurred in similarly low numbers of people taking each treatment, but confidence intervals were too wide to suggest that the two treatment options were equivalent. Asthma-related quality of life was similar in both treatment groups (mean difference (MD) in change from baseline 0.10, 95% CI − 0.07 to 0.27). Those taking LAMA add-on scored slightly better on a scale measuring asthma control than those increasing their ICS dose (MD in change from baseline − 0.18, 95% CI − 0.34 to − 0.02), although the difference was clinically small. Evidence was deemed low quality for both quality of life and asthma control. There was moderate-quality evidence that participants' trough forced expiratory volume in one second (FEV1) was 100 mL better when taking LAMA add-on than with increased ICS dose (MD in change from baseline 0.10, 95% CI 0.03 to 0.17). Only one randomised trial was found, comparing tiotropium add-on to increased dose beclomethasone. Differences between the treatments were too small or imprecise to understand whether adding a LAMA to ICS is safer or more effective than increasing the dose of ICS, and there is a possibility of carry-over effects due to the study's cross-over design. LAMA add-on may lead to more improvement in lung function (FEV1) than an increased dose of ICS. The results of this review, alongside pending results from related reviews assessing the use of LAMA against other treatments, will help to define the role of these drugs in asthma management, and this review should be updated as results from future trials emerge. Studies assessing the role of LAMA add-on should be longer and include a double-ICS treatment arm so that the results can be interpreted in the context of the guideline-recommended treatment options that are available to physicians.\nOutput:\n" }, { "from": "agent", "value": "Two people looked for published and unpublished research in several databases and websites to find relevant studies comparing LAMA plus ICS with increased doses of ICS for asthma in adults. We analysed the results available up to April 2015 in this systematic review. What did we find? We found one study involving 210 patients with asthma. The trial compared adding tiotropium (a LAMA) to doubling the dose of beclomethasone (a steroid). In the trial, people taking a combination of the LAMA and ICS were slightly less likely to have an asthma attack needing treatment with oral steroids. Our results suggest that for every 1000 people, 18 fewer in the LAMA group would need these treatments compared to patients treated with an increased dose of ICS. However, there is a relatively wide margin of error in this estimate, and the actual number of patients on LAMA who might need steroids because of an asthma attack could range from 52 fewer to 26 more people per 1000. Similarly, neither option was more clearly beneficial on any of the following measures: asthma attacks resulting in hospitalisation or admission to the emergency department, serious adverse events, control of asthma or quality of life related to asthma. On the other hand, LAMA plus ICS might improve lung function a bit more than increasing ICS dose. We didn't have much confidence in the findings because the one included study only looked at one type of LAMA (tiotropium) for a short period of time (14 weeks)." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included six published RCTs, conducted in the USA (5 RCTs) and Israel (1 RCT), with 1097 children and adolescents (11 to 18 years old), in the review. We are very uncertain about the effect of client feedback on improvement of symptoms, as reported by youth in the short term because we considered evidence to be of very low-certainty due to high risk of bias and very serious inconsistency in the effect estimates from the different studies. Similarly, we are very uncertain about the effect of client feedback on treatment acceptability, due to high risk of bias, imprecision in the results, and indirectness of measuring the outcome (RR 1.08, 95% CI 0.73 to 1.61; 2 studies, 237 participants; very low-certainty). Overall, most studies reported and carried out randomisation and allocation concealment adequately. None of the studies were blinded or attempted to blind participants and personnel and were at high risk of performance bias, and only one study had blind outcome assessors. All of the studies were at high or unclear risk of attrition bias mainly due to poor, non-transparent reporting of participants' flow through the studies. Due to the paucity of high-quality data and considerable inconsistency in results from different studies, there is currently insufficient evidence to reach any firm conclusions regarding the role of client feedback in psychological therapies for children and adolescents with mental health problems, and further research on this important topic is needed. Future studies should avoid risks of performance, detection and attrition biases, as seen in the studies included in this review. Studies from countries other than the USA are needed, as well as studies including children younger than 10 years.\nOutput:\n" }, { "from": "agent", "value": "There have been few investigations of client feedback in psychological therapies for children and adolescents with mental health problems. Most of them were carried out in the USA with older children and adolescents (11 to 18 years old). There was no clear evidence supporting the effectiveness of client feedback in psychological therapy for children and adolescents. It cannot be ruled out that client feedback has positive effects on psychotherapy outcomes in children and adolescents. High-quality studies are needed to provide sufficient evidence. Future studies should also include younger children, and should take place in countries other than the USA." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included nine RCTs with a total of 534 participants with cirrhosis and ascites. One RCT had a low risk of bias for mortality and a high risk of bias for the remaining outcomes. All included trials had a high risk of bias for non-mortality outcomes. In total, 473 participants had type 1 hepatorenal syndrome. Seven RCTs specifically evaluated terlipressin and albumin. Terlipressin was associated with a beneficial effect on mortality when including all RCTs (RR 0.85, 95% CI 0.73 to 0.98; 534 participants; number needed to treat for an additional beneficial outcome (NNTB) 10.3 people; low-quality evidence). Trial Sequential Analysis including all RCTs also found a beneficial effect of terlipressin. Additional analyses showed a beneficial effect of terlipressin and albumin on reversal of hepatorenal syndrome (RR 0.63, 95% CI 0.48 to 0.82; 510 participants; 8 RCTs; NNTB 4 people; low-quality evidence). Terlipressin increased the risk of serious cardiovascular adverse events (RR 7.26, 95% CI 1.70 to 31.05; 234 participants; 4 RCTs), but it had no effect on the risk of serious adverse events when analysed as a composite outcome (RR 0.91, 95% CI 0.68 to 1.21; 534 participants; 9 RCTs; number needed to treat for an additional harmful outcome 24.5 people; low-quality evidence). Non-serious adverse events were mainly gastrointestinal, including diarrhoea (RR 5.76, 95% CI 2.19 to 15.15; 240 participants; low-quality evidence) and abdominal pain (RR 1.54, 95% CI 0.97 to 2.43; 294 participants; low-quality evidence). We identified one ongoing trial on terlipressin versus placebo in participants with cirrhosis, ascites, and hepatorenal syndrome type 1. Three RCTs reported funding from a pharmaceutical company. The remaining trials did not report funding or did not receive funding from pharmaceutical companies. This review suggests that terlipressin may be associated with beneficial effects on mortality and renal function in people with cirrhosis and type 1 hepatorenal syndrome, but it is also associated with serious adverse effects. We downgraded the strength of the evidence due to methodological issues including bias control, clinical heterogeneity, and imprecision. Consequently, additional evidence is needed.\nOutput:\n" }, { "from": "agent", "value": "The review includes nine randomised clinical trials (RCTs) and a total of 534 participants. The trials originated from six countries. Seven trials included only participants with type 1 hepatorenal syndrome. Two trials included a total of 96 participants with type 1 or type 2 hepatorenal syndrome. Three RCTs reported funding from a pharmaceutical company. The remaining trials did not report funding or did not receive funding from pharmaceutical companies. People who received terlipressin had a lower risk of dying than people who received inactive placebo or no treatment. Terlipressin was also associated with a beneficial effect on renal function. Terlipressin increased the risk of serious circulation and heart problems (so-called cardiovascular events). Other adverse events included diarrhoea and abdominal pain. The analyses mainly included people with type 1 hepatorenal syndrome. No beneficial or harmful effects of terlipressin were found when analysing participants with type 2 hepatorenal syndrome (possibly due to the small number of participants). We considered the evidence to be of low quality." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included one single blind study (total n = 24). The overall risk of bias in the study was considered to be unclear although the randomisation was adequate. It compared a package of horticultural therapy which consisted of one hour per day of horticultural activity plus standard care with standard care alone over two weeks (10 consecutive days) with no long-term follow-up. Only two people were lost to follow-up in the study, both in the horticultural therapy group (1 RCT n = 24,RR 5.00 95% CI 0.27 to 94.34, very low quality evidence). There was no clear evidence of a difference in Personal Wellbeing Index (PWI-C) change scores between groups, however confidence intervals were wide (1 RCT n = 22, MD -0.90 95% CI -10.35 to 8.55, very low quality evidence). At the end of treatment, the Depression Anxiety Stress Scale (DASS21) change scores in horticultural therapy group were greater than that in the control group (1 RCT n = 22, MD -23.70 CI -35.37 to - 12.03, very low quality evidence). The only included study did not report on adverse effects of interventions. Based on the current very low quality data, there is insufficient evidence to draw any conclusions on benefits or harms of horticultural therapy for people with schizophrenia. This therapy remains unproven and more and larger randomised trials are needed to increase high quality evidence in this area.\nOutput:\n" }, { "from": "agent", "value": "This review focuses on the effects of horticultural therapy for people with schizophrenia. An electronic search for relevant randomised trials was run in January 2013. Only one trial was included, it randomised a total of 24 people with schizophrenia to received either their standard care plus horticultural therapy or standard care only. The trial only lasted 2 weeks (10 consecutive days) with no long-term follow-up. There are few results and the quality of evidence was rated by the review authors to be very low quality. Some of the information from this one study favoured horticultural therapy but there is insufficient evidence to draw any conclusions on benefits or harms of horticultural therapy for people with schizophrenia. More large, better conducted and reported trials are required to determine the effectiveness and benefits of horticultural therapy. This plain language summary has been written by a consumer Ben Gray, Service User and Service User Expert, Rethink Mental Illness." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: In this update, we identified eight new studies, thereby including a total of 22 trials (2503 participants), 10 of which had a low risk of bias. Most rehabilitation programmes were assessed in only one study. Both men and women were included, and overall mean age was 41.4 years. All participants had received standard discectomy, microdiscectomy and in one study standard laminectomy and (micro)discectomy. Mean duration of the rehabilitation intervention was 12 weeks; eight studies assessed six to eight-week exercise programmes, and eight studies assessed 12 to 13-week exercise programmes. Programmes were provided in primary and secondary care facilities and were started immediately after surgery (n = 4) or four to six weeks (n = 16) or one year after surgery (n = 2). In general, the overall quality of the evidence is low to very low. Rehabilitation programmes that started immediately after surgery were not more effective than their control interventions, which included exercise. Low- to very low-quality evidence suggests that there were no differences between specific rehabilitation programmes (multidisciplinary care, behavioural graded activity, strength and stretching) that started four to six weeks postsurgery and their comparators, which included some form of exercise. Low-quality evidence shows that physiotherapy from four to six weeks postsurgery onward led to better function than no treatment or education only, and that multidisciplinary rehabilitation co-ordinated by medical advisors led to faster return to work than usual care. Statistical pooling was performed only for three comparisons in which the rehabilitation programmes started four to six weeks postsurgery: exercise programmes versus no treatment, high- versus low-intensity exercise programmes and supervised versus home exercise programmes. Very low-quality evidence (five RCTs, N = 272) shows that exercises are more effective than no treatment for pain at short-term follow-up (standard mean difference (SMD) -0.90; 95% confidence interval (CI) -1.55 to -0.24), and low-quality evidence (four RCTs, N = 252) suggests that exercises are more effective for functional status on short-term follow-up (SMD -0.67; 95% CI -1.22 to -0.12) and that no difference in functional status was noted on long-term follow-up (three RCTs, N = 226; SMD -0.22; 95% CI -0.49 to 0.04). None of these studies reported that exercise increased the reoperation rate. Very low-quality evidence (two RCTs, N = 103) shows that high-intensity exercise programmes are more effective than low-intensity exercise programmes for pain in the short term (weighted mean difference (WMD) -10.67; 95% CI -17.04 to -4.30), and low-quality evidence (two RCTs, N = 103) shows that they are more effective for functional status in the short term (SMD -0.77; 95% CI -1.17 to -0.36). Very low-quality evidence (four RCTs, N = 154) suggests no significant differences between supervised and home exercise programmes for short-term pain relief (SMD -0.76;  95% CI -2.04 to 0.53) or functional status (four RCTs, N = 154; SMD -0.36; 95% CI -0.88 to 0.15). Considerable variation was noted in the content, duration and intensity of the rehabilitation programmes included in this review, and for none of them was high- or moderate-quality evidence identified. Exercise programmes starting four to six weeks postsurgery seem to lead to a faster decrease in pain and disability than no treatment, with small to medium effect sizes, and high-intensity exercise programmes seem to lead to a slightly faster decrease in pain and disability than is seen with low-intensity programmes, but the overall quality of the evidence is only low to very low. No significant differences were noted between supervised and home exercise programmes for pain relief, disability or global perceived effect. None of the trials reported an increase in reoperation rate after first-time lumbar surgery. High-quality randomised controlled trials are strongly needed.\nOutput:\n" }, { "from": "agent", "value": "This updated review evaluated the effectiveness of various rehabilitation programmes for patients who had lumbar disc surgery for the first time. We included 22 randomised controlled trials with 2503 participants, both men and women, between the ages of 18 and 65 years. The evidence is current to May 2013. Most commonly, treatment started four to six weeks after surgery, but the start of treatment ranged from two hours to 12 months after surgery. Considerable variation in the content, duration and intensity of treatments (i.e. exercise programmes) has been noted. The duration of the interventions varied from two weeks to one year; most programmes lasted six to 12 weeks. Participants reported on average serious pain intensity (56 points on a zero to 100 scale, with 100 being the worst possible pain). Most studies compared (1) exercise versus no treatment, (2) high-intensity exercise versus low-intensity exercise or (3) supervised exercise versus home exercise, most commonly starting four to six weeks after surgery. Comparisons in this review included (1) exercise versus no treatment, (2) high-intensity versus low-intensity exercise and (3) supervised versus home exercise. Patients who participated in exercise programmes four to six weeks after surgery reported slightly less short-term pain and disability than those who received no treatment. Patients who participated in high-intensity exercise programmes reported slightly less short-term pain and disability than those participating in low-intensity exercise programmes. Patients in supervised exercise programmes reported little or no difference in pain and disability compared with those in home exercise programmes. Here it was difficult to draw firm conclusions in the absence of high-quality evidence. None of the trials reported an increase in reoperation rate after first-time lumbar surgery. The evidence does not show whether all patients should be treated after surgery or only those who still have symptoms four to six weeks later. Limitations in the methods of half of the trials suggest that the results should be read with caution. Most of the treatments were assessed in only one trial. Therefore for most of the interventions, only low- to very low-quality evidence indicates that no firm conclusions can be drawn regarding their effectiveness." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The electronic search yielded 8746 records. We included 12 RCTs (3885 participants) comparing usual care with the following interventions: commonly used drugs (four studies); sedation regimens (four studies); physical therapy or cognitive therapy, or both (one study); environmental interventions (two studies); and preventive nursing care (one study). We found 15 ongoing studies and five studies awaiting classification. The participants were 48 to 70 years old; 48% to 74% were male; the mean acute physiology and chronic health evaluation (APACHE II) score was 14 to 28 (range 0 to 71; higher scores correspond to more severe disease and a higher risk of death). With the exception of one study, all participants were mechanically ventilated in medical or surgical ICUs or mixed. The studies were overall at low risk of bias. Six studies were at high risk of detection bias due to lack of blinding of outcome assessors. We report results for the two most commonly explored approaches to delirium prevention: pharmacologic and a non-pharmacologic intervention. Haloperidol versus placebo (two RCTs, 1580 participants) The event rate of ICU delirium was measured in one study including 1439 participants. No difference was identified between groups, (risk ratio (RR) 1.01, 95% confidence interval (CI) 0.87 to 1.17) (moderate-quality evidence). Haloperidol versus placebo neither reduced or increased in-hospital mortality, (RR 0.98, 95% CI 0.80 to 1.22; 2 studies; 1580 participants (moderate-quality evidence)); the number of delirium- and coma-free days, (mean difference (MD) -0.60, 95% CI -1.37 to 0.17; 2 studies, 1580 participants (moderate-quality of evidence)); number of ventilator-free days (mean 23.8 (MD -0.30, 95% CI -0.93 to 0.33) 1 study; 1439 participants, (high-quality evidence)); length of ICU stay, (MD 0.18, 95% CI ­0.60 to 0.97); 2 studies, 1580 participants; high-quality evidence). None of the studies measured cognitive impairment. In one study there were three serious adverse events in the intervention group and five in the placebo group; in the other there were five serious adverse events and three patients died, one in each group. None of the serious adverse events were judged to be related to interventions received (moderate-quality evidence). Physical and cognitive therapy interventions (one study, 65 participants) The study did not measure the event rate of ICU delirium. A physical and cognitive therapy intervention versus standard care neither reduced nor increased in-hospital mortality, (RR 0.94, 95% CI 0.40 to 2.20, I² = 0; 1 study, 65 participants; very low-quality evidence); the number of delirium- and coma-free days, (MD -2.8, 95% CI -10.1 to 4.6, I² = 0; 1 study, 65 participants; very low-quality evidence); the number of ventilator-free days (within the first 28/30 days) was median 27.4 (IQR 0 to 29.2) and 25 (IQR 0 to 28.9); 1 study, 65 participants; very low-quality evidence, length of ICU stay, (MD 1.23, 95% CI -0.68 to 3.14, I² = 0; 1 study, 65 participants; very low-quality evidence); cognitive impairment measured by the MMSE: Mini-Mental State Examination with higher scores indicating better function, (MD 0.97, 95% CI -0.19 to 2.13, I² = 0; 1 study, 30 participants; very low-quality evidence); or measured by the Dysexecutive questionnaire (DEX) with lower scores indicating better function (MD -8.76, 95% CI -19.06 to 1.54, I² = 0; 1 study, 30 participants; very low-quality evidence). One patient experienced acute back pain accompanied by hypotensive urgency during physical therapy. There is probably little or no difference between haloperidol and placebo for preventing ICU delirium but further studies are needed to increase our confidence in the findings. There is insufficient evidence to determine the effects of physical and cognitive intervention on delirium. The effects of other pharmacological interventions, sedation, environmental, and preventive nursing interventions are unclear and warrant further investigation in large multicentre studies. Five studies are awaiting classification and we identified 15 ongoing studies, evaluating pharmacological interventions, sedation regimens, physical and occupational therapy combined or separately, and environmental interventions, that may alter the conclusions of the review in future.\nOutput:\n" }, { "from": "agent", "value": "We included 12 randomized controlled trials (3885 participants) in our review. The studies included adults aged 48 to 70 years from surgical and medical ICUs. The studies compared different drugs (three studies) various approaches to sedation (five studies), physical or cognitive therapy or both (one study), noise and light reduction in the ICU (two studies), and preventive nursing care (one study). The studies had mostly small numbers of participants and did not blind the researchers who assessed effects on outcomes. We report the findings regarding the effect of the two most commonly explored approaches for preventing delirium, drug and non-drug interventions, haloperidol versus a sham drug, and early physical and cognitive therapy versus usual care. Our findings suggest that there may be little or no difference between haloperidol and placebo for preventing ICU delirium, but further studies are needed to reduce imprecision and increase our confidence in the findings. More studies of physical and cognitive therapy are needed as there is insufficient evidence to determine whether these non-pharmacological approaches can prevent delirium in the ICU. Additional research is required to explore the benefits and harms of other approaches to prevent delirium in the ICU such as sedation and changes in the ICU environment, and nursing care tailored to prevent delirium. We rated the quality of the evidence as moderate to very low. Several studies had quality shortcomings, including their use of small numbers of participants, and lack of blinding of those assessing effects of interventions for preventing delirium and other outcomes. For the interventions testing sedation approaches, physical and cognitive therapy, and changes in the environment, additional research is required to clarify their effectiveness. The five studies in ‘Studies awaiting classification’ and 15 ongoing studies may alter the conclusions of the review once they are completed and assessed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified seven trials that met the inclusion criteria. Out of these, six trials provided data for the meta-analyses. A total of 488 participants with acute cholecystitis and fit to undergo laparoscopic cholecystectomy were randomised to early laparoscopic cholecystectomy (ELC) (244 people) and delayed laparoscopic cholecystectomy (DLC) (244 people) in the six trials. Blinding was not performed in any of the trials and so all the trials were at high risk of bias. Other than blinding, three of the six trials were at low risk of bias in the other domains such as sequence generation, allocation concealment, incomplete outcome data, and selective outcome reporting. The proportion of females ranged between 43.3% and 80% in the trials that provided this information. The average age of participants ranged between 40 years and 60 years. There was no mortality in any of the participants in five trials that reported mortality. There was no significant difference in the proportion of people who developed bile duct injury in the two groups (ELC 1/219 (adjusted proportion 0.4%) versus DLC 2/219 (0.9%); Peto OR 0.49; 95% CI 0.05 to 4.72 (5 trials)). There was no significant difference between the two groups (ELC 14/219 (adjusted proportion 6.5%) versus DLC 11/219 (5.0%); RR 1.29; 95% CI 0.61 to 2.72 (5 trials)) in terms of other serious complications. None of the trials reported quality of life from the time of randomisation. There was no significant difference between the two groups in the proportion of people who required conversion to open cholecystectomy (ELC 49/244 (adjusted proportion 19.7%) versus DLC 54/244 (22.1%); RR 0.89; 95% CI 0.63 to 1.25 (6 trials)). The total hospital stay was shorter in the early group than the delayed group by four days (MD -4.12 days; 95% CI -5.22 to -3.03 (4 trials; 373 people)). There was no significant difference in the operating time between the two groups (MD -1.22 minutes; 95% CI -3.07 to 0.64 (6 trials; 488 people)). Only one trial reported return to work. The people belonging to the ELC group returned to work earlier than the DLC group (MD -11.00 days; 95% CI -19.61 to -2.39 (1 trial; 36 people)). Four trials did not report any gallstone-related morbidity during the waiting period. One trial reported five gallstone-related morbidities (cholangitis: two; biliary colic not requiring urgent operation: one; acute cholecystitis not requiring urgent operation: two). There were no reports of pancreatitis during the waiting time. Gallstone-related morbidity was not reported in the remaining trials. Forty (18.3%) of the people belonging to the delayed group had either non-resolution of symptoms or recurrence of symptoms before their planned operation and had to undergo emergency laparoscopic cholecystectomy in five trials. The proportion with conversion to open cholecystectomy was 45% (18/40) in this group of people. We found no significant difference between early and late laparoscopic cholecystectomy on our primary outcomes. However, trials with high risk of bias indicate that early laparoscopic cholecystectomy during acute cholecystitis seems safe and may shorten the total hospital stay. The majority of the important outcomes occurred rarely, and hence the confidence intervals are wide. It is unlikely that future randomised clinical trials will be powered to measure differences in bile duct injury and other serious complications since this might involve performing a trial of more than 50,000 people, but several smaller randomised trials may answer the questions through meta-analyses.\nOutput:\n" }, { "from": "agent", "value": "Six trials providing information on the review question were identified. A total of 488 people with acute cholecystitis were included. Laparoscopic cholecystectomy was performed early (within seven days of people presenting to the doctor with symptoms) in 244 people while it was performed after at least six weeks in the remaining 244 people. The proportion of females ranged between 43.3% and 80% in the trials that provided this information. The average age of participants ranged between 40 years and 60 years. All the trials were at high risk of bias (and might have overestimated the benefits or underestimated the harms of either early laparoscopic cholecystectomy or delayed laparoscopic cholecystectomy). All the people included in the trials were discharged home alive after operation in the five trials from which this information was available. There was no significant difference in the proportion of people who developed bile duct injury, surgical complications, or who required conversion from key-hole to open operation between the two groups. None of the trials reported quality of life from the time of randomisation. The total hospital stay was shorter in the early group than the delayed group by four days. There was no significant difference in the operating time between the two groups. Only one trial reported the time taken for employed people to return to work. The people belonging to the early laparoscopic cholecystectomy group returned to work 11 days, on average, earlier than the delayed laparoscopic cholecystectomy group. Four trials did not report any gallstone-related complications during the waiting period. One trial reported five gallstone-related complications, including two people with cholangitis. There were no reports of pancreatitis during the waiting time. Gallstone-related morbidity was not reported in the remaining trial. Approximately one-sixth of people belonging to the delayed group had either non-resolution of symptoms or recurrence of symptoms before their planned operation and had to undergo emergency laparoscopic cholecystectomy in five trials. Based on information from a varied number of participants as well as trials at high risk of bias, early laparoscopic cholecystectomy during acute cholecystitis appears safe and shortens the total hospital stay. The majority of the important outcomes occurred rarely and hence one cannot rule out that future trials may show that one treatment or another may be better in terms of complications. However, the trial size required to show such differences involves a clinical trial on more than 50,000 people and so it is unlikely that such large trials will be performed. Several smaller randomised trials may answer the questions through meta-analyses." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Twelve studies were included in the review. This update incorporated two new studies. One of the new trials was a large field-based trial that included 2377 participants, 1220 of whom were allocated stretching. All other 11 studies were small, with between 10 and 30 participants receiving the stretch condition. Ten studies were laboratory-based and other two were field-based. All studies were exposed to either a moderate or high risk of bias. The quality of evidence was low to moderate. There was a high degree of consistency of results across studies. The pooled estimate showed that pre-exercise stretching reduced soreness at one day after exercise by, on average, half a point on a 100-point scale (mean difference -0.52, 95% CI -11.30 to 10.26; 3 studies). Post-exercise stretching reduced soreness at one day after exercise by, on average, one point on a 100-point scale (mean difference -1.04, 95% CI -6.88 to 4.79; 4 studies). Similar effects were evident between half a day and three days after exercise. One large study showed that stretching before and after exercise reduced peak soreness over a one week period by, on average, four points on a 100-point scale (mean difference -3.80, 95% CI -5.17 to -2.43). This effect, though statistically significant, is very small. The evidence from randomised studies suggests that muscle stretching, whether conducted before, after, or before and after exercise, does not produce clinically important reductions in delayed-onset muscle soreness in healthy adults.\nOutput:\n" }, { "from": "agent", "value": "The review located 12 relevant randomised controlled studies looking at the effect of stretching before or after physical activity on muscle soreness. Eleven studies were small with between 10 to 30 people being allocated stretching exercises. In contrast, one study was large with 2337 participants, 1220 of whom were in the stretching group. Ten studies were conducted in laboratories using standardised exercises. The only two studies, which included the only large study, were so-called field-based studies. These examined the effect of stretching on muscle soreness associated with self-selected physical activity. The studies were of low to moderate quality. Some of the studies examined the effects of stretching before physical activity, some examined the effects of stretching after physical activity, and some examined effects of stretching both before and after physical activity. The studies produced very consistent findings. They showed there was little or no effect of stretching on the muscle soreness experienced in the week after the physical activity." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included eight trials of influenza vaccination compared with placebo or no vaccination, with 12,029 participants receiving at least one vaccination or control treatment. We included six new studies (n = 11,251), in addition to the two included in the previous version of the review. Four of these trials (n = 10,347) focused on prevention of influenza in the general or elderly population and reported cardiovascular outcomes among their safety analyses; four trials (n = 1682) focused on prevention of cardiovascular events in patients with established coronary heart disease. These populations were analysed separately. Follow-up continued between 42 days and one year. Five RCTs showed deficits in at least three of the risk of bias criteria assessed. When reported (seven studies), vaccination provided adequate immunogenicity or protection against influenza. Cardiovascular mortality was reported by four secondary prevention trials and was significantly reduced by influenza vaccination overall (risk ratio (RR) 0.45, 95% confidence interval (CI) 0.26 to 0.76; P value 0.003) with no significant heterogeneity between studies, and by three trials reporting cardiovascular mortality as part of their safety analyses when the numbers of events were too small to permit conclusions. In studies of patients with coronary heart disease, composite outcomes of cardiovascular events tended to be decreased with influenza vaccination compared with placebo. Generally no significant difference was found between comparison groups regarding individual outcomes such as myocardial infarction. In patients with cardiovascular disease, influenza vaccination may reduce cardiovascular mortality and combined cardiovascular events. However, studies had some risk of bias, and results were not always consistent, so additional higher-quality evidence is necessary to confirm these findings. Not enough evidence was available to establish whether influenza vaccination has a role to play in the primary prevention of cardiovascular disease.\nOutput:\n" }, { "from": "agent", "value": "We included randomised studies comparing people receiving flu vaccine with those receiving no vaccine (placebo or no treatment). For this review update, we found eight trials studying 12,029 participants. Four of these studies examined patients with known heart disease (1682 participants), and the other four focused on the general population or elderly people (10,347 participants). The general population studies reported cardiovascular disease outcomes as part of their safety analyses, but the numbers of cases were too few to allow a judgement on whether flu vaccination was protective in these populations, and no differences were seen between groups. Overall, studies in people with heart disease suggest that flu vaccination may reduce death as a result of cardiovascular disease and may reduce combined cardiovascular disease events (such as heart attacks, strokes, necessity for bypass operations, etc.). However, these studies were small and had some risk of bias, so larger studies of better quality are needed to confirm the results." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Three randomised clinical trials, including 430 participants, met the inclusion criteria for this review; however, data from two trials with 412 participants could be included in only one primary outcome (i.e. mortality). All three trials were at high risk of bias. All three trials included supportive care as cointervention. The comparisons included in the two trials reporting on mortality were: systemic chemotherapy with sorafenib versus no active intervention; and transarterial chemoembolisation plus systemic chemotherapy with sorafenib versus transarterial chemoembolisation alone. The trials did not report the duration of follow-up; however, it appeared that the participants were followed up for a period of about 18 to 30 months. The majority of the participants in the trials had cirrhotic livers. The trials included participants with intermediate-stage hepatocellular carcinoma arising from viral and non-viral aetiologies. The trials did not report the portal hypertension status of the participants. The mortality was 50% to 70% over a median follow-up period of 18 to 30 months. There was no evidence of difference in mortality at maximal follow-up between systemic chemotherapy versus no chemotherapy (hazard ratio 0.85, 95% CI 0.60 to 1.18; participants = 412; studies = 2; I2 = 0%; very low quality evidence). A subgroup analysis performed by stratifying the analysis by the presence or absence of transarterial chemoembolisation as cointervention did not alter the results. None of the trials reported on serious adverse events other than mortality, health-related quality of life, recurrence of hepatocellular carcinoma, or length of hospital stay. One of the trials providing data was funded by the pharmaceutical industry, the other did not report the source of funding, and the trial with no data for the review was also funded by the pharmaceutical industry. We found two ongoing trials. Currently, there is no evidence from randomised clinical trials that people with intermediate-stage hepatocellular carcinoma would benefit from systemic chemotherapy with sorafenib either alone or when transarterial chemoembolisation was used as a cointervention (very low quality evidence). We need high-quality randomised clinical trials designed to measure differences in clinically important outcomes (e.g. all-cause mortality or health-related quality of life).\nOutput:\n" }, { "from": "agent", "value": "Only three trials with 430 participants met our inclusion criteria; however, two of the trials (412 participants) only reported death and no other measures of how well the treatments worked. All three trials included supportive care (treatment to prevent, control, or relieve complications and side effects and improve comfort and quality of life) as a co-intervention. The trials assessed transarterial chemoembolisation (where anti-cancer drugs block the blood supply and treat the cancer through the vessels supplying the cancer), chemotherapy using sorafenib (a drug which blocks cancer growth), or a combination of transarterial chemoembolisation and sorafenib. It appeared that the trials followed participants for about 18 to 30 months from the initiation of treatment. Two trials were funded by the pharmaceutical industry; one trial did not report the source of funding. Over 18 to 30 months, 50% to 75% of participants died. There was no evidence of any difference between the people who received chemotherapy and those who did not receive chemotherapy. None of the trials reported complications, health-related quality of life (a measure of a person's satisfaction with their life and health), cancer recurrence, or length of hospital stay. Overall, there is currently no evidence for benefit of any active treatment in addition to supportive treatment for intermediate-stage hepatocellular carcinoma. There is significant uncertainty on this and further high-quality randomised clinical trials are required. The overall quality of evidence was low or very low and all the trials were at high risk of bias, which means that there is possibility of making the wrong conclusions, overestimating benefits, or underestimating harms of one treatment or the other because of the way that the trials were conducted." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We added seven studies during this update, bringing the total to 15 studies, involving 989 participants. The interventions involved various memory retraining techniques, such as computerised programmes and training on internal and external memory aids. Control groups varied in format from assessment-only groups, discussion and games, non-specific cognitive retraining, and attention or visuospatial training. The risk of bias of the included studies was generally low, but we found eight studies to have high risk of bias related to certain aspects of their methodology. We found significant effect of intervention on objective assessments of memory in both the immediate and long-term follow-ups: standardised mean difference (SMD) 0.23 (95% confidence interval (CI) 0.05 to 0.41) and SMD 0.26 (95% CI 0.03 to 0.49), respectively. We also found significant effect of intervention for quality of life in the immediate follow-up (SMD 0.23 (95% CI 0.05 to 0.41)). These findings showed that the intervention group performed significantly better than the control group. We also found a significant difference for activities of daily living (ADL) in the long-term follow-up (SMD -0.33 (95% CI -0.63 to -0.03)), showing that the control groups had significantly less difficulty completing ADLs than the intervention groups. We found no significant effects, either immediate or long-term, on subjective reports of memory problems (SMD 0.04 (95% CI -0.19 to 0.27) and SMD 0.04 (95% CI -0.19 to 0.27)); on mood (SMD 0.02 (95% CI -0.16 to 0.20) and SMD -0.01 (95% CI -0.21 to 0.20)); and on immediate follow-up for ADL (SMD -0.13 (95% CI -0.60 to 0.33)) and in the long term for quality of life (SMD 0.16 (95% CI -0.03 to 0.36)). We could not complete a sensitivity analysis of intention-to-treat in comparison with per-protocol analysis, due to insufficient information from the included papers. However, a sensitivity analysis of high- versus low-risk studies suggested that while quality of the trials did not affect most outcomes, differences were seen in the objective memory outcomes (both at immediate and long term) and quality of life (immediate) outcome, with studies with higher risk of bias inflating the overall effect size estimates for these outcomes, and the test of overall effect changing from being statistically significant to not significant when studies at high risk of bias were excluded. This suggests that lower-quality studies may have positively influenced the outcomes. There is some evidence to support the effectiveness of memory rehabilitation on memory function, as well as on quality of life. However, the evidence is limited and does not extend to subjective reports of memory functioning or mood. Furthermore, the objective measures used are not ecologically valid measures, and thus potentially limit generalisability of these findings into daily life. Further robust RCTs of high methodological quality and better quality of reporting, using ecologically valid outcome assessments, are still needed.\nOutput:\n" }, { "from": "agent", "value": "This review included 15 studies with 989 participants involving various types of memory retraining techniques, some using computer programs or memory aids such as diaries or calendars. The results of this review showed some evidence to support the use of memory rehabilitation in people with MS. Those participants who had memory rehabilitation had better memory functioning compared to those who did not receive memory rehabilitation, and this difference between groups was found after the intervention was completed and for some time thereafter. However, this outcome was usually measured on assessments that were abstract and did not reflect people’s daily life. Those participants who received memory rehabilitation also showed better quality of life, but this effect was not maintained long term. We also found that those participants who did not receive the memory rehabilitation were better at completing activities of daily living, but these differences between groups were small. The groups who did and did not receive memory rehabilitation did not differ in terms of their subjective reports of memory problems or mood. There are still relatively few large, good-quality studies to base our findings on, so more are needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Six randomized controlled trials were included (total 162 participants, age range 7 to 53 years).  Pimozide was compared with: placebo and haloperidol (two trials), placebo (one trial), haloperidol (one trial), and risperidone (two trials). Methodological quality was rated ‘fair’ for all studies. Studies used different outcome measurement scales for assessing tic severity and adverse effects. Significant clinical heterogeneity made meta-analysis inappropriate. Pimozide was superior to placebo in three studies, though it caused more side effects than placebo in one of these. Pimozide was inferior to haloperidol in one of three studies (the other two showed no significant difference between the drugs), which also showed significantly fewer side effects associated with pimozide. No significant differences between pimozide and risperidone were detected. Pimozide is an effective treatment for tics in Tourette Syndrome, though the number of trials comparing its effect to placebo and other drugs is limited. Trials of longer duration (minimum six months) are needed to investigate the longer-term effects of pimozide compared to atypical neuroleptics.  Future trials should use the Yale Global Tic Severity Scale to assess the main outcome measure, and quantify adverse events with the Extrapyramidal Symptoms Rating Scale.\nOutput:\n" }, { "from": "agent", "value": "The review authors searched the medical literature for clinical trials that compared pimozide to other drugs, or a dummy drug (placebo), for treating tics in patients with Tourette Syndrome. The trials identified showed that pimozide was more effective at reducing tics than placebo. It was slightly less effective than the drug haloperidol, but showed fewer side effects. There were no important differences between pimozide and risperidone for either reduction of tics or side effects. In future, if trials could be run for longer, it would help the investigation of the nature of side effects caused by these drugs." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Three randomised clinical trials were included in this review. All of them had a high risk of bias. One trial was conducted in Shanghai, China. There are several published reports on this trial, in which data were presented differently. According to the 2004 trial report, participants were randomised to screening every six months with alpha-foetoprotein and ultrasonography (n = 9373) versus no screening (n = 9443). We could not draw any definite conclusions from it. A second trial was conducted in Toronto, Canada. In this trial, there were 1069 participants with chronic hepatitis B. The trial compared screening every six months with alpha-foetoprotein alone (n = 532) versus alpha-foetoprotein and ultrasound (n = 538) over a period of five years. This trial was designed as a pilot trial; the small number of participants and the rare events did not allow an effective comparison between the two modes of screening that were studied. The remaining trial, conducted in Taiwan and published as an abstract, was designed as a cluster randomised trial to determine the optimal interval for screening using alpha foetoprotein and ultrasound. Screening intervals of four months and 12 months were compared in the two groups. Further details about the screening strategy were not available. The trial reported on cumulative four-year survival, cumulative three-year incidence of hepatocellular carcinoma, and mean tumour size. The cumulative four-year survival was not significantly different between the two screening intervals. The incidence of hepatocellular cancer was higher in the four-monthly screening group. The included trials did not report on adverse events. It appears that the sensitivity and specificity of the screening modes were poor, accounting for a substantial number of false-positive and false-negative screening results. There is not enough evidence to support or refute the value of alpha-foetoprotein or ultrasound screening, or both, of hepatitis B surface antigen (HBsAg) positive patients for hepatocellular carcinoma. More and better designed randomised trials are required to compare screening against no screening.\nOutput:\n" }, { "from": "agent", "value": "Only three trials could be included in this review. One of these trials was conducted in Shanghai, China. It compared screening twice yearly with ultrasound and alpha-foetoprotein against no screening. The trial has a high risk of systematic errors (bias) and several published reports of the trial provide different results. Another trial was conducted in Toronto, Canada. It compared screening with alpha-foetoprotein and ultrasound versus screening with alpha-foetoprotein alone. This trial had too few participants. As there were no participants who were not screened, we cannot assess whether screening is effective in reducing mortality. The remaining trial was published as an abstract only. It was designed to determine the optimal time interval for screening using alpha fetoprotein and ultrasound. The cumulative four-year survival was not significantly different between the two studied screening intervals of four months and 12 months. Thus, to date, there is insufficient evidence regarding screening for liver cancer among patients with chronic hepatitis B infection." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included two trials involving 754 participants. One new trial of 660 participants showed the same success rate of vacuum procedure of 98.2% by both methods (risk ratio (RR) 1.00, 95% confidence interval (CI) 0.98 to 1.02). The two included trials showed significant reductions in the time between applying the vacuum cup and delivery, (one trial (74 women): mean difference (MD) -6.10 minutes, 95% CI -8.83 to -3.37 and the other trial (660 women): with median difference -4.4 minutes, 95% CI -4.8 to -4.0). The two included trials showed no significant difference in detachment rate (RR 0.85, 95% CI 0.38 to 1.86, 2 studies, 754 women), no significant difference in Apgar score below seven at one minute (RR 1.04, 95% CI 0.51 to 2.09) and five minutes (RR 1.00, 95% CI 0.29 to 3.42), no significant differences in scalp abrasions or lacerations, cephalhematoma, subgaleal hemorrhage and hyperbilirubinemia. There were no significant differences between the two methods in all secondary outcomes. The rapid negative pressure application for vacuum assisted vaginal birth reduces duration of the procedure whilst there is no evidence of differences in maternal and neonatal outcomes. Rapid method of negative application should be recommended for vacuum extraction assisted vaginal delivery.\nOutput:\n" }, { "from": "agent", "value": "Two good quality randomized controlled trials involving 754 women were identified. Rapid negative pressure application reduced the duration of the procedure without any evidence of differences in outcomes for the mother or infant. Rapid method of negative pressure application should be recommended for vacuum extraction assisted vaginal delivery." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included two studies with 72 participants. Overall, the two studies were at moderate risk of bias. The evidence was derived from group mean data and completer analysis (very low quality evidence overall). We rated the quality of all outcomes according to GRADE as very low due to indirectness, imprecision and potential reporting bias. The primary outcomes in our review were participant-reported pain relief of 50% or greater, Patient Global Impression of Change (PGIC) much or very much improved, withdrawal due to adverse events (tolerability) and serious adverse events (safety). Nabilone was compared to placebo and to amitriptyline in one study each. Study sizes were 32 and 40 participants. One study used a cross-over design and one used a parallel group design; study duration was four or six weeks. Both studies used nabilone, a synthetic cannabinoid, with a bedtime dosage of 1 mg/day. No study reported the proportion of participants experiencing at least 30% or 50% pain relief or who were very much improved. No study provided first or second tier (high to moderate quality) evidence for an outcome of efficacy, tolerability and safety. Third tier (very low quality) evidence indicated greater reduction of pain and limitations of HRQoL compared to placebo in one study. There were no significant differences to placebo noted for fatigue and depression (very low quality evidence). Third tier evidence indicated better effects of nabilone on sleep than amitriptyline (very low quality evidence). There were no significant differences between the two drugs noted for pain, mood and HRQoL (very low quality evidence). More participants dropped out due to adverse events in the nabilone groups (4/52 participants) than in the control groups (1/20 in placebo and 0/32 in amitriptyline group). The most frequent adverse events were dizziness, nausea, dry mouth and drowsiness (six participants with nabilone). Neither study reported serious adverse events during the period of both studies. We planned to create a GRADE 'Summary of findings' table, but due to the scarcity of data we were unable to do this. We found no relevant study with herbal cannabis, plant-based cannabinoids or synthetic cannabinoids other than nabilone in fibromyalgia. We found no convincing, unbiased, high quality evidence suggesting that nabilone is of value in treating people with fibromyalgia. The tolerability of nabilone was low in people with fibromyalgia.\nOutput:\n" }, { "from": "agent", "value": "In April 2016 we searched for reports of clinical trials that used cannabis products to treat symptoms in adults with fibromyalgia. We found two small, moderate quality studies, of four and six weeks long, including 72 participants. Both studies tested nabilone, a synthetic (man-made) cannabis product, comparing it with placebo (a dummy pill) or amitriptyline (an antidepressant frequently used in the treatment of fibromyalgia). Nabilone did not convincingly relieve fibromyalgia symptoms (pain, sleep, fatigue) better than placebo or amitriptyline (very low quality evidence). Compared with placebo and amitriptyline, more people experienced side effects and left the study due to side effects (very low quality evidence). There were no serious side effects reported. We found no relevant study with herbal cannabis, plant-based cannabinoids or other synthetic cannabinoids than nabilone in fibromyalgia. There was not enough high quality evidence available to draw any robust conclusions. We found no studies on medical cannabis in fibromyalgia." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified five trials. There were 1633 participants in the narrow excision margin group and 1664 in the wide excision margin group. Narrow margin definition ranged from 1 to 2 cm; wide margins ranged from 3 to 5 cm. Median follow-up ranged from 5 to 16 years. This systematic review summarises the evidence regarding width of excision margins for primary cutaneous melanoma. None of the five published trials, nor our meta-analysis, showed a statistically significant difference in overall survival between narrow or wide excision. The summary estimate for overall survival favoured wide excision by a small degree [Hazard Ratio 1.04; 95% confidence interval 0.95 to 1.15; P = 0.40], but the result was not significantly different. This result is compatible with both a 5% relative reduction in overall mortality favouring narrower excision and a 15% relative reduction in overall mortality favouring wider excision. Therefore, a small (but potentially important) difference in overall survival between wide and narrow excision margins cannot be confidently ruled out. The summary estimate for recurrence free survival favoured wide excision [Hazard Ratio 1.13; P = 0.06; 95% confidence interval 0.99 to 1.28] but again the result did not reach statistical significance (P < 0.05 level). Current randomised trial evidence is insufficient to address optimal excision margins for primary cutaneous melanoma.\nOutput:\n" }, { "from": "agent", "value": "We found five published randomised trials, none of which showed a statistically significant difference in overall survival for patients who had either narrow or wide removal of the melanoma and surrounding tissue.  Similarly, our meta-analysis showed there was no statistically significant difference in overall survival between the two groups treated with either narrow or wide excision. The summary estimate for overall survival favoured wide excision by a small degree, but the result was not significantly different. This result is compatible with both a 5% relative reduction in overall mortality favouring narrower excision and a 15% relative reduction in overall mortality favouring wider excision. Current randomised trial evidence is insufficient to address optimal excision margins for primary cutaneous melanoma." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included five studies involving 1140 women with asymptomatic bacteriuria. We did not perform meta-analysis; each trial examined different antibiotic regimens and so we were not able to pool results. In a study comparing a single dose of fosfomycin trometamol 3 g with a five-day course of cefuroxime, there was no significant difference in persistent infection (risk ratio (RR) 1.36, 95% confidence interval (CI) 0.24 to 7.75), shift to other antibiotics (RR 0.08, 95% CI 0.00 to 1.45), or in allergy or pruritus (RR 2.73, 95% CI 0.11 to 65.24). A comparison of seven-day courses of 400 mg pivmecillinam versus 500 mg ampicillin, both given four times daily, showed no significant difference in persistent infection at two weeks or recurrent infection, but there was an increase in vomiting (RR 4.57, 95% CI 1.40 to 14.90) and women were more likely to stop treatment early with pivmecillinam (RR 8.82, 95% CI 1.16 to 66.95). When cephalexin 1 g versus Miraxid® (pivmecillinam 200 mg and pivampicillin 250 mg) were given twice-daily for three days, there was no significant difference in persistent or recurrent infection. A one- versus seven-day course of nitrofurantoin resulted in more persistent infection with the shorter course (RR 1.76, 95% CI 1.29 to 2.40), but no significant difference in symptomatic infection at two weeks, nausea, or preterm birth. Comparing cycloserine with sulphadimidine, no significant differences in symptomatic, persistent, or recurrent infections were noted. We cannot draw any definite conclusion on the most effective and safest antibiotic regimen for the initial treatment of asymptomatic bacteriuria in pregnancy. One study showed advantages with a longer course of nitrofurantoin, and another showed better tolerability with ampicillin compared with pivmecillinam; otherwise, there was no significant difference demonstrated between groups treated with different antibiotics. Given this lack of conclusive evidence, it may be useful for clinicians to consider factors such as cost, local availability and side effects in the selection of the best treatment option.\nOutput:\n" }, { "from": "agent", "value": "We included five randomized controlled trials involving 1140 women with urine test results showing asymptomatic bacteriuria. Each of the five studies looked at different antibiotics; thus, we have not pooled the results. Four of the comparisons (fosfomycin versus cefuroxime; pivmecillinam versus ampicillin; cephalexin versus Miraxid® (pivmecillinam 200 mg and pivampicillin 250 mg); and cycloserine versus sulphadimidine) showed no definite advantage of one antibiotic over another for treating infection, side effects, or safety. Ampicillin compared with pivmecillinam resulted in less vomiting and was thus better tolerated by the women in one study. There was however no difference in curing present infection and preventing recurring infection in women who took ampicillin compared with those who took pivmecillinam. In another study comparing a one-day versus a seven-day course of nitrofurantoin, the longer course was better in treating bacteria in urine during pregnancy. Women receiving the shorter course had more persistent infection but no clear difference in symptomatic infection at two weeks, nausea or preterm birth." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Seven studies, involving 632 DME eyes were included. Four examined the effectiveness of intravitreal triamcinolone acetate injection (IVTA), three examined intravitreal steroids implantation (fluocinolone acetonide implant (FAI) or dexamethasone drug delivery system (DDS)). Two trials were at low risk of bias, one was at median risk of bias, two were at high risk of bias and the remaining two were at unclear risk of bias. The preponderance of data suggest a beneficial effect from IVTA. Comparing IVTA with controls, the mean difference in visual acuity was -0.15 LogMAR (95% CI -0.21 to -0.09) at 3 months (based on three trials), -0.23 LogMAR (95% CI -0.33 to -0.13) at 6 months (two trials), -0.29 LogMAR (95% CI -0.47 to -0.11) at 9 months (one trial), and -0.11 LogMAR (95% CI -0.20 to -0.03) at 24 months (one trial), all in favor of IVTA. The relative risk (RR) for one or more lines improvement in visual acuity was 2.85 (95% CI 1.59 to 5.10) at 3 months (two trials), 1.25 (95% CI 0.66 to 2.38) at 6 months (one trial), and 2.17 (95% CI 1.15 to 4.11) at 24 months (one trial), all in favor of IVTA. We did not find evidence for three or more lines improvement in visual acuity. The mean difference in retinal thickness was -131.97 um (95% CI -169.08 to -94.86) at 3 months (two trials), -135.00 um (95% CI -194.50 to -75.50) at 6 months (one trial), -133.00 um (95% CI -199.86 to -66.14) at 9 months (one trial), and -59.00 um (95% CI -103.50 to -14.50) at 24 months (one trial), all in favor of IVTA. The RR for at least one grade macular edema resolution was 5.15 (95% CI 2.23 to 11.88) at 3 months in favor of IVTA (one trial). Two trials reported improved clinical outcome when FAI was compared to standard of care. Beneficial effect was also observed in one dexamethasone DDS trial. Increased intraocular pressure and cataract formation were side effects requiring monitoring and management. RCTs included in this review suggest that steroids placed inside the eye by either intravitreal injection or surgical implantation may improve visual outcomes in eyes with persistent or refractory DME. Since the studies in our report focused on chronic or refractory DME, the question arises whether intravitreal steroids therapy could be of value in other stages of DME, especially the earlier stages either as standalone therapy or in combination with other therapies, such as laser photocoagulation.\nOutput:\n" }, { "from": "agent", "value": "This systematic review included seven randomized clinical trials involving 632 eyes from five countries evaluating the effectiveness and safety of intravitreal steroids for treating DME. Two trials were at low risk of bias, one was at median risk of bias, two were at high risk of bias, and the remaining two had an unclear risk of bias. In this systematic review, the preponderance of data suggest a beneficial effect from IVTA. The average improvement in visual acuity was 7.5 letters more (-0.15 LogMAR; 95% CI -0.21 to -0.09) in the IVTA treated eyes than in those treated with other therapies at three months (based on three trials), 11.5 letters more (-0.23 LogMAR; 95% CI -0.33 to -0.13) at six months (two trials), 14.5 letters more (-0.29 LogMAR; 95% CI -0.47 to -0.11) at nine months (one trial), and 5.7 letters more (-0.11 LogMAR; 95% CI -0.20 to -0.03) at 24 months (one trial). Improved clinical outcomes were also reported in FAI and dexamethasone DDS trials. Elevation of intraocular pressure and cataract progression occur in both IVTA and implants treated eyes but appear manageable." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Fifty six trials met the inclusion criteria, involving 3257 children of whom 2412 used an alarm. The quality of many trials was poor, and evidence for many comparisons was inadequate. Most alarms used audio methods. Compared to no treatment, about two thirds of children became dry during alarm use (RR for failure 0.38, 95% CI 0.33 to 0.45). Nearly half who persisted with alarm use remained dry after treatment finished, compared to almost none after no treatment (RR of failure or relapse 45 of 81 (55%) versus 80 of 81 (99%), RR 0.56, 95% CI 0.46 to 0.68). There was insufficient evidence to draw conclusions about different types of alarm, or about how alarms compare to other behavioural interventions. Relapse rates were lower when overlearning was added to alarm treatment (RR 1.92, 95% CI 1.27 to 2.92) or if dry bed training was used as well (RR 2.0, 95% CI 1.25 to 3.20). Penalties for wet beds appeared to be counter-productive. Alarms using electric shocks were unacceptable to children or their parents. Although desmopressin may have a more immediate effect, alarms appeared to be as effective by the end of a course of treatment (RR 0.85, 95% CI 0.53 to 1.37) but their relative effectiveness after stopping treatment was unclear from two small trials which compared them directly. Evidence about the benefit of supplementing alarm treatment with desmopressin was conflicting. Alarms were not significantly better than tricyclics during treatment (RR 0.59, 95% CI 0.32 to 1.09) but the relapse rate was less afterwards (7 of 12 (58%) versus 12 of 12 (100%), RR 0.58, 95% CI 0.36 to 0.94). However, other Cochrane reviews of desmopressin and tricyclics suggest that drug treatment alone, while effective for some children during treatment, is unlikely to be followed by sustained cure as almost all the children relapse. Alarm interventions are an effective treatment for nocturnal bedwetting in children. Alarms appear more effective than desmopressin or tricyclics because around half the children remain dry after alarm treatment stops. Overlearning (giving extra fluids at bedtime after successfully becoming dry using an alarm), dry bed training and avoiding penalties may further reduce the relapse rate. Better quality research comparing alarms with other treatments is needed, including follow-up to determine relapse rates.\nOutput:\n" }, { "from": "agent", "value": "The review of trials found 56 studies involving 3257 children. Alarm interventions reduce night-time bed wetting in about two thirds of children during treatment, and about half the children remained dry after stopping using the alarm. Alarms take longer to reduce bedwetting than desmopressin, but their effects continue after treatment in half the children who use alarms. So alarms are better in the long term than treatment with desmopressin or tricyclic drugs. Overlearning (giving children extra fluids at bedtime after successfully becoming dry using an alarm) and dry bed training (getting children to go to the toilet repeatedly and changing their own sheets when they wet) may reduce the relapse rate. There are no serious side-effects, which can occur with drug treatment. However, children need more supervision and time from other family members at first. There was not enough evidence with which to compare alarms with other non-drug treatments. Because some of the studies were of poor quality, better research comparing alarms with other treatments is needed, including follow-up to measure relapse rates." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included five RCTs (2277 participants) that compared different frequencies of CVAD dressing changes. The studies were all conducted in Europe and published between 1995 and 2009. Participants were recruited from the intensive care and cancer care departments of one children's and four adult hospitals. The studies used a variety of transparent dressings and compared a longer interval between dressing changes (5 to15 days; intervention) with a shorter interval between changes (2 to 5 days; control). In each study participants were followed up until the CVAD was removed or until discharge from ICU or hospital. Confirmed catheter-related bloodstream infection (CRBSI) One trial randomised 995 people receiving central venous catheters to a longer or shorter interval between dressing changes and measured CRBSI. It is unclear whether there is a difference in the risk of CRBSI between people having long or short intervals between dressing changes (RR 1.42, 95% confidence interval (CI) 0.40 to 4.98) (low quality evidence). Suspected catheter-related bloodstream infection Two trials randomised a total of 151 participants to longer or shorter dressing intervals and measured suspected CRBSI. It is unclear whether there is a difference in the risk of suspected CRBSI between people having long or short intervals between dressing changes (RR 0.70, 95% CI 0.23 to 2.10) (low quality evidence). All cause mortality Three trials randomised a total of 896 participants to longer or shorter dressing intervals and measured all cause mortality. It is unclear whether there is a difference in the risk of death from any cause between people having long or short intervals between dressing changes (RR 1.06, 95% CI 0.90 to 1.25) (low quality evidence). Catheter-site infection Two trials randomised a total of 371 participants to longer or shorter dressing intervals and measured catheter-site infection. It is unclear whether there is a difference in risk of catheter-site infection between people having long or short intervals between dressing changes (RR 1.07, 95% CI 0.71 to 1.63) (low quality evidence). Skin damage One small trial (112 children) and three trials (1475 adults) measured skin damage. There was very low quality evidence for the effect of long intervals between dressing changes on skin damage compared with short intervals (children: RR of scoring ≥ 2 on the skin damage scale 0.33, 95% CI 0.16 to 0.68; data for adults not pooled). Pain Two studies involving 193 participants measured pain. It is unclear if there is a difference between long and short interval dressing changes on pain during dressing removal (RR 0.80, 95% CI 0.46 to 1.38) (low quality evidence). The best available evidence is currently inconclusive regarding whether longer intervals between CVAD dressing changes are associated with more or less catheter-related infection, mortality or pain than shorter intervals.\nOutput:\n" }, { "from": "agent", "value": "The five studies that were included in the review were published between 1995 and 2009 and involved a total of 2277 participants. Four countries were represented (two studies from France and one each from Italy, Sweden, and the Czech Republic). One study involved children and the remaining four trials included only adults. Four of the studies included cancer patients and one included patients in an intensive care unit. We classified the time intervals between dressing changes as short (2 - 5 days) in the more frequently changed dressings group and long (5-15 days) in the less frequently changed group. All studies used transparent dressings made of synthetic materials and two studies used gauze (a fabric dressing that does not stick to the skin) secured with tape when skin was damaged. CVAD dressings were monitored on a daily basis in all trials and participants were followed up at least until the CVAD was removed or until discharge. In one study, the manufacturer provided one of the products, but had no influence in the design or how the results were analysed and reported. The current evidence leaves us uncertain whether the frequency of dressing changes for CVADs influences risk of CRBSI or death. Of particular interest to patients are problems that may be associated with the dressing themselves, such as pain when they are removed and the skin damage that the dressing may cause. We found no clear evidence that pain, which was assessed daily, was affected by the frequency of dressing changes. The quality of the evidence was very low or low. We downgraded quality because of small and few studies, poor study designs and differences in results between the studies. Better designed studies are still needed to show whether longer interval or shorter intervals between dressing changes are more effective in preventing catheter related infections, mortality, skin damage, dressing removal pain, quality of life and cost. This plain language summary is up-to-date as of 10 June 2015." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: One hundred and eighteen studies with 138 treatment groups and 17,364 participants were included in this review. Fifty-seven of these studies were included in the original version of this review while 61 were added, including 27 on interventions that were not considered in the original version. Interventions included amiodarone, beta-blockers, sotalol, magnesium, atrial pacing and posterior pericardiotomy. Each of the studied interventions significantly reduced the rate of post-operative atrial fibrillation after cardiac surgery compared with a control. Beta-blockers (odds ratio (OR) 0.33; 95% confidence interval) CI 0.26 to 0.43; I2 = 55%) and sotalol (OR 0.34; 95% CI 0.26 to 0.43; I2 = 3%) appear to have similar efficacy while magnesium's efficacy (OR 0.55; 95% CI 0.41 to 0.73; I2 = 51%) may be slightly less. Amiodarone (OR 0.43; 95% CI 0.34 to 0.54; I2 = 63%), atrial pacing (OR 0.47; 95% CI 0.36 to 0.61; I2 = 50%) and posterior pericardiotomy (OR 0.35; 95% CI 0.18 to 0.67; I2 = 66%) were all found to be effective. Prophylactic intervention decreased the hospital length of stay by approximately two-thirds of a day and decreased the cost of hospital treatment by roughly $1250 US. Intervention was also found to reduce the odds of post-operative stroke, though this reduction did not reach statistical significance (OR 0.69; 95% CI 0.47 to 1.01; I2 = 0%). No significant effect on all-cause or cardiovascular mortality was demonstrated. Prophylaxis to prevent atrial fibrillation after cardiac surgery with any of the studied pharmacological or non-pharmacological interventions may be favored because of its reduction in the rate of atrial fibrillation, decrease in the length of stay and cost of hospital treatment and a possible decrease in the rate of stroke. However, this review is limited by the quality of the available data and heterogeneity between the included studies. Selection of appropriate interventions may depend on the individual patient situation and should take into consideration adverse effects and the cost associated with each approach.\nOutput:\n" }, { "from": "agent", "value": "Atrial fibrillation after heart surgery is a common complication that has been associated with poor outcomes. We reviewed the literature to better understand the role of preventative interventions for this condition. By combining the results of 118 studies with 17,364 participants, we are able to gain a better understanding of the evidence behind each of these interventions. All of the interventions studied were effective in reducing the occurrence of atrial fibrillation, length of hospital stay, cost of hospital treatment and may be effective in reducing the risk of stroke. The interventions did not have an effect on death after heart surgery. It was not possible to analyze the adverse events associated with the medications studied in this review, but these should be considered by clinicians when choosing an appropriate intervention for their patients. Furthermore, differences in the design between the studies combined in this review may complicate interpretation of these results." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Thirteen trials met the inclusion criteria and are included in the review. All studies had at least one domain with unclear risk of bias. Some studies were at high risk of bias for random sequence generation (two trials), allocation concealment (two trials), blinding of outcome assessors (one trial) and incomplete outcome data (one trial). Duration and content of multiple risk factor interventions varied across the trials. Two trials recruited healthy participants and the other 11 trials recruited people with varying risks of CVD, such as participants with known hypertension and type 2 diabetes. Only one study reported CVD outcomes and multiple risk factor interventions did not reduce the incidence of cardiovascular events (RR 0.57, 95% CI 0.11 to 3.07, 232 participants, low-quality evidence); the result is imprecise (a wide confidence interval and small sample size) and makes it difficult to draw a reliable conclusion. None of the included trials reported all-cause mortality. The pooled effect indicated a reduction in systolic blood pressure (MD -6.72 mmHg, 95% CI -9.82 to -3.61, I² = 91%, 4868 participants, low-quality evidence), diastolic blood pressure (MD -4.40 mmHg, 95% CI -6.47 to -2.34, I² = 92%, 4701 participants, low-quality evidence), body mass index (MD -0.76 kg/m², 95% CI -1.29 to -0.22, I² = 80%, 2984 participants, low-quality evidence) and waist circumference (MD -3.31, 95% CI -4.77 to -1.86, I² = 55%, 393 participants, moderate-quality evidence) in favour of multiple risk factor interventions, but there was substantial heterogeneity. There was insufficient evidence to determine the effect of these interventions on consumption of fruit or vegetables, smoking cessation, glycated haemoglobin, fasting blood sugar, high density lipoprotein (HDL) cholesterol, low density lipoprotein (LDL) cholesterol and total cholesterol. None of the included trials reported on adverse events. Due to the limited evidence currently available, we can draw no conclusions as to the effectiveness of multiple risk factor interventions on combined CVD events and mortality. There is some evidence that multiple risk factor interventions may lower blood pressure levels, body mass index and waist circumference in populations in LMIC settings at high risk of hypertension and diabetes. There was considerable heterogeneity between the trials, the trials were small, and at some risk of bias. Larger studies with longer follow-up periods are required to confirm whether multiple risk factor interventions lead to reduced CVD events and mortality in LMIC settings.\nOutput:\n" }, { "from": "agent", "value": "We performed a thorough search of the medical literature up to June 2014. We identified 13 trials that recruited 7310 participants. Two trials recruited healthy participants and the other 11 trials recruited people at varying risk of CVD, such as participants with known hypertension(\"high blood pressure\") and type 2 diabetes, and randomly assigned them to either a multiple risk factor intervention or to no intervention. The trials were conducted between 2001 and 2010, and published between 2004 and 2012. Three trials were conducted in Turkey. Two trials each were conducted in China and Mexico. One trial recruited participants from both China and Nigeria. The other trials were conducted in Brazil, India, Pakistan, Romania and Jordan. The content of the interventions varied across the trials; most of the trials included dietary advice and advice on physical activity. The trials follow-up the participants between six months to 30 months (average follow-up period was 13.3 months). We found that evidence for effects on cardiovascular disease events was scarce, with only one trial reporting these. None of the included trials reported deaths from any cause. Multiple risk factors interventions may lower systolic blood pressure, diastolic blood pressure, body mass index and waist circumference. We found no difference for eating more fruit and vegetables, rates of smoking cessation, measure of blood glucose sugar was for the past two to three months, fasting blood sugar, high density lipoprotein (HDL) cholesterol, low density lipoprotein (LDL) cholesterol and total cholesterol. None of the included trials reported on harms. Overall, the studies included in this review were at some risk of bias and there was variation between the results of the studies when we analysed the data. Our findings should be treated with some caution." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 16 trials, with a total of 2144 participants. Two studies included children only. The other 14 studies included predominantly young adults, of whom over 60% were male. Seven studies recruited people with ankle sprains only. Most studies were at low or unclear risk of bias; however, two were at high risk of selection bias, three were at high risk of bias from lack of blinding, one was at high risk of bias due to incomplete outcome data, and four were at high risk of selective outcome reporting bias. The evidence was usually either low quality or very low quality, reflecting study limitations, indirectness such from as suboptimal dosing of single comparators, imprecision, or one or more of these. Thus we are either uncertain or very uncertain of the estimates. Nine studies, involving 991 participants, compared NSAIDs with paracetamol. While tending to favour paracetamol, there was a lack of clinically important differences between the two groups in pain at less than 24 hours (377 participants, 4 studies; moderate-quality evidence), at days 1 to 3 (431 participants, 4 studies; low quality), and at day 7 or over (467 participants, 4 studies; low quality). A similar lack of difference between the two groups applied to swelling at day 3 (86 participants, 1 study; very low quality) and at day 7 or over (77 participants, 1 study; low quality). There was little difference between the two groups in return to function at day 7 or over (316 participants, 3 studies; very low quality): based on an assumed recovery of function of 804 per 1000 participants in the paracetamol group, 8 fewer per 1000 recovered in the NSAID group (95% confidence interval (CI) 80 fewer to 73 more). There was low-quality evidence of a lower risk of gastrointestinal adverse events in the paracetamol group: based on an assumed risk of gastrointestinal adverse events of 16 per 1000 participants in the paracetamol group, 13 more participants per 1000 had a gastrointestinal adverse event in the NSAID group (95% CI 0 to 35 more). Four studies, involving 958 participants, compared NSAIDs with opioids. Since a study of a selective COX-2 inhibitor NSAID (valdecoxib) that was subsequently withdrawn from the market dominates the evidence for this comparison (706 participants included in the analyses for pain, function and gastrointestinal adverse events), the applicability of these results is in doubt and we give only a brief summary. There was low quality evidence for a lack of clinically important differences between the two groups regarding pain at less than 24 hours, at days 4 to 6, and at day 7. Evidence from single studies showed a similar lack of difference between the two groups for swelling at day 3 (68 participants) and day 10 (84 participants). Return to function at day 7 or over favoured the NSAID group (low-quality), and there were fewer gastrointestinal adverse events in the selective COX-2 inhibitor NSAID group (very low quality). Four studies, involving 240 participants, compared NSAIDs with the combination of paracetamol and an opioid. The applicability of findings from these studies is partly in question because the dextropropoxyphene combination analgesic agents used are no longer in general use. While the point estimates favoured NSAID, the very low-quality evidence did not show a difference between the two interventions in the numbers with little or no pain at day 1 (51 participants, 1 study), day 3 (149 participants, 2 studies), or day 7 (138 participants, 2 studies). Very low-quality evidence showed a similar lack of difference between the two groups applied to swelling at day 3 (reported in two studies) and at day 7 (reported in two studies), in return to function at day 7 (89 participants, 1 study), and in gastrointestinal adverse events (141 participants, 3 studies). No studies compared NSAIDs with complementary and alternative medicines, and no study reported re-injury rates. There is generally low- or very low-quality but consistent evidence of no clinically important difference in analgesic efficacy between NSAIDs and other oral analgesics. There is low-quality evidence of more gastrointestinal adverse effects with non-selective NSAID compared with paracetamol. There is low- or very low-quality evidence of better function and fewer adverse events with NSAIDs compared with opioid-containing analgesics; however, one study dominated this evidence using a now unavailable COX-2 selective NSAID and is of uncertain applicability. Further research is required to determine whether there is any difference in return to function or adverse effects between both non-selective and COX-2 selective NSAIDs versus paracetamol.\nOutput:\n" }, { "from": "agent", "value": "The evidence available for most outcomes was either low or very low quality. This means that we are unsure of the reliability of these results. We found no evidence for an important difference between NSAIDs and paracetamol for people with strains, sprains and bruises for pain relief, swelling or return to function at seven days or over. However, there was some evidence that people treated with NSAIDs had slightly more side-effects related to the stomach or intestines. Although there was some evidence to suggest a greater return to function at seven days and fewer side-effects for people with sprains, strains and bruises using an NSAID compared with an opioid, we cannot say if this would apply to drugs that are currently available. This is because most of the evidence came from a study that tested an NSAID that is no longer on the market. We found no evidence for an important difference between NSAIDs and a combination of paracetamol and opioid for people with sprains, strains and bruises regarding pain relief, swelling, return to function at seven days or over, or gut-related side-effects. However, the combination painkiller used in the studies is not now in common use. This means that we cannot be sure that these results would currently apply. We found no studies comparing NSAIDs and complementary and alternative medicines. Also, no studies looked at the risk of re-injury after treatment. This review found low or very low-quality but consistent evidence showing no important difference between NSAIDs and paracetamol, opioids or a combination of paracetamol and opioid in pain or swelling after a soft tissue injury. There is low-quality evidence of more gut-related complications with NSAIDs compared with paracetamol. Although there is either low- or very low-quality evidence of better function and fewer adverse events with NSAIDs compared with opioid-containing analgesics, one study dominated this evidence using a now unavailable NSAID and is therefore of uncertain applicability. Further research is required to determine whether there is any difference in return to function or adverse effects between different types of NSAIDs versus paracetamol." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included four trials involving 543 women and their babies (but only data from 521 women and their babies is included in our analyses). Three of the four included studies had moderate to high risk of bias and one study was at low to moderate risk of bias. Babies born to women receiving management for borderline GDM (generally dietary counselling and metabolic monitoring) were less likely to be macrosomic (birthweight greater than 4000 g) (three trials, 438 infants, risk ratio (RR) 0.38, 95% confidence interval (CI) 0.19 to 0.74) or large-for-gestational (LGA) age (three trials, 438 infants, RR 0.37, 95% CI 0.20 to 0.66) when compared with those born to women in the routine care group. There were no significant differences in rates of caesarean section (three trials, 509 women, RR 0.93, 95% CI 0.68 to 1.27) and operative vaginal birth (one trial, 83 women, RR 1.37, 95% CI 0.20 to 9.27) between the two groups. This review found interventions including providing dietary advice and blood glucose level monitoring for women with pregnancy hyperglycaemia not meeting GDM and T2DM diagnostic criteria helped reduce the number of macrosomic and LGA babies without increasing caesarean section and operative vaginal birth rates. It is important to notice that the results of this review were based on four small randomised trials with moderate to high risk of bias without follow-up outcomes for both women and their babies.\nOutput:\n" }, { "from": "agent", "value": "This review found dietary advice or counselling and blood glucose level monitoring for women with borderline GDM helped reduce the number of macrosomic and LGA babies. A single trial found that the interventions led to more inductions of labour. The interventions did not increase the risk of caesarean sections, operative vaginal births or women's weight gain in pregnancy. These findings were based on four small randomised controlled trials (involving 543 women). The trials were of moderate to high risk of bias and only data from 521 women and their babies is included in our analyses. Until additional evidence from large well designed randomised trials becomes available, current evidence is insufficient to make conclusive recommendations for the management of women with pregnancy high blood glucose concentrations not meeting GDM (or type 2 diabetes) diagnostic criteria." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 2292 unique records.We included 129 records reporting on 121 studies, including 12 ongoing studies and two studies awaiting classification. We judged the overall risk of bias of two studies as low. Selection bias was the most relevant risk of bias domain across the included studies, with 78 studies not clearly reporting the method used for random sequence generation. Reporting bias was the domain with least risk of bias, with 12 studies not reporting all outcomes that researchers intended to investigate. Any intervention versus placebo or no prophylaxis In comparison with placebo, any intervention seems to have a beneficial effect on the occurrence of upper GI bleeding (risk ratio (RR) 0.47, 95% confidence interval (CI) 0.39 to 0.57; moderate certainty of evidence). The use of any intervention reduced the risk of upper GI bleeding by 10% (95% CI -12.0% to -7%). The effect estimate of any intervention versus placebo or no prophylaxis with respect to the occurrence of nosocomial pneumonia, all-cause mortality in the ICU, duration of ICU stay, duration of intubation (all with low certainty of evidence), the number of participants requiring blood transfusions (moderate certainty of evidence), and the units of blood transfused was consistent with benefits and harms. None of the included studies explicitly reported on serious adverse events. Individual interventions versus placebo or no prophylaxis In comparison with placebo or no prophylaxis, antacids, H2 receptor antagonists, and sucralfate were effective in preventing upper GI bleeding in ICU patients. Researchers found that with H2 receptor antagonists compared with placebo or no prophylaxis, 11% less developed upper GI bleeding (95% CI -0.16 to -0.06; RR 0.50, 95% CI 0.36 to 0.70; 24 studies; 2149 participants; moderate certainty of evidence). Of ICU patients taking antacids versus placebo or no prophylaxis, 9% less developed upper GI bleeding (95% CI -0.17 to -0.00; RR 0.49, 95% CI 0.25 to 0.99; eight studies; 774 participants; low certainty of evidence). Among ICU patients taking sucralfate versus placebo or no prophylaxis, 5% less had upper GI bleeding (95% CI -0.10 to -0.01; RR 0.53, 95% CI 0.32 to 0.88; seven studies; 598 participants; moderate certainty of evidence). The remaining interventions including proton pump inhibitors did not show a significant effect in preventing upper GI bleeding in ICU patients when compared with placebo or no prophylaxis. Regarding the occurrence of nosocomial pneumonia, the effects of H2 receptor antagonists (RR 1.12, 95% CI 0.85 to 1.48; eight studies; 945 participants; low certainty of evidence) and of sucralfate (RR 1.33, 95% CI 0.86 to 2.04; four studies; 450 participants; low certainty of evidence) were consistent with benefits and harms when compared with placebo or no prophylaxis. None of the studies comparing antacids versus placebo or no prophylaxis provided data regarding nosocomial pneumonia. H2 receptor antagonists versus proton pump inhibitors H2 receptor antagonists and proton pump inhibitors are most commonly used in practice to prevent upper GI bleeding in ICU patients. Proton pump inhibitors significantly more often prevented upper GI bleeding in ICU patients compared with H2 receptor antagonists (RR 2.90, 95% CI 1.83 to 4.58; 18 studies; 1636 participants; low certainty of evidence). When taking H2 receptor antagonists, 4.8% more patients might experience upper GI bleeding (95% CI 2.1% to 9%). Nosocomial pneumonia occurred in similar proportions of participants taking H2 receptor antagonists and participants taking proton pump inhibitors (RR 1.02, 95% CI 0.77 to 1.35; 10 studies; 1256 participants; low certainty of evidence). This review shows that antacids, sucralfate, and H2 receptor antagonists might be more effective in preventing upper GI bleeding in ICU patients compared with placebo or no prophylaxis. The effect estimates of any treatment versus no prophylaxis on nosocomial pneumonia were consistent with benefits and harms. Evidence of low certainty suggests that proton pump inhibitors might be more effective than H2 receptor antagonists. Therefore, patient-relevant benefits and especially harms of H2 receptor antagonists compared with proton pump inhibitors need to be assessed by larger, high-quality RCTs to confirm the results of previously conducted, smaller, and older studies.\nOutput:\n" }, { "from": "agent", "value": "The evidence is current to August 2017. We included 106 studies with a total of 15,027 critically ill participants of any age and any gender. Relevant effects were found for the following drugs: H2 receptor antagonists, antacids, sucralfate, and proton pump inhibitors. H2 receptor antagonists inhibit gastric acid secretion by blocking histamine receptors but can cause a small number of blood platelets (thrombocytopaenia), inflammation of the kidney (interstitial nephritis), and confusion. Antacids neutralise stomach acid but may cause diarrhoea or constipation. Proton pump inhibitors inhibit the final stage of gastric acid production, and it has been found that they may be associated with increased risk of Clostridium difficile diarrhoea. Ulcer protective agents, such as sucralfate, create a barrier between the gastric acid and the gastric mucosa by coating it. They may, however, cause constipation and interfere with the absorption of certain antibacterial agents. In comparison with placebo or no preventive treatment, H2 receptor antagonists, antacids, and sucralfate might be effective in preventing clinically important upper GI bleeding in ICU patients. Hospital-acquired pneumonia was most likely to occur in ICU patients taking either H2 receptor antagonists or sucralfate when compared with patients given placebo or no preventive treatment. Evidence of low certainty suggests that proton pump inhibitors were more effective than H2 receptor antagonists in preventing upper GI bleeding in ICU patients. With proton pump inhibitors, 25 of 1000 people were likely to develop upper GI bleeding, and with H2 receptor antagonists, 73 of 1000 people (95% confidence interval 46 to 115 people) were likely to develop upper GI bleeding. The effect of H2 receptor antagonists versus proton pump inhibitors with respect to the risk for developing hospital-acquired pneumonia was consistent with benefits and harms. Our certainty in the evidence ranged from low to moderate. For effects of different interventions compared with placebo or no prophylaxis, the certainty of evidence was moderate (H2 receptor antagonists) or low (antacids and sucralfate). For effects of H2 receptor antagonists compared with placebo or no preventive treatment on risk of hospital-acquired pneumonia, the certainty of evidence was low. For effects of H2 receptor antagonists compared with proton pump inhibitors on hospital-acquired pneumonia, the certainty of evidence was also low." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: A total of 26 trials involving 2997 people were included, with a follow-up ranging from 3 to 24 months. Studies were conducted in 11 different countries. The mean age of the included participants was 68 years, 68% were male and the mean forced expiratory volume in one second (FEV1)% predicted value was 44.3% (range 28% to 66%). Participants were treated in all types of healthcare settings: primary (n = 8), secondary (n = 12), tertiary care (n = 1), and in both primary and secondary care (n = 5). Overall, the studies were of high to moderate methodological quality. Compared with controls, IDM showed a statistically and clinically significant improvement in disease-specific QoL on all domains of the Chronic Respiratory Questionnaire after 12 months: dyspnea (mean difference (MD) 1.02; 95% confidence interval (CI) 0.67 to 1.36); fatigue (MD 0.82; 95% CI 0.46 to 1.17); emotional (MD 0.61; 95% CI 0.26 to 0.95) and mastery (MD 0.75; 95% CI 0.38 to 1.12). The St. George's Respiratory Questionnaire (SGRQ) for QoL reached the clinically relevant difference of four units only for the impact domain (MD -4.04; 95% CI -5.96 to -2.11, P < 0.0001). IDM showed a significantly improved disease-specific QoL on the activity domain of the SGRQ: MD -2.70 (95% CI -4.84 to -0.55, P = 0.01). There was no significant difference on the symptom domain of the SGRQ: MD -2.39 (95% CI -5.31 to 0.53, P = 0.11). According to the GRADE approach, quality of evidence on the SGRQ was scored as high quality, and on the CRQ as moderate quality evidence. Participants treated with an IDM program had a clinically relevant improvement in six-minute walking distance of 43.86 meters compared with controls after 12 months (95% CI 21.83 to 65.89; P < 0.001, moderate quality). There was a reduction in the number of participants with one or more hospital admissions over three to 12 months from 27 per 100 participants in the control group to 20 (95% CI 15 to 27) per 100 participants in the IDM group (OR 0.68; 95% CI 0.47 to 0.99, P = 0.04; number needed to treat = 15). Hospitalization days were significantly lower in the IDM group compared with controls after 12 months (MD -3.78 days; 95% CI -5.90 to -1.67, P < 0.001). Admissions and hospital days were graded as high quality evidence. No adverse effects were reported in the intervention group. No difference between groups was found on mortality (OR 0.96; 95%CI 0.52 to 1.74). There was insufficient evidence to refute or confirm the long term effectiveness of IDM. In these COPD participants, IDM not only improved disease-specific QoL and exercise capacity, but also reduced hospital admissions and hospital days per person.\nOutput:\n" }, { "from": "agent", "value": "We evaluated 26 studies in 2997 people with COPD. Overall the evidence found was of high to moderate quality. The trials were conducted in 11 different countries. The average age of participants was 68 years, 68% of participants were men and the severity of COPD on average was severe (according to lung function measures). Some of the trials took place in GP clinics and some in hospitals. Overall, the studies were of good to moderate methodological quality. People who participated in an IDM program had better quality of life and improved their exercise tolerance after 12 months. Furthermore, in participants treated with such a program, the number of hospital admissions related to exacerbations decreased and the total number of hospital days was reduced by three days. We found no evidence of an effect on mortality. The results support an IDM program for people with COPD to optimize quality of life and exercise tolerance. This plain language summary is up-to-date as of April 2012." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Seven studies, covering 1624 participants, met the inclusion criteria. All included studies investigated adults and compared dexmedetomidine with traditional sedatives, including propofol, midazolam and lorazepam. Compared with traditional sedatives, dexmedetomidine reduced the geometric mean duration of mechanical ventilation by 22% (95% CI 10% to 33%; four studies, 1120 participants, low quality evidence), and consequently the length of stay in the intensive care unit (ICU) by 14% (95% CI 1% to 24%; five studies, 1223 participants, very low quality evidence). There was no evidence that dexmedetomidine decreased the risk of delirium (RR 0.85; 95% CI 0.63 to 1.14; seven studies, 1624 participants, very low quality evidence) as results were consistent with both no effect and appreciable benefit. Only one study assessed the risk of coma, but lacked methodological reliability (RR 0.69; 95% CI 0.55 to 0.86, very low quality evidence). Of all the adverse events included, the most commonly reported one was bradycardia, and we observed a doubled (111%) increase in the incidence of bradycardia (RR 2.11; 95% CI 1.39 to 3.20; six studies, 1587 participants, very low quality evidence). Our meta-analysis provided no evidence that dexmedetomidine had any impact on mortality (RR 0.99; 95% CI 0.79 to 1.24; six studies, 1584 participants, very low quality evidence). We observed high levels of heterogeneity in risk of delirium (I² = 70%), but due to the limited number of studies we were unable to determine the source of heterogeneity through subgroup analyses or meta-regression. We judged six of the seven studies to be at high risk of bias. In this review, we found no eligible studies for children or for clonidine. Compared with traditional sedatives, long-term sedation using dexmedetomidine in critically ill adults reduced the duration of mechanical ventilation and ICU length of stay. There was no evidence for a beneficial effect on risk of delirium and the heterogeneity was high. The evidence for risk of coma was inadequate. The most common adverse event was bradycardia. No evidence indicated that dexmedetomidine changed mortality. The general quality of evidence ranged from very low to low, due to high risks of bias, serious inconsistency and imprecision, and strongly suspected publication bias. Future studies could pay more attention to children and to using clonidine.\nOutput:\n" }, { "from": "agent", "value": "We searched the databases until October 2014. We included seven randomized controlled trials, with a total of 1624 participants, comparing dexmedetomidine versus traditional sedatives. All the studies required participants to have an anticipated need for sedation of more than 24 hours. The alternative sedatives included propofol, midazolam and lorazepam. We found no eligible studies in children or for clonidine. Of the seven studies, six were funded by the drug manufacturer, and one did not state any conflict of interest. Compared with traditional sedatives, dexmedetomidine reduced the breathing support time by approximately one-fifth, and the length of stay time in ICU by one-seventh. Dexmedetomidine was at least as effective as traditional sedatives for producing sedation and maintaining a light sedation level. There was no clear evidence in support of dexmedetomidine reducing the risk of delirium (a kind of acute confusion state), as results were consistent with both no effect and appreciable benefit. We had insufficient information to draw conclusions about reducing the risk of coma. Dexmedetomidine doubled the incidence of slow heartbeat, which was the most commonly reported adverse event. Our review provides no evidence that dexmedetomidine changed the overall death rate. The general quality of evidence ranged from very low to low, as most of the studies were at high risk of bias, serious inconsistency and imprecision, or strongly suspected publication bias." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 17 randomised trials (3149 participants) conducted in nine different countries. Seven studies (1325 women) recruited exclusively women undergoing elective CS and five studies (833 women) only included women having a primary CS. Ten studies (1731 women) used conventional feeding protocols (nil by mouth until the return of intestinal function). The gum-chewing regimen varied among studies, in relation to its initiation (immediately after CS, up to 12 hours later), duration of each session (from 15 to 60 minutes) and number of sessions per day (three to more than six). All the studies were classified as having a high risk of bias due to the nature of the intervention, women could not be blinded and most of the outcomes were self-reported. Primary outcomes of this review: for the women that chewed gum, the time to passage of first flatus was seven hours shorter than those women in the 'usual care' control group (MD -7.09 hours, 95% CI -9.27 to -4.91 hours; 2399 women; 13 studies; random-effects Tau² = 14.63, I² = 95%, very low-quality evidence). This effect was consistent in all subgroup analyses (primary and repeat CS, time spent chewing gum per day, early and conventional feeding protocols, elective and non-elective CS and time after CS when gum-chewing was initiated). The rate of ileus was on average over 60% lower in the chewing-gum group compared to the control (RR 0.39, 95% CI 0.19 to 0.80; 1139 participants; four studies; I² = 39%, low-quality evidence). Tolerance to gum-chewing appeared to be high. Three women in one study complained about the chewing gum (but no further information was provided) and none of the studies reported adverse effects (eight studies, 925 women, low-quality evidence). Secondary outcomes of this review: the time to passage of faeces occurred on average nine hours earlier in the intervention group (MD -9.22 hours, 95% CI -11.49 to -6.95 hours; 2016 participants; 11 studies; random-effects Tau² = 12.53, I² = 93%, very low-quality evidence). The average duration of hospital stay was shorter in the intervention compared to the control group (MD -0.36 days, 95% CI -0.53 to -0.18 days; 1489 participants; seven studies; random-effects Tau² = 0.04, I² = 92%). The first intestinal sounds were heard earlier in the intervention than in the control group (MD -4.56 hours, 95% CI -6.18 to -2.93 hours; 1729 participants; nine studies; random-effects Tau² = 5.41, I² = 96%). None of the studies assessed women's satisfaction in relation to having to chew gum. The need for analgesia or antiemetic agents did not differ between the intervention and control groups (average RR 0.50, 95% CI 0.12 to 2.13; 726 participants; three studies; random-effects Tau² = 0.79, I² = 69%). This review found 17 randomised controlled trials (involving 3149 women). We downgraded the quality of the evidence for time to first passage of flatus and of faeces and for adverse effects/intolerance to gum chewing because of the high risk of bias of the studies (due to lack of blinding and self-report). For time to first flatus and faeces, we downgraded the quality of the evidence further because of the high heterogeneity in these meta-analyses and the potential for publication bias based on the visual inspection of the funnel plots. The quality of the evidence for adverse effects/tolerance to gum chewing and for ileus was downgraded because of the small number of events. The quality of the evidence for ileus was further downgraded due to the unclear risk of bias for the assessors evaluating this outcome. The available evidence suggests that gum chewing in the immediate postoperative period after a CS is a well tolerated intervention that enhances early recovery of bowel function. However the overall quality of the evidence is very low to low. Further research is necessary to establish the optimal regimen of gum-chewing (initiation, number and duration of sessions per day) to enhance bowel function recovery and to assess potential adverse effects of and women's satisfaction with this intervention. New studies also need to assess the compliance of the participants to the recommended gum-chewing instructions. Future large, well designed and conducted studies, with better methodological and reporting quality, will help to inform future updates of this review and enhance the body of evidence for this intervention.\nOutput:\n" }, { "from": "agent", "value": "We included randomised controlled studies published up to June 2016. We found 17 studies, with 3149 women who had just delivered by CS. In these studies, a group of women chewed gum and a second group did not, receiving usual care. The studies were conducted in nine countries (mostly low- to middle-income countries) and were different in many aspects. For instance, some studies included only women having their first baby and others included women with a previous CS; some studies included only elective (pre-scheduled) CS and others also included emergency CS. The way that gum was given also differed in the studies; in some the women started chewing gum right after the CS and in others they waited for up to 12 hours. Also, the women could not be blinded to receiving the gum. The combination of the results (in a meta-analysis) of these studies showed that the women who chewed gum after a CS had an earlier return of their bowel function. On average, they passed gas seven hours earlier (13 studies, 2399 women). This effect was consistent for first versus repeat CS, time spent chewing gum per day, early feeding versus nothing by mouth until the return of intestinal function, elective versus non-elective or emergency CS, and length of time after CS when gum-chewing was initiated. The quality of the evidence for this outcome was very low. The women chewing gum were at least half as likely to have 'ileus' (a combination of symptoms such as bloating, cramping, nausea, vomiting and inability to defecate) than the women who did not chew gum (four studies, 1139 women, low-quality evidence). Gum chewing reduced the time to first defecation to about nine hours earlier (11 studies, 2016 women, very low-quality evidence) and the time to hospital discharge by some eight hours (seven studies, 1489 women). Only three out of 925 women complained about having to chew gum and there were no reports of adverse effects associated with gum-chewing (eight studies, 925 women, low-quality evidence). None of the studies assessed women's satisfaction in relation to chewing gum. The overall quality of the evidence was low to very low, mostly due to lack of blinding of the participants (the women knew they were chewing gum) and heterogeneity between the studies. The available evidence suggests that gum-chewing in the first 24 hours after a CS is a well-tolerated simple, low-cost, safe and easy intervention that enhances early recovery of bowel function, improves maternal comfort and potentially reduces hospital costs. Further research is necessary to establish the optimal regimen of gum-chewing (when to start, number and duration of sessions per day) to enhance bowel function recovery and to assess potential adverse effects and women's satisfaction with this intervention." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The findings of this review are based on a single trial involving 425 women with gestational diabetes. The trial compared induction of labour with expectant management (waiting for the spontaneous onset of labour in the absence of any maternal or fetal issues that may necessitate birth) in pregnant women with gestational diabetes at term. We assessed the overall risk of bias as being low for most domains, apart from performance, detection and attrition bias (for outcome perineum intact), which we assessed as being at high risk. It was an open-label trial, and women and healthcare professionals were not blinded. There were no clear differences between women randomised to induction of labour and women randomised to expectant management for maternal mortality or serious maternal morbidity (risk ratio (RR) 1.48, 95% confidence interval (CI) 0.25 to 8.76, one trial, 425 women); caesarean section (RR 1.06, 95% CI 0.64 to 1.77, one trial, 425 women); or instrumental vaginal birth (RR 0.81, 95% CI 0.45 to 1.46, one trial, 425 women). For the primary outcome of maternal mortality or serious maternal morbidity, there were no deaths in either group and serious maternal morbidity related to admissions to intensive care unit. The quality of the evidence contributing to these outcomes was assessed as very low, mainly due to the study having high risk of bias for some domains and because of the imprecision of effect estimates. In relation to primary neonatal outcomes, there were no perinatal deaths in either group. The quality of evidence for this outcome was judged as very low, mainly due to high risk of bias and imprecision of effect estimates. There were no clear differences in infant outcomes between women randomised to induction of labour and women randomised to expectant management: shoulder dystocia (RR 2.96, 95% CI 0.31 to 28.21, one trial, 425 infants, very low-quality evidence); large-for-gestational age (RR 0.53, 95% CI 0.28 to 1.02, one trial, 425 infants, low-quality evidence). There were no clear differences between women randomised to induction of labour and women randomised to expectant management for postpartum haemorrhage (RR 1.17, 95% CI 0.53 to 2.54, one trial, 425 women); admission to intensive care unit (RR 1.48, 95% CI 0.25 to 8.76, one trial, 425 women); and intact perineum (RR 1.02, 95% CI 0.73 to 1.43, one trial, 425 women). No infant experienced a birth trauma, therefore, we could not draw conclusions about the effect of the intervention on the outcomes of brachial plexus injury and bone fracture at birth. Infants of women in the induction-of-labour group had higher incidences of neonatal hyperbilirubinaemia (jaundice) when compared to infants of women in the expectant-management group (RR 2.46, 95% CI 1.11 to 5.46, one trial, 425 women). We found no data on the following prespecified outcomes of this review: postnatal depression, maternal satisfaction, length of postnatal stay (mother), acidaemia, intracranial haemorrhage, hypoxia ischaemic encephalopathy, small-for-gestational age, length of postnatal stay (baby) and cost. The authors of this trial acknowledge that it is underpowered for their primary outcome of caesarean section. The authors of the trial and of this review note that the CIs demonstrate a wide range, therefore making it inappropriate to draw definite conclusions. There is limited evidence to inform implications for practice. The available data are not of high quality and lack power to detect possible important differences in either benefit or harm. There is an urgent need for high-quality trials evaluating the effectiveness of planned birth at or near term gestation for women with gestational diabetes compared with an expectant approach.\nOutput:\n" }, { "from": "agent", "value": "Our search identified one trial involving 425 women and their babies. In this trial, 214 women had an induction of their labour at term, the other 211 women waited for a spontaneous onset of their labour. The findings of this trial highlighted no clear difference between the babies of women in either group in relation to the number of large babies, baby's shoulder getting stuck during birth or babies with breathing problems, low blood sugar and admission to a neonatal intensive care unit. No baby in the trial experienced birth trauma. In the group of women whose labour was induced, there were more incidences of jaundice in the babies. There was no clear difference between women in either group in relation to serious health problems for women, caesarean section, instrumental vaginal birth, postpartum haemorrhage, admission to an intensive care unit and intact perineum. There were no reports in either group of maternal deaths. It should be noted that most of the evidence was found to be of very low quality. The following outcomes were not reported: postnatal depression, maternal satisfaction, length of postnatal stay (mother), babies with high blood acid, bleeding in the baby's brain, other brain problems for the babies, babies small-for-gestational age and length of baby's postnatal stay. There is insufficient evidence to clearly identify if there are differences in health outcomes for women with gestational diabetes and their babies when elective birth is undertaken compared to waiting for labour to start spontaneously or until 41 weeks' gestation if all is well. More research is needed to answer this question." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Twelve studies were identified in the searches and seven of these were eligible for inclusion in the review. Five studies, involving 260 participants, provided data for analysis. One study showed that cognitive behaviour therapy significantly reduced the affective component of pain (feelings about pain), mean difference -0.99 (95% confidence interval -1.62 to -0.36), but not the sensory component (pain intensity), mean difference 0.00 (95% confidence interval -9.39 to 9.39). One study of family psycho-education was not associated with a reduction in depression. Another study evaluating cognitive behavioural therapy had inconclusive results for the assessment of coping strategies, and showed no difference between groups assessed on health service utilisation. In addition, family home-based cognitive behavioural therapy did not show any difference compared to disease education. One study of patient education on health beliefs showed a significant improvement in attitudes towards health workers, mean difference -4.39 (95% CI -6.45 to -2.33) and medication, mean difference -1.74 (95% CI -2.98 to -0.50). Nonetheless, these results may not apply across all ages, severity of sickle cell disease, types of pain (acute or chronic), or setting. Evidence for the efficacy of psychological therapies in sickle cell disease is currently limited. This systematic review has clearly identified the need for well-designed, adequately-powered, multicentre randomised controlled trials assessing the effectiveness of specific interventions in sickle cell disease.\nOutput:\n" }, { "from": "agent", "value": "We searched for randomised or quasi-randomised controlled trials which compared psychological treatments to each other or to no treatment in sickle cell disease. We included seven studies in the review, of which five, with 260 people, had data we could enter into the review. One study showed that cognitive behaviour therapy reduced the affective part of pain (feelings about pain), but not the sensory part (pain intensity). Another study of this therapy had inconclusive results for coping strategies and showed no difference on how different groups used the health service. A study using cognitive behavioural therapy with teenagers and their families at home did not show any difference when compared with education about sickle cell disease. One education study did not show a reduction in depression. Furthermore, one study in patient education helped improve attitudes to healthcare workers and medication use in adolescents and young adults. The authors believe that some patient education seems relevant for children, adolescents and young adults, while methods to improve the ability to cope in both children and adults are important. Nonetheless, these results may not apply to across all ages, clinical severity, types of pain (acute or chronic) that people with sickle cell disease have, or which country they live in. More research needs to be done in this area." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified eight RCTs involving 805 participants. Two trials comparing COCP with placebo were considered to be moderate quality and the remaining studies were low to very low quality, mainly because of serious risk of bias from lack of blinding and concerns over precision. COCP versus placebo COCP, with a step-down oestrogen and step-up progestogen regimen, improved response to treatment (return to menstrual 'normality') (OR 22.12, 95% CI 4.40 to 111.12; 2 trials; 363 participants; I2 = 50%; moderate-quality evidence), and lowered MBL (OR 5.15, 95% CI 3.16 to 8.40; 2 trials; 339 participants; I2 = 0%; moderate-quality evidence) when compared to placebo. The results suggested that, if the chance of 'successful' treatment was 3% in women taking placebo, then COCP increased this chance from 12% to 77% in women with unacceptable HMB. Minor adverse events, in particular breast pain, were more common with COCP. No study in this comparison reported semi-objectively assessed MBL or participant satisfaction with treatment. COCP versus other medical treatments Non-steroidal anti-inflammatory drugs (NSAIDs) There was insufficient evidence to determine whether the COCP reduced MBL when compared to NSAIDs (mefenamic acid and naproxen). No study in this comparison reported semi-objectively assessed MBL, subjectively assessed MBL, participant satisfaction with treatment or adverse events. Levonorgestrel-releasing intrauterine system (LNG IUS) The LNG IUS was more effective than COCP in reducing MBL (OR 0.21, 95% CI 0.09 to 0.48; 2 trials; 151 participants; I2 = 0%; low-quality evidence) but it was not clear whether satisfaction with treatment or adverse effects varied according to which treatment was used. No study in this comparison reported semi-objectively assessed MBL or subjectively assessed MBL. Contraceptive vaginal ring (CVR) versus other medical treatments COCP COCP was compared with CVR in two trials. There were discrepancies between some of the findings and there was no evidence of a benefit for one treatment compared to the other for response to treatment, MBL or participant satisfaction with treatment. There was a greater likelihood of nausea with COCP. No study in this comparison reported objectively assessed MBL or subjectively assessed MBL. Progestogens CVR was compared to long course progestogens in one trial. It is possible that CVR increased the odds of satisfaction; but we are uncertain whether CVR improved MBL. The evidence was based on small numbers of participants and was very low quality, so definitive conclusions could not be reached. No study in this comparison reported objectively assessed MBL, subjectively assessed MBL, or adverse events. Moderate-quality evidence suggests that the combined oral contraceptive pill over six months reduces HMB in women with unacceptable HMB from 12% to 77% (compared to 3% in women taking placebo). When compared with other medical options for HMB, COCP was less effective than the LNG IUS. Limited evidence suggested that COCP and CVR had similar effects. There was insufficient evidence to determine comparative efficacy of combined hormonal contraceptives with NSAIDs, or long course progestogens.\nOutput:\n" }, { "from": "agent", "value": "Eight studies, which included 805 women, were identified that compared combined hormonal contraceptives (mostly, the combined contraceptive pill) with either no treatment, placebo or other medical treatments. The studies assessed the effects of interventions on menstrual bleeding, satisfaction, quality of life, adverse events, and haemoglobin levels (protein in red blood cells that carries oxygen throughout the body). The evidence is current to September 2018. Two studies found that a type of COCP, containing estradiol valerate and dienogest, reduced HMB and improved quality of life and haemoglobin levels when compared with placebo, but at the expense of some minor side effects. There was insufficient evidence to compare contraceptives with other treatments, such as nonsteroidal anti-inflammatories or progestogens. Two studies found that the levonorgestrel-releasing intrauterine system (LNG IUS) was more effective than the COCP at reducing menstrual blood loss. Two trials found no evidence of different effects between the oral contraceptive pill or the hormonal vaginal ring. We found no studies that assessed the effects of the combined hormonal patch (transdermal patch). The quality of the evidence that compared the oral contraceptive pill with placebo was moderate, but the evidence for the other comparisons was either low or very low in quality. The LNG IUS is more effective than the COCP at reducing menstrual bleeding but evidence was insufficient for the other treatment comparisons. This means that, although it is likely that combined hormonal contraceptives can reduce HMB, we cannot be absolutely certain how they compare with other medical treatments for reducing HMB (although LNG IUS appears to be more effective)." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included eight studies, with a total of 1308 women randomised. The pooled data from these studies show a statistically significant and clinically meaningful reduction in non-cephalic presentation at birth (average risk ratio (RR) 0.42, 95% confidence interval (CI) 0.29 to 0.61, eight trials, 1305 women); vaginal cephalic birth not achieved (average RR 0.46, 95% CI 0.33 to 0.62, seven trials, 1253 women, evidence graded very low); and caesarean section (average RR 0.57, 95% CI 0.40 to 0.82, eight trials, 1305 women, evidence graded very low) when ECV was attempted in comparison to no ECV attempted. There were no significant differences in the incidence of Apgar score ratings below seven at one minute (average RR 0.67, 95% CI 0.32 to 1.37, three trials, 168 infants) or five minutes (RR 0.63, 95% CI 0.29 to 1.36, five trials, 428 infants, evidence graded very low), low umbilical vein pH levels (RR 0.65, 95% CI 0.17 to 2.44, one trial, 52 infants, evidence graded very low), neonatal admission (RR 0.80, 95% CI 0.48 to 1.34, four trials, 368 infants, evidence graded very low), perinatal death (RR 0.39, 95% CI 0.09 to 1.64, eight trials, 1305 infants, evidence graded low), nor time from enrolment to delivery (mean difference -0.25 days, 95% CI -2.81 to 2.31, two trials, 256 women). All of the trials included in this review had design limitations, and the level of evidence was graded low or very low. No studies attempted to blind the intervention, and the process of random allocation was suboptimal in several studies. Three of the eight trials had serious design limitations, however excluding these studies in a sensitivity analysis for outcomes with substantial heterogeneity did not alter the results. Attempting cephalic version at term reduces the chance of non-cephalic presentation at birth, vaginal cephalic birth not achieved and caesarean section. There is not enough evidence from randomised trials to assess complications of ECV at term. Large observational studies suggest that complications are rare. A visual summary of some of the results from this review can be found here.\nOutput:\n" }, { "from": "agent", "value": "We found 8 studies involving 1308 women. (We included studies up to 28 February 2015.) All the studies were randomised and involved women with low-risk pregnancies. Using ECV around 36 weeks or more increased the chance that babies were born head-first and reduced the risk of having a caesarean section. There were no clear differences in other outcomes such as the risk of babies dying. The quality of the studies and therefore the strength of the evidence was varied. If an unborn baby is lying bottom-down, turning it by ECV just before birth can reduce some of the problems this position can cause. These studies are too small to show if ECV is safe to use in women with low-risk pregnancies, however other types of studies suggest that it is safe. We also do not know if it should be used in high-risk cases, such as mothers who have already had a caesarean section, or who are expecting twins. A visual summary of some of the results from this review can be found here." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: This review included 12 multicentre RCTs randomly assigning 9547 participants with stable COPD. All the studies were industry-sponsored and had similar inclusion criteria with relatively good methodological quality. All but one study included in the meta-analysis were double-blind and scored low risk of bias. The study duration ranged from four weeks to 52 weeks. Participants were more often males, mainly Caucasians, mean age ranging from 61.7 to 65.6 years, and with a smoking history of 10 or more pack years. They had moderate to severe symptoms at randomisation; the mean post-bronchodilator forced expiratory volume in one second (FEV1) was between 46% and 57.6% of the predicted normal value, and the mean St George's Respiratory Questionnaire score (SGRQ) ranged from 45.1 to 50.4 when reported. There was no difference between aclidinium and placebo in all-cause mortality (low quality) and number of patients with exacerbations requiring a short course of oral steroids or antibiotics, or both (moderate quality). Aclidinium improved quality of life by lowering the SGRQ total score with a mean difference of -2.34 (95% CI -3.18 to -1.51; I2 = 48%, 7 trials, 4442 participants) when compared to placebo. More patients on aclidinium achieved a clinically meaningful improvement of at least four units decrease in SGRQ total score (OR 1.49; 95% CI 1.31 to 1.70; I2 = 34%; number needed to treat (NNT) = 10, 95% CI 8 to 15, high quality evidence) over 12 to 52 weeks than on placebo. Aclidinium also resulted in a significantly greater improvement in pre-dose FEV1 than placebo with a mean difference of 0.09 L (95% CI 0.08 to 0.10; I2 = 39%, 9 trials, 4963 participants). No trials assessed functional capacity. Aclidinium reduced the number of patients with exacerbations requiring hospitalisation by 4 to 20 fewer per 1000 over 4 to 52 weeks (OR 0.64; 95% CI 0.46 to 0.88; I2 = 0%, 10 trials, 5624 people; NNT = 77, 95% CI 51 to 233, high quality evidence) compared to placebo. There was no difference in non-fatal serious adverse events (moderate quality evidence) between aclidinium and placebo. Compared to tiotropium, aclidinium did not demonstrate significant differences for exacerbations requiring oral steroids or antibiotics, or both, exacerbation-related hospitalisations and non-fatal serious adverse events (very low quality evidence). Inadequate data prevented the comparison of aclidinium to formoterol or other LABAs. Aclidinium is associated with improved quality of life and reduced hospitalisations due to severe exacerbations in patients with moderate to severe stable COPD compared to placebo. Overall, aclidinium did not significantly reduce mortality, serious adverse events or exacerbations requiring oral steroids or antibiotics, or both. Currently, the available data are insufficient and of very low quality in comparisons of the efficacy of aclidinium versus tiotropium. The efficacy of aclidinium versus LABAs cannot be assessed due to inaccurate data. Thus additional trials are recommended to assess the efficacy and safety of aclidinium compared to other LAMAs or LABAs.\nOutput:\n" }, { "from": "agent", "value": "The evidence was current to 7 April 2014. We included 12 studies involving 9547 COPD patients over a period of four to 52 weeks. These studies were sponsored by drug companies and were well designed. Both patients and the people doing the research did not know which treatment the patients were getting; although in one study one treatment was known to both parties. More men than women took part, and they were mostly Caucasians. They were in their 60s and had smoked a lot in their lives. These people had moderate to severe symptoms when they started treatment. Aclidinium did not reduce the number of people with flare-ups that need additional drugs. There was little or no difference in deaths or serious side effects between aclidinium and a dummy inhaler. Aclidinium inhalers improved quality of life more than the dummy inhalers. People who took aclidinium had fewer hospital admissions due to serious flare-ups. Based on our results, among 1000 COPD patients using a dummy inhaler over four weeks to one year 37 would have severe flare-ups needing hospital admission. Only 17 to 33 patients out of 1000 would require hospital admission if they were using aclidinium inhalers. We also set out to compare this new medication with tiotropium, which is already used to treat COPD. There were only two studies for this comparison thus we could not be sure how aclidinium compared to tiotropium. We also could not compare aclidinium with another well known inhaler that contains the drug formoterol because of unreliable data. For the comparison of aclidinium inhalers and dummy inhalers, we are confident that there are benefits in terms of the number of hospitalisations and patients' quality of life; we are less certain about the numbers of flare-ups needing additional drugs and serious side effects. We do not have enough information to assess any effect on the number of deaths. We did not have enough information to reliably compare aclidinium with tiotropium or formoterol." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: This review included 10 studies with a total number of 686 participants featuring in 20 different outcomes of interest. Overall, there was significant clinical improvement in clinical global state at medium term amongst people receiving trifluoperazine (3 RCTs, n = 417, RR 4.61, CI 1.54 to 13.84, low quality evidence) and significantly fewer people receiving trifluoperazine left the studies early due to relapse or worsening at medium term (2 RCTs, n = 381, RR 0.34, CI 0.23 to 0.49, low quality evidence). However, results were equivocal for leaving the study early at medium term for any reason (2 RCTs, n = 391, RR 0.80, CI 0.17 to 3.81, very low quality evidence) and due to severe adverse effects (2 RCTs, n = 391, RR 1.54, CI 0.56 to 4.24, very low quality evidence). Equivocal data were also found for intensified symptoms at medium term (2 RCTs, n = 80, RR 1.05, CI 0.54 to 2.05, very low quality evidence) and rates of agitation or distress again at medium term (1 RCT, n = 52, RR 2.00, CI 0.19 to 20.72, very low quality evidence). Comparison between low and high-dose trifluoperazine with placebo from a single study provided equivocal evidence of effects. For economic outcomes, we valued outcomes in GBP terms and presented them in additional tables; there was an estimated saving of £3488.3 in favour of trifluoperazine. However, numerous assumptions were made and these savings need to be interpreted in light of those assumptions. Our results agree with existing evidence that compared to placebo, trifluoperazine is an effective antipsychotic for people with schizophrenia. Furthermore, our review provides supportive evidence that trifluoperazine increases the risk of extrapyramidal adverse effects. Although the effect sizes against placebo are similar to those observed with other agents, they are based on data from many small, pre-CONSORT trials with generally either a low or very low GRADE evidence that has limited implication for clinical practice. Large, independent trials are needed that adhere to the CONSORT statement to compare trifluoperazine with placebo used in the treatment of schizophrenia and schizophrenia-like illnesses.\nOutput:\n" }, { "from": "agent", "value": "This review is based on a search for trials carried out in July 2012, and includes 10 studies with 686 participants. The aim was to determine the effects of trifluoperazine for schizophrenia when compared with placebo (a ‘dummy’ treatment). As expected, people given trifluoperazine showed a significant improvement compared to placebo in both the short and medium term, reinforcing the use of this well-established typical antipsychotic for people with schizophrenia. However, trifluoperazine can cause side effects such as confusion, agitation, having a dry mouth and blurred vision, but causes less sedation and dizzy spells, so is generally well tolerated by people with schizophrenia. The authors of the review conclude that trifluoperazine has similar effectiveness to other common antipsychotic drugs, although it may cause more side effects. Evidence used in the review was also graded as low or very low quality. In the light of this, use of other antipsychotic drugs should be considered before starting on trifluoperazine. Most of the included studies were conducted roughly 40 years ago so new, large, comprehensive and independent research trials are needed. This plain language summary has been written by a consumer Ben Gray from RETHINK." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: 72 RCTs met our inclusion criteria. The methodological quality of included studies varied. An organized system of regular review allied to vigorous antihypertensive drug therapy was shown to reduce systolic blood pressure (weighted mean difference (WMD) -8.0 mmHg, 95% CI: -8.8 to -7.2 mmHg) and diastolic blood pressure (WMD -4.3 mmHg, 95% CI: -4.7 to -3.9 mmHg) for three strata of entry blood pressure, and all-cause mortality at five years follow-up (6.4% versus 7.8%, difference 1.4%) in a single large RCT- the Hypertension Detection and Follow-Up study. Other interventions had variable effects. Self-monitoring was associated with moderate net reduction in systolic blood pressure (WMD -2.5 mmHg, 95% CI: -3.7 to -1.3 mmHg) and diastolic blood pressure (WMD -1.8 mmHg, 95% CI: -2.4 to -1.2 mmHg). RCTs of educational interventions directed at patients or health professionals were heterogeneous but appeared unlikely to be associated with large net reductions in blood pressure by themselves. Nurse or pharmacist led care may be a promising way forward, with the majority of RCTs being associated with improved blood pressure control and mean SBP and DBP but these interventions require further evaluation. Appointment reminder systems also require further evaluation due to heterogeneity and small trial numbers, but the majority of trials increased the proportion of individuals who attended for follow-up (odds ratio 0.41, 95% CI 0.32 to 0.51) and in two small trials also led to improved blood pressure control, odds ratio favouring intervention 0.54 (95% CI 0.41 to 0.73). Family practices and community-based clinics need to have an organized system of regular follow-up and review of their hypertensive patients. Antihypertensive drug therapy should be implemented by means of a vigorous stepped care approach when patients do not reach target blood pressure levels. Self-monitoring and appointment reminders may be useful adjuncts to the above strategies to improve blood pressure control but require further evaluation.\nOutput:\n" }, { "from": "agent", "value": "Seventy two randomised controlled trials met our inclusion criteria. The range of interventions used included (1) self-monitoring, (2) educational interventions directed to the patient, (3) educational interventions directed to the health professional, (4) health professional (nurse or pharmacist) led care, (5) organizational interventions that aimed to improve the delivery of care, (6) appointment reminder systems. The trials showed a wide variety of methodological quality, part of which may be attributed to poor reporting. An organized system of regular review allied to vigorous antihypertensive drug therapy was shown to reduce blood pressure and all-cause mortality in a single large RCT- the Hypertension Detection and Follow-Up study. Other interventions had variable effects. Weighted data analysis showed that self-monitoring was associated with moderate net reductions in systolic blood pressure (weighted mean difference -2.5 mmHg, 95% CI: -3.7 to -1.3 mmHg) and diastolic blood pressure (weighted mean difference -1.8 mmHg, 95% CI: -2.4 to -1.2 mmHg). Trials of educational interventions directed at patients or health professionals were heterogeneous but appeared unlikely to be associated with large net reductions in blood pressure by themselves. Nurse or pharmacist led care may be a promising way of improving control in patients with hypertension, with the majority of RCTs being associated with improved blood pressure control, improved systolic blood pressure and more modestly improved diastolic blood pressure, but these interventions require further evaluation. Appointment reminder systems increased the proportion of individuals who attended for follow-up (absolute difference 16%, but this pooled result should be treated with caution because of the heterogeneous results from individual RCTs) and in two small trials also led to improved blood pressure control, odds ratio favouring intervention 0.54 (95% CI 0.41 to 0.73). We conclude that an organized system of registration, recall and regular review allied to a vigorous stepped care approach to antihypertensive drug treatment appears the most likely way to improve the control of high blood pressure. Health professional (nurse or pharmacist) led care and appointment reminder systems requires further evaluation. Education alone, either to health professionals or patients, does not appear to be associated with large net reductions in blood pressure." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Two trials (one RCT and one CCT) (total 80 participants) met the review criteria. Both trials scored poorly on the methodological quality assessment. There was 'insufficient evidence' for VR programs for (a)‘competitive employment’, in altering rates of job retention, changes in employment, improvement in rates of re-entry into the labour force; (b) for altering ‘work ability' by improving participants’ confidence in the accommodation request process, or employability maturity or job seeking activity. No evidence could be assimilated for changes in proportions of persons in supported employment or on disability pensions, nor for cost-effectiveness. There was inconclusive evidence to support VR for pwMS. However, the review highlights some of the challenges in providing VR for pwMS. Clinicians need to be aware of vocational issues, and to understand and manage barriers for maintaining employment. Proactive and timely VR programs should incorporate practical solutions to deal with work disability, workplace accommodation and educate employers, and the wider community. Liaison with policy makers is imperative for government initiatives that encourage work focused VR programs. Future research in VR should focus on improving methodological and scientific rigour of clinical trials; on the development of appropriate and valid outcome measures; and on cost effectiveness of VR programs.\nOutput:\n" }, { "from": "agent", "value": "Among the pertinent medical literature, only two studies, comprising a total of 80 participants, met the criteria of the methodological quality necessary for their inclusion in this review, although the subsequent quality assessment revealed they scored poorly. Furthermore, the two studies were carried out in USA, with limited generalisability in other geographical/cultural settings. The whole data neither supports nor refutes the effectiveness or cost-effectiveness of VR programs for persons with MS. The data also identified critical points worth of future attention: more awareness of vocational issues by professionals; putting in place practical solutions such as a proper workplace accommodations and employers' education; asking for political/governmental initiatives to really support disabled employees; taking into account that supported withdrawal from work at the proper time is as important as supported re-entering to work. Further research are necessary also to improve the methodology of the researches and to identify those individuals most likely to benefit." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We identified 18 trials, which included 6407 participants. We found 12 of these studies in the literature search for this update. Eight studies included a total of 2728 participants with painful diabetic neuropathy and six studies involved 2249 participants with fibromyalgia. Three studies included participants with depression and painful physical symptoms and one included participants with central neuropathic pain. Studies were mostly at low risk of bias, although significant drop outs, imputation methods and almost every study being performed or sponsored by the drug manufacturer add to the risk of bias in some domains. Duloxetine at 60 mg daily is effective in treating painful diabetic peripheral neuropathy in the short term, with a risk ratio (RR) for ≥ 50% pain reduction at 12 weeks of 1.73 (95% CI 1.44 to 2.08). The related NNTB is 5 (95% CI 4 to 7). Duloxetine at 60 mg daily is also effective for fibromyalgia over 12 weeks (RR for ≥ 50% reduction in pain 1.57, 95% CI 1.20 to 2.06; NNTB 8, 95% CI 4 to 21) and over 28 weeks (RR 1.58, 95% CI 1.10 to 2.27) as well as for painful physical symptoms in depression (RR 1.37, 95% CI 1.19 to 1.59; NNTB 8, 95% CI 5 to 14). There was no effect on central neuropathic pain in a single, small, high quality trial. In all conditions, adverse events were common in both treatment and placebo arms but more common in the treatment arm, with a dose-dependent effect. Most adverse effects were minor, but 12.6% of participants stopped the drug due to adverse effects. Serious adverse events were rare. There is adequate amounts of moderate quality evidence from eight studies performed by the manufacturers of duloxetine that doses of 60 mg and 120 mg daily are efficacious for treating pain in diabetic peripheral neuropathy but lower daily doses are not. Further trials are not required. In fibromyalgia, there is lower quality evidence that duloxetine is effective at similar doses to those used in diabetic peripheral neuropathy and with a similar magnitude of effect. The effect in fibromyalgia may be achieved through a greater improvement in mental symptoms than in somatic physical pain. There is low to moderate quality evidence that pain relief is also achieved in pain associated with depressive symptoms, but the NNTB of 8 in fibromyalgia and depression is not an indication of substantial efficacy. More trials (preferably independent investigator led studies) in these indications are required to reach an optimal information size to make convincing determinations of efficacy. Minor side effects are common and more common with duloxetine 60 mg and particularly with 120 mg daily, than 20 mg daily, but serious side effects are rare. Improved direct comparisons of duloxetine with other antidepressants and with other drugs, such as pregabalin, that have already been shown to be efficacious in neuropathic pain would be appropriate. Unbiased economic comparisons would further help decision making, but no high quality study includes economic data.\nOutput:\n" }, { "from": "agent", "value": "We looked at all the published scientific literature and found 18 trials, involving a total of 6407 participants, that were of sufficient quality to include in this review. Eight trials tested the effect of duloxetine on painful diabetic neuropathy and six on the pain of fibromyalgia. Three trials treated painful physical symptoms associated with depression and one small study investigated duloxetine for the pain from strokes or diseases of the spinal cord (central pain). The usual dose of duloxetine is 60 mg. At this dose, there was moderate quality evidence that duloxetine reduced pain in both painful diabetic peripheral neuropathy and fibromyalgia. In diabetic peripheral neuropathic pain, a 50% or better improvement with duloxetine 60 mg per day was just over one and a half times more likely than with placebo. Another way of saying this is that five people with painful diabetic peripheral neuropathy had to receive duloxetine to achieve a 50% or better response in one person. The effect on fibromyalgia was similar but the number needed to treat for one person to improve by 50% or more was eight. On the basis of a single study it is not possible to determine if a dose of 20 mg is effective, and 120 mg was no more effective than 60 mg. We calculated that for diabetic neuropathy there have been enough trials to draw these conclusions and no more trials are needed. In fibromyalgia and the painful symptoms associated with depression, more trials are required to make convincing statements about the effectiveness of duloxetine. Most people taking duloxetine will have at least one side effect. These are mostly minor and the most common are feeling sick, being too awake or too sleepy, headache, dry mouth, constipation or dizziness. About one in six people stop duloxetine because of side effects. Serious problems caused by duloxetine are very rare. Although duloxetine is beneficial in the treatment of neuropathic pain and fibromyalgia there is little evidence from trials comparing duloxetine to other antidepressant drugs as to which is better. We have concluded that duloxetine is useful for treating pain caused by diabetic neuropathy and probably fibromyalgia. The information in this review is up to date to November 2013, the most recent search of the literature." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Twelve included studies in 11 publications (1511 participants), all with chronic neuropathic pain: central post-stroke pain (1), chemotherapy-induced neuropathic pain (1), diabetic neuropathy (4), HIV-related neuropathy (2), mixed neuropathic pain (2), spinal cord injury-related pain (1), and trigeminal neuralgia (1). We did not identify any additional studies. Participants were aged between 26 and 77 years. Study duration was two weeks in one study and at least six weeks in the remainder; eight were of eight-week duration or longer. No study provided first-tier evidence for an efficacy outcome. There was no convincing evidence that lamotrigine is effective in treating neuropathic pain and fibromyalgia at doses of 200 mg to 400 mg daily. Almost 10% of participants taking lamotrigine reported a skin rash. Large, high-quality, long-duration studies reporting clinically useful levels of pain relief for individual participants provided no convincing evidence that lamotrigine is effective in treating neuropathic pain and fibromyalgia at doses of about 200 to 400 mg daily. Given the availability of more effective treatments including antiepileptics and antidepressant medicines, lamotrigine does not have a significant place in therapy based on the available evidence. The adverse effect profile of lamotrigine is also of concern.\nOutput:\n" }, { "from": "agent", "value": "On 26 November 2013 we performed searches to look for clinical trials where lamotrigine was used to treat neuropathic pain or fibromyalgia. We found 12 studies of reasonable quality that tested lamotrigine against placebo for a number of weeks. Almost half of the 1511 people in the studies had painful limbs because of damaged nerves caused by diabetes, and seven different painful neuropathic conditions were examined. No studies looked at fibromyalgia. Lamotrigine did not help the pain, and was no different from placebo except in causing more side effects. Adverse events were more frequent with lamotrigine than placebo, with rash in 1 person in 27." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Of the 1125 records screened for eligibility, four RCTs (N = 201 participants), and one on-going study, met the inclusion criteria. Two classes of antidepressants were investigated in two separate comparisons with placebo: a tricyclic antidepressant (TCA) and selective serotonin reuptake inhibitors (SSRIs). TCA versus placebo Only one RCT (N = 30 participants) provided results for this comparison. Primary outcomes The TCA (nortriptyline) reduced depressive symptoms post-treatment compared to placebo (MD -10.20, 95% CI -16.75 to -3.65; P = 0.007; very low-quality evidence), as measured by the Hamilton Depression Rating Scale (HAM-D). Three participants withdrew from the trial due to adverse events related to the tested antidepressant (dry mouth, sedation, orthostatic hypotension). Secondary outcomes The overall results post-treatment indicated that nortriptyline was not effective in improving the quality of life of individuals with COPD, as measured by the Sickness Impact Profile (MD -2.80, 95% CI -11.02 to 5.42; P = 0.50; very low-quality evidence). The results for the change in dyspnoea for the domains examined (e.g. dyspnoea scores for 'most day-to-day activities') post-treatment showed no improvement in the intervention group (MD 9.80, 95% CI -6.20 to 25.80; P = 0.23; very low-quality evidence). No data were reported for change in FEV1, change in exercise tolerance, change in hospital utilisation, or cost-effectiveness. The TCA study provided short-term results, with the last follow-up data collection at 12 weeks. The quality of the evidence for all the outcomes evaluated was very low due to a small sample size, imprecision, attrition, and selection and reporting bias. SSRIs versus placebo Three RCTs (N = 171 participants) provided results for this comparison. Primary outcomes The pooled results for two studies showed no difference for the change in depressive symptoms post-intervention (SMD 0.75, 95% CI -1.14 to 2.64; 148 participants; 2 studies; P = 0.44; very low-quality evidence). High heterogeneity was observed (I² = 95%), limiting the reliability of these findings. While it was not possible to meta-analyse the total adverse events rates across the studies, it was possible to combine the results for two medication-specific adverse effects: nausea and dizziness. There were no significant post-treatment group differences for nausea (OR 2.32, 95% CI 0.66 to 8.12; 171 participants; 3 studies; P = 0.19; very low-quality evidence) or dizziness (OR 0.61, 95% CI 0.09 to 4.06; 143 participants; 2 studies; P = 0.61; very low-quality evidence). Secondary outcomes The pooled analysis of two trials reporting data for the change in quality of life did not show improvement post-treatment in the intervention group compared to placebo (SMD 1.17, 95% CI -0.80 to 3.15; 148 participants; 2 studies; P = 0.25; very low-quality evidence). There was no difference between groups in change in FEV1 post-treatment (MD 0.01, 95% CI -0.03 to 0.05; 148 participants; 2 studies; P = 0.60; low-quality evidence). However, two trials reported improvement in exercise tolerance in the SSRI group versus the placebo group (MD 13.88, 95% CI 11.73 to 16.03; 148 participants; 2 studies; P < 0.001; very low-quality evidence). The trials included in this comparison did not report data related to the change in dyspnoea, hospital utilisation rates, or cost-effectiveness. There is insufficient evidence to make definitive statements about the efficacy or safety of antidepressants for treating COPD-related depression. New RCTs are needed; with better methodological quality and more accurate reporting of the methods used. Moreover, longer-term follow-up data collection is needed, including outcomes such as adverse events, hospital utilisation and cost-effectiveness.\nOutput:\n" }, { "from": "agent", "value": "This review included experimental studies called randomised controlled trials (studies in which participants are assigned to a treatment group based on a random method) that compared the effectiveness of pharmacological interventions (antidepressants) to placebo (inactive treatment in the same form as the active treatment, e.g. a pill). Study participants were adults diagnosed with COPD and depression. What does the evidence from the review tell us? We have identified only four studies worldwide that were eligible for inclusion in our review. This means limited evidence to support the use of antidepressants for the treatment of depression in patients with COPD. Only one study evaluated a tricyclic antidepressant, nortriptyline, finding that it reduced depressive symptoms when compared to a placebo. Three studies evaluated a newer generation class of antidepressants called selective serotonin reuptake inhibitors (SSRIs), finding no evidence for their effectiveness in improving depressive symptoms. Due to the limited evidence, we are unable to make definitive statements about the effectiveness but also safety of antidepressants when used for COPD-related depression. However, SSRIs may increase exercise capacity in patients with COPD. Given that the current findings were based on only four small studies with evidence rated as of very low quality, it is important to interpret our results with caution. What should happen next? Insufficient evidence prevented us from making clear recommendations for doctors, other healthcare professionals, researchers, or policymakers. More studies with better methodological quality and a larger number of participants are needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Four randomised controlled trials involving 543 women were identified and are included in this review. In the included studies, the active treatment arm was the 20 μg/day levonorgestrel-releasing intrauterine system (LNG-IUS) plus endometrial surveillance; the control arm was endometrial surveillance alone. In tamoxifen users, the LNG-IUS led to a reduction in the incidence of endometrial polyps over both a 12-month period (Peto OR 0.22, 95% CI 0.08 to 0.64, 2 studies, n = 212, I² = 0%) and over a long-term follow-up period (24 to 60 months) (Peto OR 0.22, 95% CI 0.13 to 0.39, 4 studies, n = 417, I² = 0%, moderate quality evidence). Also the LNG-IUS led to a reduction in the incidence of endometrial hyperplasia over a long-term follow-up period (24 to 60 months) (Peto OR 0.13, 95% CI 0.03 to 0.67, four studies, n = 417, I² = 0%, moderate quality evidence). However, it should be noted that the number of events of endometrial hyperplasia was low (n = 6). None of the trials were sufficiently powered to detect whether LNG-IUS leads to significant changes in the incidence of endometrial cancer in tamoxifen users. At 12 months of follow-up abnormal vaginal bleeding or spotting was more common in the LNG-IUS treatment group (Peto OR 7.26, 95% CI 3.37 to 15.66, 3 studies, n = 376, I² = 0%, moderate quality evidence). By 24 months of follow-up, abnormal vaginal bleeding or spotting occurred less frequently compared to 12 months of follow-up in the LNG-IUS treatment group but was still more common than the control group (Peto OR 2.72, 95% CI 1.04 to 7.10, 2 studies, n = 233, I² = 0%, moderate quality evidence). By 60 months of follow-up, no cases of abnormal vaginal bleeding or spotting were reported in either group. The numbers of events for the following outcomes were low: fibroids (n = 13), breast cancer recurrence (n = 18), and breast cancer-related deaths (n = 16). There was no evidence of a difference between the LNG-IUS treatment group and controls for these outcomes. The quality of the evidence was judged as moderate, due to limited sample sizes and low event rates for the outcome comparisons. The LNG-IUS reduces the incidence of benign endometrial polyps and endometrial hyperplasia in women with breast cancer taking tamoxifen. At 12 and 24 months of follow-up, the LNG-IUS increased abnormal vaginal bleeding or spotting among women in the treatment group compared to those in the control. There is no clear evidence from the available randomised controlled trials that the LNG-IUS prevents endometrial cancer in these women. There is no clear evidence from the available randomised controlled trials that the LNG-IUS affects the risk of breast cancer recurrence or breast cancer-related deaths. Larger studies are necessary to assess the effects of the LNG-IUS on the incidence of endometrial cancer, and to determine whether the LNG-IUS might have an impact on the risk of secondary breast cancer events.\nOutput:\n" }, { "from": "agent", "value": "We included four randomised controlled trials involving 543 women. The studies took place in the United Kingdom, Turkey, Egypt and Hong Kong, and the primary outcome in all studies was abnormal changes in the lining of the uterus. Three studies reported on the outcome of fibroids. Three studies reported on abnormal vaginal bleeding or spotting. Two studies reported on the outcomes of breast cancer recurrence, and three studies reported on the outcomes of breast cancer-related death. The evidence is current to October 2015. This review suggests that the LNG-IUS can reduce the risk of endometrial polyps and endometrial hyperplasia over a long-term follow-up period (24 to 60 months) in women taking tamoxifen following breast cancer. At 12 and 24 months of follow-up, more women in the LNG-IUS group experienced abnormal vaginal bleeding or spotting. However by 60 months of follow-up, no abnormal vaginal bleeding or spotting was reported in either group. There were insufficient data to show whether there is any effect on incidence of endometrial cancer (a cancer originating in glandular tissue), fibroids, breast cancer recurrence, or breast cancer-related death. The quality of the evidence was judged as moderate, due to limited sample sizes and low event rates for the outcome comparisons. Larger studies are necessary to assess the effects of the LNG-IUS on the incidence of endometrial cancer, and the impact of the LNG-IUS on the risk of secondary breast cancer events." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: One RCT and nine observational studies were included in the review. These ten studies identified 2,112 episodes of HIV transmission, 1,016 among treated couples and 1,096 among untreated couples. The rate ratio for the single randomised controlled trial was 0.04 [95% CI 0.00, 0.27]. All index partners in this study had CD4 cell counts at baseline of 350-550 cells/µL. Similarly, the summary rate ratio for the nine observational studies was 0.58 [95% CI 0.35, 0.96], with substantial heterogeneity (I2=64%). After excluding two studies with inadequate person-time data, we estimated a summary rate ratio of 0.36 [95% CI 0.17, 0.75] with substantial heterogeneity (I2=62%). We also performed subgroup analyses among the observational studies to see if the effect of ART on prevention of HIV differed by the index partner's CD4 cell count. Among couples in which the infected partner had ≥350 CD4 cells/µL, we estimated a rate ratio of 0.12 [95% CI 0.01, 1.99]. In this subgroup, there were 247 transmissions in untreated couples and 30 in treated couples. ART is a potent intervention for prevention of HIV in discordant couples in which the index partner has ≤550 CD4 cells/µL. A recent multicentre RCT confirms the suspected benefit seen in earlier observational studies and reported in more recent ones. Questions remain about durability of protection, the balance of benefits and adverse events associated with earlier therapy, long-term adherence and transmission of ART-resistant strains to partners. Resource limitations and implementation challenges must also be addressed. Counselling, support, and follow up, as well as mutual disclosure, may have a role in supporting adherence, so programmes should be designed with these components. In addition to ART provision, the operational aspects of delivering such programmes must be considered.\nOutput:\n" }, { "from": "agent", "value": "We found one randomised controlled trial and nine observational studies that examined this question. Overall we found that in couples in which the infected partner was being treated with antiretroviral drugs the uninfected partners had, at worst, more than 40% lower risk of being infected than in couples where the infected partner was not receiving treatment. Since the World Health Organization (WHO) already recommends antiretroviral treatment for all persons with ≤350 CD4 cells/µL, we also examined studies that had studied couples in which the infected partners had CD4 counts higher than this level. We found that there is strong evidence from the randomised controlled trial that in this group HIV was less likely to be transmitted to uninfected partners from treated infected partners than from untreated infected partners." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: This review update includes a total of 12 trials (944) women (type 1 diabetes: 660 women; type 2 diabetes: 113 women; type 1 or type 2 (unspecified): 171 women. The trials took place in Europe, the USA and Canada. Three of the 12 included studies are at low risk of bias, eight studies are at moderate risk of bias, and one study is at high risk of bias. Four trials reported that they were provided with the continuous glucose monitors free of charge or at a reduced cost by the manufacturer. Continuous glucose monitoring (CGM) versus intermittent glucose monitoring, (four studies, 609 women) CGM may reduce hypertensive disorders of pregnancy (pre-eclampsia and pregnancy-induced hypertension) (risk ratio (RR) 0.58, 95% confidence interval (CI) 0.39 to 0.85; 2 studies, 384 women; low-quality evidence), although it should be noted that only two of the four relevant studies reported data for this composite outcome. Conversely, this did not translate into a clear reduction for pre-eclampsia (RR 0.65, 95% CI 0.39 to 1.08; 4 studies, 609 women, moderate-quality evidence). There was also no clear reduction in caesarean section (average RR 0.94, 95% CI 0.75 to 1.18; 3 studies, 427 women; I2 = 41%; moderate-quality evidence) or large-for-gestational age (average RR 0.84, 95% CI 0.57 to 1.26; 3 studies, 421 women; I2 = 70%; low-quality evidence) with CGM. There was not enough evidence to assess perinatal mortality (RR 0.82, 95% CI 0.05 to 12.61, 71 infants, 1 study; low-quality evidence), or mortality or morbidity composite (RR 0.80, 95% CI 0.61 to 1.06; 1 study, 200 women) as the evidence was based on single studies of low quality. CGM appears to reduce neonatal hypoglycaemia (RR 0.66, 95% CI 0.48 to 0.93; 3 studies, 428 infants). Neurosensory disability was not reported. Other methods of glucose monitoring For the following five comparisons, self-monitoring versus a different type of self-monitoring (two studies, 43 women); self-monitoring at home versus hospitalisation (one study, 100 women), pre-prandial versus post-prandial glucose monitoring (one study, 61 women), automated telemedicine monitoring versus conventional system (three studies, 84 women), and constant CGM versus intermittent CGM (one study, 25 women), it is uncertain whether any of the interventions has any impact on any of our GRADE outcomes (hypertensive disorders of pregnancy, caesarean section, large-for-gestational age) because the quality of the evidence was found to be very low. This was due to evidence largely being derived from single trials, with design limitations and limitations with imprecision (wide CIs, small sample sizes, and few events). There was not enough evidence to assess perinatal mortality and neonatal mortality and morbidity composite. Other important outcomes, such as neurosensory disability, were not reported in any of these comparisons. Two new studies (406 women) have been incorporated to one of the comparisons for this update. Although the evidence suggests that CGM in comparison to intermittent glucose monitoring may reduce hypertensive disorders of pregnancy, this did not translate into a clear reduction for pre-eclampsia, and so this result should be viewed with caution. There was no evidence of a difference for other primary outcomes for this comparison. The evidence base for the effectiveness of other monitoring techniques analysed in the other five comparisons is weak and based on mainly single studies with very low-quality evidence. Additional evidence from large well-designed randomised trials is required to inform choices of other glucose monitoring techniques and to confirm the effectiveness of CGM.\nOutput:\n" }, { "from": "agent", "value": "This is an update of a review first published in 2014, updated in 2017. We searched for evidence from randomised controlled studies in November 2018. We identified 12 studies involving 944 women (type 1 diabetes: 660 women; type 2 diabetes: 113 women; in two trials (171 women) there was a mix of type 1 and type 2 diabetes. The trials were from Europe, USA and Canada. There were six comparisons. These were: continuous versus intermittent monitoring of blood glucose (four studies, 609 women); two different ways of self-monitoring (two studies, 43 women); self-monitoring at home versus hospitalisation to control blood glucose levels (one study, 100 women); blood glucose monitoring before a meal (pre-prandial) versus blood glucose monitoring after a meal (post-prandial) (one study, 61 women); automated telemedicine monitoring versus conventional care (three studies, 84 women); and constant continuous monitoring versus intermittent continuous monitoring (one study, 25 women), Continuous versus intermittent monitoring may reduce overall high blood pressure problems during pregnancy (two studies, 384 women, low-quality evidence). However, it should be noted that only two of four relevant studies reported data for this outcome. There was more evidence on high blood pressure and protein in their urine (pre-eclampsia), which showed no clear difference (four studies, 609 women). We also found no difference in the number of women having a caesarean section (three studies, 427 women; moderate-quality evidence). There was not enough evidence to assess infant deaths or the combined outcome of infant deaths and ill-health as these outcomes were based on single studies. Four studies received some support from commercial partners. The other comparisons of different ways of monitoring blood glucose levels were based on very small studies or single studies with very low-quality evidence that did not show any clear differences in outcomes. Although the evidence from randomised controlled studies suggests that continuous monitoring of blood glucose levels may be more effective in reducing high blood pressure problems during pregnancy, only two studies reported on this. There was no clear reduction for pre-eclampsia based on evidence from four studies. For other methods of glucose monitoring, the review showed that there is not enough evidence to say with any certainty which monitoring method for blood glucose is best. More research is needed to find out which other monitoring method is best at reducing the risk of complications for pregnant women with pre-existing diabetes and to confirm the effectiveness of continuous glucose monitoring." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The search identified 77 trials. We included 34 trials in the review involving 69,338 babies, five studies are awaiting classification and there are two ongoing community trials. Included studies were conducted in both developed and developing countries. Among the 34 included trials, three were large, cluster-randomized trials conducted in community settings in developing countries and 31 studies were conducted in hospital settings mostly in developed countries. Data for community and hospital studies were analyzed separately. The three trials conducted in community settings contributed 78% of the total number of children included in this review. Of the trials conducted in hospital settings, the majority had small sample sizes. There were 22 different interventions studied across the included trials and the most commonly studied antiseptics were 70% alcohol, triple dye and chlorhexidine. Only one antiseptic, chlorhexidine was studied in community settings for umbilical cord care. Three community trials reported data on all-cause mortality that comprised 1325 deaths in 54,624 participants and combined results showed a reduction of 23% (average risk ratio (RR) 0.77, 95% confidence interval (CI) 0.63 to 0.94, random-effects, T² = 0.02, I² = 50%) in the chlorhexidine group compared with control. The reduction in omphalitis ranged from 27% to 56% depending on the severity of infection. Cord separation time was increased by 1.7 days in the chlorhexidine group compared with dry cord care (mean difference (MD) 1.75 days, 95% CI 0.44 to 3.05, random-effects, T² = 0.88, I² = 100%). Washing of umbilical cord with soap and water was not advantageous compared with dry cord care in community settings. Among studies conducted in hospital settings, no study reported data for mortality or tetanus. No antiseptic was advantageous to reduce the incidence of omphalitis compared with dry cord care in hospital settings. Topical triple dye application reduced bacterial colonization with Staphylococcus aureus compared with dry cord care (average RR 0.15, 95% CI 0.10 to 0.22, four studies, n = 1319, random-effects, T² = 0.04, I² = 24%) or alcohol application (average RR 0.45, 95% CI 0.25 to 0.80, two studies, n = 487, random-effects, T² = 0.00, I² = 0%). There was no advantage of application of alcohol and triple dye for reduction of colonization with streptococcus. Topical alcohol application was advantageous in reduction of colonization with Enterococcus coli compared with dry cord care (average RR 0.73, 95% CI 0.58 to 0.92, two studies, n = 432, random-effects, T² = 0.00, I² = 0%) and in a separate analysis, triple dye increased the risk of colonization compared with alcohol (RR 3.44, 95% CI 2.10 to 5.64, one study, n = 373). Cord separation time was significantly increased with topical application of alcohol (MD 1.76 days, 95% CI 0.03 to 3.48, nine studies, n = 2921, random-effects, T² = 6.54, I² = 97%) and triple dye (MD 4.10 days, 95% CI 3.07 to 5.13, one study, n = 372) compared with dry cord care in hospital settings. The number of studies was insufficient to make any inference about the efficacy of other antiseptics. There is significant evidence to suggest that topical application of chlorhexidine to umbilical cord reduces neonatal mortality and omphalitis in community and primary care settings in developing countries. It may increase cord separation time however, there is no evidence that it increases risk of subsequent morbidity or infection. There is insufficient evidence to support the application of an antiseptic to umbilical cord in hospital settings compared with dry cord care in developed countries.\nOutput:\n" }, { "from": "agent", "value": "The umbilical cord connects the baby and mother during pregnancy. The cord is cut after birth. The cord stump then dries and falls off, generally within five to 15 days. Infection of the umbilical cord stump (omphalitis), caused by skin bacteria, is a significant cause of illness and death in newborn babies in developing countries. This review evaluated all studies that assessed antiseptics applied topically to the umbilical cord to determine if they reduce the risk of cord infection and death. Thirty-four randomised controlled studies were included involving 69,338 babies. There were 22 different interventions studied. The most commonly studied antiseptics in the included studies were 70% alcohol, triple dye and chlorhexidine. Three studies were conducted in community settings in developing countries; the remainder were conducted in hospital settings, mostly in developed countries. Studies conducted in community settings were large and contributed about 78% of all the participants included in this review. Hospital-based studies were small and had limitations. Studies conducted in community settings evaluated the effectiveness of topical application of chlorhexidine and combined results showed that chlorhexidine reduced risk of death by 23% and the risk of cord infection ranging from 27% to 56%, depending on the severity of infection. Topical application of chlorhexidine may increase cord separation time by about 1.7 days, however, this does not increase subsequent risk of cord infection or death. None of the studies conducted in hospital settings reported data for risk of death or tetanus. No antiseptic was found to be advantageous for the prevention of cord infection compared with dry cord care in hospital settings. Topical triple dye application reduced bacterial colonization with Staphylococcus aureus compared to both dry cord care and alcohol application. There was no advantage of application of alcohol and triple dye for reduction of colonization with streptococcus. Topical alcohol application was advantageous in the reduction of colonization with Enterococcus coli compared with dry cord care and triple dye application. Cord separation time was increased with topical application of alcohol and triple dye compared with dry cord care in hospital settings. There were insufficient studies to determine the efficacy of other antiseptics." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Of 56 trials identified, none reported data on violent injuries. Aggressive behaviour was significantly reduced in intervention groups compared to no intervention groups immediately post intervention in 34 trials with data, (Standardised Mean Difference (SMD) = -0.41; 95% confidence interval (CI) -0.56 to -0.26). This effect was maintained in the seven studies reporting 12 month follow-up (SMD = -0.40, (95% CI -0.73 to -0.06)). School or agency disciplinary actions in response to aggressive behaviour were reduced in intervention groups for nine trials with data, SMD = -0.48; 95% CI -1.16 to 0.19, although this difference may have been due to chance and was not maintained, based on two studies reporting follow-up to two to four months (SMD = 0.03; 95% CI -0.42 to 0.47). Subgroup analyses suggested that interventions designed to improve relationship or social skills may be more effective than interventions designed to teach skills of non-response to provocative situations, but that benefits were similar when delivered to children in primary versus secondary school, and to groups of mixed sex versus boys alone. School-based secondary prevention programmes to reduce aggressive behaviour appear to produce improvements in behaviour greater than would have been expected by chance. Benefits can be achieved in both primary and secondary school age groups and in both mixed sex groups and boys-only groups. Further research is required to establish whether such programmes reduce the incidence of violent injuries or if the benefits identified can be maintained beyond 12 months.\nOutput:\n" }, { "from": "agent", "value": "The authors found 56 studies; the overall findings show that school-based secondary prevention programmes aimed at reducing aggressive behaviour do appear to produce improvements in behaviour. The improvements can be achieved in both primary and secondary school age groups and in both mixed sex groups and boy-only groups. Further research is needed to investigate if the apparent beneficial programmes effects can be realised outside the experimental setting and in settings other than schools. None of the studies collected data on violent injury, so we can not be certain of the extent to which an improvement in behaviour translates to an actual injury reduction. In addition, more research is needed to determine if the beneficial effects can be maintained over time, and if the benefits can be justified against the costs of implementing such programmes." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We retrieved 24,310 citations after removal of duplicates. We reviewed the full text of 317 full-text articles and finally included 70 records, referring to 48 studies, in our synthesis. We were able to perform meta-analysis on 28 studies in the community setting (44 articles) and on 6 studies in primary care (8 articles), but we could not extract usable 2 x 2 data for the remaining 14 community studies, which we did not include in the meta-analysis. All of the studies in the community were in asymptomatic people, whereas two of the six studies in primary care were conducted in people who had symptoms of possible dementia. We judged two studies to be at high risk of bias in the patient selection domain, three studies to be at high risk of bias in the index test domain and nine studies to be at high risk of bias regarding flow and timing. We assessed most studies as being applicable to the review question though we had concerns about selection of participants in six studies and target condition in one study. The accuracy of the MMSE for diagnosing dementia was reported at 18 cut points in the community (MMSE score 10, 14-30 inclusive) and 10 cut points in primary care (MMSE score 17-26 inclusive). The total number of participants in studies included in the meta-analyses ranged from 37 to 2727, median 314 (interquartile range (IQR) 160 to 647). In the community, the pooled accuracy at a cut point of 24 (15 studies) was sensitivity 0.85 (95% confidence interval (CI) 0.74 to 0.92), specificity 0.90 (95% CI 0.82 to 0.95); at a cut point of 25 (10 studies), sensitivity 0.87 (95% CI 0.78 to 0.93), specificity 0.82 (95% CI 0.65 to 0.92); and in seven studies that adjusted accuracy estimates for level of education, sensitivity 0.97 (95% CI 0.83 to 1.00), specificity 0.70 (95% CI 0.50 to 0.85). There was insufficient data to evaluate the accuracy of the MMSE for diagnosing dementia subtypes.We could not estimate summary diagnostic accuracy in primary care due to insufficient data. The MMSE contributes to a diagnosis of dementia in low prevalence settings, but should not be used in isolation to confirm or exclude disease. We recommend that future work evaluates the diagnostic accuracy of tests in the context of the diagnostic pathway experienced by the patient and that investigators report how undergoing the MMSE changes patient-relevant outcomes.\nOutput:\n" }, { "from": "agent", "value": "Two of the studies had serious design weaknesses with regard to their methods for selecting participants, three with regard to the application of the test (MMSE), and nine with regard to the presentation of flow and timing. We were able to do a combined statistical analysis (meta-analysis) on 28 studies in the community setting (44 articles) and 6 studies in primary care (8 articles), but we could not extract usable data for the remaining 14 community studies. Two of the six studies in primary care were conducted in people who had symptoms of possible dementia. We were able to calculate the summary diagnostic accuracy of the MMSE at three cut points in community-based studies, but we didn't have enough data to do this in the primary care studies. A perfect test would have sensitivity (ability to identify anyone with dementia) of 1.0 (100%) and specificity (ability to identify people without dementia) of 1.0 (100%). For the MMSE, the summary accuracy at a cut point of 25 (10 studies) was sensitivity 0.87 and specificity 0.82. In seven studies that adjusted accuracy estimates for level of education, we found that the test had a sensitivity of 0.97 and specificity of 0.70. The summary accuracy at a cut point of 24 (15 studies) was sensitivity 0.85 and specificity 0.90. Based on these results, we would expect 85% of people with dementia to be correctly identified with the MMSE, while 15% would be wrongly classified as not having dementia; 90% of those tested would be correctly identified as not having dementia whilst 10% would be false positives and might be referred for further testing. Our results support the use of the MMSE as part of the process for deciding whether or not someone has dementia, but the results of the test should be interpreted in broader context of the individual patient, such as their personality, behaviour and how they are managing at home and in daily life." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 33 studies of STPP involving 2173 randomised participants with common mental disorders. Studies were of diverse conditions in which problems with emotional regulation were purported to play a causative role albeit through a range of symptom presentations. These studies evaluated STPP for this review's primary outcomes (general, somatic, anxiety and depressive symptom reduction), as well as interpersonal problems and social adjustment. Except for somatic measures in the short-term, all outcome categories suggested significantly greater improvement in the treatment versus the control groups in the short-term and medium-term. Effect sizes increased in long-term follow-up, but some of these effects did not reach statistical significance. A relatively small number of studies (N < 20) contributed data for the outcome categories. There was also significant heterogeneity between studies in most categories, possibly due to observed differences between manualised versus non-manualised treatments, short versus longer treatments, studies with observer-rated versus self report outcomes, and studies employing different treatment models. There has been further study of STPP and it continues to show promise, with modest to large gains for a wide variety of people. However, given the limited data, loss of significance in some measures at long-term follow-up and heterogeneity between studies, these findings should be interpreted with caution. Furthermore, variability in treatment delivery and treatment quality may limit the reliability of estimates of effect for STPP. Larger studies of higher quality and with specific diagnoses are warranted.\nOutput:\n" }, { "from": "agent", "value": "We searched scientific databases to find all published and unpublished studies of STPP compared with wait-list control, treatment as usual or minimal treatment up to July 2012. We searched for studies in adults over 17 years of age with common mental disorders being treated in an outpatient setting. We excluded people with psychotic disorders. We included 33 studies involving 2173 people. When the results of the studies were combined and analysed, we found that there was a significantly greater improvement in the groups of people who received STPP versus the control groups, both in the short-term (less than three months after treatment) and medium-term (three to six months after treatment). These benefits generally appeared to increase in the long-term. However, some results did not remain statistically significant in the long-term and, in addition, the studies varied in terms of their design, meaning that these conclusions are tentative and need confirmation with further research. The finding that a short-term psychological therapy treatment may be broadly applicable and effective is of importance in the atmosphere of current global healthcare and economic restrictions. The studies were of variable quality." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The search identified three RCTs with 138 participants. All three trials included only children with viral encephalitis, one of these included only children with Japanese encephalitis, a specific form of viral encephalitis. Only the trial of Japanese encephalitis (22 children) contributed to the primary outcome of this review and follow-up in that study was for three to six months after hospital discharge. There was no follow-up of participants in the other two studies. We identified one ongoing trial. For the primary outcomes, the results showed no significant difference between IVIG and placebo when used in the treatment of children with Japanese encephalitis: significant disability (RR 0.75, 95% CI 0.22 to 2.60; P = 0.65) and serious adverse events (RR 1.00, 95% CI 0.07 to 14.05; P = 1.00). For the secondary outcomes, the study of Japanese encephalitis showed no significant difference between IVIG and placebo when assessing significant disability at hospital discharge (RR 1.00, 95% CI 0.60 to 1.67). There was no significant difference (P = 0.53) in Glasgow Coma Score at discharge between IVIG (median score 14; range 3 to 15) and placebo (median 14 score; range 7 to 15) in the Japanese encephalitis study. The median length of hospital stay in the Japanese encephalitis study was similar for IVIG-treated (median 13 days; range 9 to 21) and placebo-treated (median 12 days; range 6 to 18) children (P = 0.59). Pooled analysis of the results of the other two studies resulted in a significantly lower mean length of hospital stay (MD -4.54 days, 95% CI -7.47 to -1.61; P = 0.002), time to resolution of fever (MD -0.97 days, 95% CI -1.25 to -0.69; P < 0.00001), time to stop spasms (MD -1.49 days, 95% CI -1.97 to -1.01; P < 0.00001), time to regain consciousness (MD -1.10 days, 95% CI -1.48 to -0.72; P < 0.00001), and time to resolution of neuropathic symptoms (MD -3.20 days, 95% CI -3.34 to -3.06; P < 0.00001) in favour of IVIG when compared with standard care. None of the included studies reported other outcomes of interest in this review including need for invasive ventilation, duration of invasive ventilation, cognitive impairment, poor adaptive functioning, quality of life, number of seizures, and new diagnosis of epilepsy. The quality of evidence was very low for all outcomes of this review. The findings suggest a clinical benefit of adjunctive IVIG treatment for children with viral encephalitis for some clinical measures (i.e. mean length of hospital stay, time (days) to stop spasms, time to regain consciousness, and time to resolution of neuropathic symptoms and fever. For children with Japanese encephalitis, IVIG had a similar effect to placebo when assessing significant disability and serious adverse events. Despite these findings, the risk of bias in the included studies and quality of the evidence make it impossible to reach any firm conclusions on the efficacy and safety of IVIG as add-on treatment for children with encephalitis. Furthermore, the included studies involved only children with viral encephalitis, therefore findings of this review cannot be generalised to all forms of encephalitis. Future well-designed RCTs are needed to assess the efficacy and safety of IVIG in the management of children with all forms of encephalitis. There is a need for internationally agreed core outcome measures for clinical trials in childhood encephalitis.\nOutput:\n" }, { "from": "agent", "value": "We searched medical databases for studies in which neither participants nor researchers were told which treatment was given (called a randomised double-blind trial). The effectiveness and safety of IVIG were considered in terms of the occurrence of significant disability at six months after hospital discharge and the proportion of children experiencing at least one serious side effect. Up to 30 September 2016, only three studies comprising 138 children met the criteria to be included in this review. All three studies included only children with viral encephalitis. One study of Japanese encephalitis, a specific form of viral encephalitis, analysed both effectiveness and safety, and concluded that IVIG treatment had no additional beneficial effects when compared with placebo (pretend) treatment. The other two studies analysed other measurements, such as length of hospital stay, time to resolution of spasms, symptoms arising due to nerve damage, and time to regain consciousness and concluded that adding IVIG treatment was more effective than standard care alone when these outcomes were considered. The quality of the evidence was very low due to the small number of children and studies. The quality of evidence in the included studies was very low, making it impossible to draw any firm and definite conclusions on the clinical efficacy and safety of IVIG treatment for children with encephalitis. Furthermore, there was no information on funding while, for one study, the main authors' group was affiliated to the funding body: this is a well-known potential source of conflict of interest and thus of bias." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: This review included two trials, involving 103 participants, one comparing titanium with resorbable plates and screws and the other titanium with resorbable screws. Both studies were at high risk of bias and provided very limited data for the primary outcomes of this review. All participants in one trial suffered mild to moderate postoperative discomfort with no statistically significant difference between the two plating groups at different follow-up times. Mean scores of patient satisfaction were 7.43 to 8.63 (range 0 to 10) with no statistically significant difference between the two groups throughout follow-up. Adverse effects reported in one study were two plate exposures in each group occurring between the third and ninth months. Plate exposures occurred mainly in the posterior maxillary region, except for one titanium plate exposure in the mandibular premolar region. Known causes of infection were associated with loosened screws and wound dehiscence with no statistically significant difference in the infection rate between titanium (3/196), and resorbable (3/165) plates. We do not have sufficient evidence to determine if titanium plates or resorbable plates are superior for fixation of bones after orthognathic surgery. This review provides insufficient evidence to show any difference in postoperative pain and discomfort, level of patient satisfaction, plate exposure or infection for plate and screw fixation using either titanium or resorbable materials.\nOutput:\n" }, { "from": "agent", "value": "We included two studies that analysed a total of 103 participants. The evidence in this review is up to date as of 20 January 2017. Study participants were adults older than 16 years of age. One study compared titanium with resorbable plates and screws and the other titanium with resorbable screws. One study was conducted in China, the other in Germany. Both studies were at high risk of bias and provided very limited data. We do not have sufficient evidence to determine if titanium plates or resorbable plates are superior for the fixation of bones after corrective jaw surgery. This review provides insufficient evidence to show any difference in postoperative pain and discomfort, level of patient satisfaction, plate exposure or infection for plate and screw fixation using either titanium or resorbable materials. Both included studies were assessed as being at high risk of bias and the very limited and weak evidence was of very low quality." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included three new RCTs in this update, which now comprises 10 studies with a total of 614 participants. We judged most trials as having uncertain risk of bias regarding randomization. Other than this, the overall risk of bias was low. Most included trials had small sample sizes. All of the trials assessed the primary outcome of conversion to general anaesthesia. Ten trials comparing anaesthesia performed with hyperbaric and isobaric bupivacaine failed to show any difference in need for conversion to general anaesthesia (RR 0.33, 95% CI 0.09 to 1.17, 614 participants, very low quality of evidence). Nine trials also failed to show a difference in the need for supplemental analgesics (RR 0.61, 95% CI 0.26 to 1.41, 554 participants, very low quality of evidence). Four trials comparing requirement for ephedrine did not show any difference (RR 0.89, 95% CI 0.57 to 1.38, 256 participants, very low quality of evidence). Seven trials did not provide convincing evidence of difference in nausea and vomiting (RR 0.99, 95% CI 0.57 to 1.72, 433 participants, low quality of evidence). Three trials failed to show a difference in headache (OR 1.82, 95% CI 0.47 to 6.99, 234 participants, low quality of evidence). Two trials showed that the time until sensory block to the thoracic 4th (T4) spinal level was shorter with hyperbaric bupivacaine (MD -1.06 minutes, 95% CI -1.80 to -0.31, 128 participants, moderate quality of evidence). Six trials showed no difference in the amount of ephedrine used (RR 0.23, 95% CI -1.65 to 2.12, 386 participants, moderate quality of evidence). Three trials failed to show any difference in high block (RR 0.88, 95% CI 0.16 to 4.90, 205 participants). Data are limited for some of the outcomes. Reporting of the included trials is less than optimal. For these reasons the overall quality of evidence is low or very low for most of the outcomes, based on the GRADE method of assessment. This review found that intrathecal hyperbaric bupivacaine had a more rapid onset of sensory blockade at the 4th thoracic vertebra (T4) level than isobaric bupivacaine. Hower, despite incorporating more data in the analysis, we found little evidence that the need for conversion to general anaesthesia and supplemental analgesia differed between the hyperbaric or isobaric bupivacaine groups. This is mainly due to the rarity of these outcomes, variability in the dose, use of adjuvant drugs and differences in the technique used for regional anaesthesia. There were no differences in the adverse effects studied. Any possible advantage of hyperbaric bupivacaine needs to be confirmed in larger randomized trials. In future research, criteria for conversion to general anaesthesia need to be defined objectively and applied uniformly.\nOutput:\n" }, { "from": "agent", "value": "The evidence is current to March 2016. We found 10 clinical trials evaluating these two types of bupivacaine, involving 614 women. The studies assessed the following effects of the two types of medicine: women needing to switch to general anaesthesia, additional drugs for pain relief or low blood pressure, experiencing nausea and vomiting, headache and excessive numbness. We found that all the studies had been done properly. None of them reported their source of funding. We await responses from the authors of two more studies, and will cover these when we next update the review. We found that there is insufficient evidence to establish whether denser or normal bupivacaine is the more effective in reducing the need for: a) switching to general anaesthesia; b) additional pain relief medication. Denser bupivacaine had a more rapid onset of pain relief. Due to the differences among the included studies in doses given, variety of additional drugs used for pain relief, variation in regional anaesthesia techniques and the small numbers of participants, we rated the overall quality of evidence for different outcomes from very low to moderate, as very few women experienced untoward events in all trials. We conclude that the denser form provides faster pain relief than the normal one. More research is required to be certain about the effectiveness of the denser form for other outcomes." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Forty-one studies (8928 patients) were included. The majority of included studies were rated as low risk of bias. Ten studies were rated at high risk of bias. Seven of these studies were single-blind and three studies were open-label. However, two open-label studies and four of the single-blind studies utilized investigator performed endoscopy as an endpoint, which may protect against bias. 5-ASA was significantly superior to placebo for maintenance of clinical or endoscopic remission. Forty-one per cent of 5-ASA patients relapsed compared to 58% of placebo patients (7 studies, 1298 patients; RR 0.69, 95% CI 0.62 to 0.77). There was a trend towards greater efficacy with higher doses of 5-ASA with a statistically significant benefit for the 1 to 1.9 g/day (RR 0.65; 95% CI 0.56 to 0.76) and the > 2 g/day subgroups (RR 0.73, 95% CI 0.60 to 0.89). SASP was significantly superior to 5-ASA for maintenance of remission. Forty-eight per cent of 5-ASA patients relapsed compared to 43% of SASP patients (12 studies, 1655 patients; RR 1.14, 95% CI 1.03 to 1.27). A GRADE analysis indicated that the overall quality of the evidence for the primary outcome for the placebo and SASP-controlled studies was high. No statistically significant differences in efficacy or adherence were found between once daily and conventionally dosed 5-ASA. Twenty-nine per cent of once daily patients relapsed over 12 months compared to 31% of conventionally dosed patients (8 studies, 3127 patients; RR 0.91, 95% CI 0.82 to 1.01). Eleven per cent of patients in the once daily group failed to adhere to their medication regimen compared to 9% of patients in the conventional dosing group (6 studies, 1462 patients; RR 1.22, 95% CI 0.91 to 1.64). There does not appear to be any difference in efficacy among the various 5-ASA formulations. Forty-four per cent of patients in the 5-ASA group relapsed compared to 41% of patients in the 5-ASA comparator group (6 studies, 707 patients; RR 1.08, 95% CI 0.91 to 1.28). A pooled analysis of two studies showed no statistically significant difference in efficacy between Balsalazide 6 g and 3 g/day. Twenty-three per cent of patients in the 6 g/day group relapsed compared to 33% of patients in the 3 g/day group (216 patients; RR 0.76; 95% CI 0.45 to 2.79). One study found Balsalazide 4 g to be superior to 2 g/day. Thirty-seven per cent of patients in the 4 g/day Balsalazide group relapsed compared to 55% of patients in the 2 g/day group (133 patients; RR 0.66; 95% CI 0.45 to 0.97). One study found a statistically significant difference between Salofalk granules 3 g and 1.5 g/day. Twenty-five per cent of patients in the Salofalk 3 g/day group relapsed compared to 39% of patients in the 1.5 g/day group (429 patients; RR 0.65; 95% CI 0.49 to 0.86). Common adverse events included flatulence, abdominal pain, nausea, diarrhea, headache, dyspepsia, and nasopharyngitis. There were no statistically significant differences in the incidence of adverse events between 5-ASA and placebo, 5-ASA and SASP, once daily and conventionally dosed 5-ASA, 5-ASA and comparator 5-ASA formulations and 5-ASA dose ranging studies. The trials that compared 5-ASA and SASP may have been biased in favour of SASP because most trials enrolled patients known to be tolerant to SASP which may have minimized SASP-related adverse events. 5-ASA was superior to placebo for maintenance therapy in ulcerative colitis. However, 5-ASA had a statistically significant therapeutic inferiority relative to SASP. Oral 5-ASA administered once daily is as effective and safe as conventional dosing for maintenance of remission in quiescent ulcerative colitis. There does not appear to be any difference in efficacy or safety between the various formulations of 5-ASA. Patients with extensive ulcerative colitis or with frequent relapses may benefit from a higher dose of maintenance therapy. High dose therapy appears to be as safe as low dose and is not associated with a higher incidence of adverse events.\nOutput:\n" }, { "from": "agent", "value": "This review includes 41 randomized trials with a total of 8928 participants. Oral 5-ASA was found to be more effective than placebo (fake drug) for maintaining remission. Although oral 5-ASA preparations are effective for maintaining remission in ulcerative colitis, they are no more effective than sulfasalazine (SASP) therapy. People who have become well can remain so by continuing to take either medication. There is no evidence that side effects are more frequent with one or the other medication. However, the side effects of 5-ASA may be notably less than those associated with SASP therapy. Common side effects associated with 5-ASA included flatulence, abdominal pain, nausea, diarrhea, headache, dyspepsia (indigestion), and nasopharyngitis (inflammation of the nasal passages). Most of the trials comparing 5-ASA with SASP enrolled patients who were known to tolerate SASP. This may have reduced SASP-related side effects in these trials. Male infertility is associated with SASP and not with 5-ASA, so 5-ASA may be preferred for patients concerned about fertility. 5-ASA therapy is more expensive than SASP, so SASP may be the preferred option where cost is an important factor. Oral 5-ASA administered once daily is as effective and safe as conventional dosing (two or three times daily) for maintaining remission in ulcerative colitis. There does not appear to be any difference in efficacy or safety between the various formulations of 5-ASA. Patients with extensive ulcerative colitis or with frequent relapses may benefit from a higher dose of maintenance therapy. High dose therapy appears to be as safe as low dose and is not associated with a higher incidence of side effects." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Nine studies with 658 infants fulfilled the inclusion criteria. Term and preterm infants with Rh or ABO (or both) incompatibility were included. The use of exchange transfusion decreased significantly in the immunoglobulin treated group (typical RR 0.35, 95% CI 0.25 to 0.49; typical RD -0.22, 95% CI -0.27 to -0.16; NNTB 5). The mean number of exchange transfusions per infant was also significantly lower in the immunoglobulin treated group (MD -0.34, 95% CI -0.50 to -0.17). However, sensitivity analysis by risk of bias showed that in the only two studies in which the treatment was masked by use of a placebo and outcome assessment was blinded, the results differed; there was no difference in the need for exchange transfusions (RR 0.98, 95% CI 0.48 to 1.98) or number of exchange transfusions (MD -0.04, 95% CI -0.18 to 0.10). Two studies assessed long-term outcomes and found no cases of kernicterus, deafness or cerebral palsy. Although overall results show a significant reduction in the need for exchange transfusion in infants treated with IVIg, the applicability of the results is limited because of low to very low quality of evidence. Furthermore, the two studies at lowest risk of bias show no benefit of IVIg in reducing the need for and number of exchange transfusions. Based on these results, we have insufficient confidence in the effect estimate for benefit of IVIg to make even a weak recommendation for the use of IVIg for the treatment of alloimmune HDN. Further studies are needed before the use of IVIg for the treatment of alloimmune HDN can be recommended, and should include blinding of the intervention by use of a placebo as well as sufficient sample size to assess the potential for serious adverse effects.\nOutput:\n" }, { "from": "agent", "value": "We searched the medical literature to 19 May 2017 and found nine randomized (clinical studies where people are randomly put into one of two or more treatment groups) or partly (quasi) randomized trials (including 658 participants) that assessed the efficiency of IVIg in infants with alloimmune HDN. Analysis of all included studies showed a reduction in the need for and number of ETs in infants treated with IVIg combined with phototherapy compared to infants treated with phototherapy only. However, this was not confirmed in an analysis of the two placebo-controlled studies (where a pretend treatment was given). There was no difference in the need for or number of top-up transfusions. The evidence from the studies was very low quality. However, two studies used a placebo, thereby minimizing bias and allowing blinding of the researchers assessing the response. These studies were consistent with each other and yielded moderate quality evidence (with a relatively small total number of participants involved (172) being the only reason to not regard the level of evidence from them as high) that IVIg was ineffective in preventing ET or top-up transfusions. Based on all included studies, we could make no conclusions on the benefit of IVIg in preventing ET or top-up transfusion. However, the two placebo-controlled trials provided evidence of moderate quality that IVIg was ineffective in preventing ET or top-up transfusion, and therefore routine use in alloimmune HDN should not be recommended. However, since there was some evidence that IVIg reduced hemolysis (in laboratory studies), future high-quality studies are needed to determine whether IVIg has limited role in some infants with alloimmune HDN." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Five trials involving 7391 women (2033 with a history of a pregnancy affected by a NTD and 5358 with no history of NTDs) were included. Four comparisons were made: 1) supplementation with any folate versus no intervention, placebo or other micronutrients without folate (five trials); 2) supplementation with folic acid alone versus no treatment or placebo (one trial); 3) supplementation with folate plus other micronutrients versus other micronutrients without folate (four trials); and 4) supplementation with folate plus other micronutrients versus the same other micronutrients without folate (two trials). The risk of bias of the trials was variable. Only one trial was considered to be at low risk of bias. The remaining studies lacked clarity regarding the randomisation method or whether the allocation to the intervention was concealed. All the participants were blinded to the intervention, though blinding was unclear for outcome assessors in the five trials. The results of the first comparison involving 6708 births with information on NTDs and other infant outcomes, show a protective effect of daily folic acid supplementation (alone or in combination with other vitamins and minerals) in preventing NTDs compared with no interventions/placebo or vitamins and minerals without folic acid (risk ratio (RR) 0.31, 95% confidence interval (CI) 0.17 to 0.58); five studies; 6708 births; high quality evidence). Only one study assessed the incidence of NTDs and showed no evidence of an effect (RR 0.07, 95% CI 0.00 to 1.32; 4862 births) although no events were found in the group that received folic acid. Folic acid had a significant protective effect for reoccurrence (RR 0.34, 95% CI 0.18 to 0.64); four studies; 1846 births). Subgroup analyses suggest that the positive effect of folic acid on NTD incidence and recurrence is not affected by the explored daily folic acid dosage (400 µg (0.4 mg) or higher) or whether folic acid is given alone or with other vitamins and minerals. These results are consistent across all four review comparisons. There is no evidence of any preventive or negative effects on cleft palate (RR 0.73, 95% CI 0.05 to 10.89; three studies; 5612 births; low quality evidence), cleft lip ((RR 0.79, 95% CI 0.14 to 4.36; three studies; 5612 births; low quality evidence), congenital cardiovascular defects (RR 0.57, 95% CI 0.24 to 1.33; three studies; 5612 births; low quality evidence), miscarriages (RR 1.10, 95% CI 0.94 to 1.28; five studies; 7391 pregnancies; moderate quality evidence) or any other birth defects (RR 0.94, 95% CI 0.53 to 1.66; three studies; 5612 births; low quality evidence). There were no included trials assessing the effects of this intervention on neonatal death, maternal blood folate or anaemia at term. Folic acid, alone or in combination with vitamins and minerals, prevents NTDs, but does not have a clear effect on other birth defects.\nOutput:\n" }, { "from": "agent", "value": "This review confirms that folic acid supplementation prevents the first and second time occurrence of NTDs and shows there is not enough evidence to determine if folic acid prevents other birth defects. Information about the safety of other current and alternative supplementation schemes and any possible effects on other outcomes for mothers and babies is also lacking. This review of five trials, involving 7391 pregnancies (2033 with a history of a pregnancy affected by a NTD and 5358 with no history of NTDs), shows the protective effect of daily folic acid supplementation in doses ranging from 0.36 mg (360 µg) to 4 mg (4000 µg) a day, with and without other vitamins and minerals, before conception and up to 12 weeks of pregnancy, for preventing the recurrence of these defects. There were insufficient data to evaluate the effects on other outcomes such as cleft lip and palate, miscarriages or any other birth defects. More research is needed on different types of supplementation programmes and the use of different types of supplements (such as 5-methyl-tetrahydrofolate -5-MTHF), particularly in countries where folic acid fortification of staple foods like wheat or maize flour is not mandatory and where the prevalence of NTDs is still high. The overall quality of the evidence for neonatal outcomes was high for NTDs, whereas, it was of low quality for other neonatal outcomes. The overall quality of the evidence for maternal outcomes was rated as moderate." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included two trials comparing planned caesarean section versus planned vaginal birth for twin pregnancies. Most of the data included in the review were from a multicentre trial where 2804 women were randomised in 106 centres in 25 countries. All centres had facilities to perform emergency caesarean section and had anaesthetic, obstetrical, and nursing staff available in the hospital at the time of planned vaginal delivery. In the second trial carried out in Israel, 60 women were randomised. We judged the risk of bias to be low for all categories except performance (high) and outcome assessment bias (unclear). There was no clear evidence of differences between women randomised to planned caesarean section or planned vaginal birth for maternal death or serious morbidity (risk ratio (RR) 0.86, 95% confidence interval (CI) 0.67 to 1.11; 2844 women; two studies; moderate quality evidence). There was no significant difference between groups for perinatal or neonatal death or serious neonatal morbidity (RR 1.15, 95% CI 0.80 to 1.67; data for 5565 babies, one study, moderate quality evidence). No studies reported childhood disability. For secondary outcomes there was no clear evidence of differences between groups for perinatal or neonatal mortality (RR 1.41, 95% CI 0.76 to 2.62; 5685 babies; two studies, moderate quality evidence), serious neonatal morbidity (RR 1.03, 95% CI 0.65 to 1.64; 5644 babies; two studies, moderate quality evidence) or any of the other neonatal outcomes reported. The number of women undergoing caesarean section was reported in both trials. Most women in the planned caesarean group had treatment as planned (90.9% underwent caesarean section), whereas in the planned vaginal birth group 42.9% had caesarean section for at least one twin. For maternal mortality; no events were reported in one trial and two deaths (one in each group) in the other. There were no significant differences between groups for serious maternal morbidity overall (RR 0.86, 95% CI 0.67 to 1.11; 2844 women; two studies) or for different types of short-term morbidity. There were no significant differences between groups for failure to breastfeed (RR 1.14, 95% CI 0.95 to 1.38; 2570 women, one study; moderate quality evidence) or the number of women with scores greater than 12 on the Edinbugh postnatal depression scale (RR 0.95, 95% CI 0.78 to 1.14; 2570 women, one study; moderate quality evidence). Data mainly from one large, multicentre study found no clear evidence of benefit from planned caesarean section for term twin pregnancies with leading cephalic presentation. Data on long-term infant outcomes are awaited. Women should be informed of possible risks and benefits of labour and vaginal birth pertinent to their specific clinical presentation and the current and long-term effects of caesarean section for both mother and babies. There is insufficient evidence to support the routine use of planned caesarean section for term twin pregnancy with leading cephalic presentation, except in the context of further randomised trials.\nOutput:\n" }, { "from": "agent", "value": "In this review we included two randomised trials comparing planned caesarean versus planned vaginal birth for twin pregnancies which together included 2864 women. For important outcomes the evidence was assessed as being of moderate quality. For maternal mortality no events were reported in one trial and two deaths (one in each group) in the other. There was no clear evidence of differences between women randomised to planned caesarean or planned vaginal birth for death or serous illness in either the mothers or babies. No studies reported childhood disability. The number of women undergoing caesarean section was reported in both trials. Most women in the planned caesarean group had treatment as planned (90.9%), whereas in the planned vaginal birth group 42.9% had caesarean section for at least one twin. There were no significant differences between groups for failure to breastfeed or for postnatal depression. There is very little clear research evidence to provide guidance on the method of birth for twin pregnancies. The benefits and risks should be made available to women, including short-term and long-term consequences for both mother and babies. Future research should aim to provide more clarity on this issue as medical interventions in the birth process should be avoided unless there is reasonable clinical certainty that they will be of long-term benefit." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Thirteen trials were included. None measured an injury outcome. Two trials measured error, and the remaining trials used neuropsychological tests to assess cognitive performance. The trials assessing the impact on errors found that caffeine significantly reduced the number of errors compared to placebo. The pooled effect estimates on performance by cognitive domain suggest that, when compared to placebo, caffeine improved concept formation and reasoning (SMD -0.41; 95% CI -1.04 to 0.23), memory (SMD -1.08; 95% CI -2.07 to -0.09), orientation and attention (SMD -0.55; 95% CI -0.83 to -0.27) and perception (SMD -0.77; 95% CI -1.73 to 0.20); although there was no beneficial effect on verbal functioning and language skills (SMD 0.18; 95% CI -0.50 to 0.87). One trial comparing the effects of caffeine with a nap found that there were significantly less errors made in the caffeine group. Other trials comparing caffeine with other active interventions (for example nap, bright light, modafinil) found no significant differences. There is a high risk of bias for the adequacy of allocation concealment and presence of selective outcome reporting amongst the trials. Caffeine may be an effective intervention for improving performance in shift workers however, there are no trials from which we can assess its effect on injuries. The results largely originate from studies involving young participants under simulated conditions, and the extent to which the findings are generalisable to older workers and real world shift work is unclear. Based on the current evidence, there is no reason for healthy individuals who already use caffeine within recommended levels to improve their alertness to stop doing so. The assessment of the relative effects of caffeine to other potential countermeasures should be a focus of future research.\nOutput:\n" }, { "from": "agent", "value": "For this systematic review, the authors searched for randomised controlled trials which investigated the effects of caffeine on injury, error and cognitive performance in shift workers. They found 13 trials - none of the trials looked at the effect on injury, two trials measured error, while the remaining trials used neuropsychological tests to assess cognitive performance. The results of the trials suggest that compared to no intervention, caffeine can reduce the number of errors and improve cognitive performance in shift workers. No difference in effect was found by the trials comparing caffeine with other interventions (such as nap, bright light and modafinil). However, due to some methodological weaknesses of the trials, some caution is required when interpreting the results. The authors of the systematic review conclude that caffeine may be an effective intervention for improving performance in shift workers however, there are no trials from which they could assess its effect on injuries. Based on the current evidence, the review authors judge that there is no reason for healthy shift workers who already use caffeine within recommended levels to improve their alertness, to stop doing so. They go on to suggest that it would be useful for further trials to be undertaken to assess the effects of caffeine against other potential countermeasures." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: The search identified 102 potentially eligible studies. Judged from the information in the title and abstract six of these concerning the percutaneous block, involving 358 participants, fulfilled the inclusion criteria and were included in the review. All were RCTs in which the participants were followed for at least four weeks. We excluded studies published only as abstracts. We identified one RCT comparing EUS-guided or computed tomography (CT) -guided CPB but its aim was to assess efficacy in controlling chronic abdominal pain associated with chronic pancreatitis rather than pancreatic cancer, so it was excluded. For pain (VAS) at four weeks the mean difference was -0.42 in favour of CPB (95% confidence interval (CI) -0.70 to - 0.13, P = 0.004, fixed-effect model). At eight weeks the mean difference was -0.44 (95% CI -0.89 to - 0.01, random-effects model). At eight weeks there was significant heterogeneity (I2 = 89%). Opioid consumption was significantly lower in the CPB group than the control group (P < 0.00001). Although statistical evidence is minimal for the superiority of pain relief over analgesic therapy, the fact that CPB causes fewer adverse effects than opioids is important for patients. Further studies and RCTs are recommended to demonstrate the potential efficacy of a less invasive technique under EUS guidance.\nOutput:\n" }, { "from": "agent", "value": "We searched for studies comparing CPB with standard analgesic therapy in patients with inoperable pancreatic cancer. We were interested in the primary outcome of pain, measured on a visual analogue scale (VAS). We also looked at the amount of opioid (morphine-like drugs) patients took (opioid consumption) and adverse effects of the treatment. Six studies (358 participants) comparing CPB with standard therapy (painkillers) met our inclusion criteria. At four weeks pain scores were significantly lower in the CPB group. Opioid consumption was also significantly lower than in the control group. The main adverse effects were diarrhoea or constipation (this symptom was significantly more likely in the control group, where opioid consumption was higher). Endoscopic ultrasonography (EUS)-guided CPB is becoming popular as a minimally invasive technique that has fewer risks, but we were not able to find any RCTs assessing this method (current medical literature on this subject is limited to studies without control groups). Although the data on EUS-guided CPB and pain control are promising, we await rigorously designed RCTs that may validate these findings. We conclude that, although statistical evidence is minimal for the superiority of pain relief over analgesic therapy, the fact that CPB causes fewer adverse effects than opioids is important for patients." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Twelve studies were eligible for inclusion. Allergic disease and / or food hypersensitivity outcomes were assessed by 6 studies enrolling 2080 infants, but outcomes for only 1549 infants were reported. Studies generally had adequate randomisation, allocation concealment and blinding of treatment. However, the findings of this review should be treated with caution due to excess losses in patient follow-up (17% to 61%). Meta-analysis of five studies reporting the outcomes of 1477 infants found a significant reduction in infant eczema (typical RR 0.82, 95% CI 0.70, 0.95). However, there was significant and substantial heterogeneity between studies. One study reported that the difference in eczema between groups persisted to 4 years age. When the analysis was restricted to studies reporting atopic eczema (confirmed by skin prick test or specific IgE), the findings were no longer significant (typical RR 0.80, 95% CI 0.62, 1.02). All studies reporting significant benefits used probiotic supplements containing L. rhamnosus and enrolled infants at high risk of allergy. No other benefits were reported for any other allergic disease or food hypersensitivity outcome. There is insufficient evidence to recommend the addition of probiotics to infant feeds for prevention of allergic disease or food hypersensitivity. Although there was a reduction in clinical eczema in infants, this effect was not consistent between studies and caution is advised in view of methodological concerns regarding included studies. Further studies are required to determine whether the findings are reproducible.\nOutput:\n" }, { "from": "agent", "value": "This review found that probiotics added to infant feeds may help prevent infant eczema, with one study suggesting the benefit may persist to four years of age. However, concerns regarding the quality of studies, inconsistency of findings between studies, and the fact that the benefits did not persist if restricted to infants with evidence of sensitisation to allergens, suggests that further studies are needed to confirm these results." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 11 studies with a total of 596 participants. Two studies assessed fish oil versus olive oil or corn oil placebo. The following were all looked at in single studies: oral zinc sulphate compared to placebo, selenium versus selenium plus vitamin E versus placebo, vitamin D versus placebo, vitamin D versus vitamin E versus vitamins D plus vitamin E together versus placebo, pyridoxine versus placebo, sea buckthorn seed oil versus sea buckthorn pulp oil versus placebo, hempseed oil versus placebo, sunflower oil (linoleic acid) versus fish oil versus placebo, and DHA versus control (saturated fatty acids of the same energy value). Two small studies on fish oil suggest a possible modest benefit, but many outcomes were explored. A convincingly positive result from a much larger study with a publicly-registered protocol is needed before clinical practice can be influenced. There is no convincing evidence of the benefit of dietary supplements in eczema, and they cannot be recommended for the public or for clinical practice at present. Whilst some may argue that at least supplements do not do any harm, high doses of vitamin D may give rise to serious medical problems, and the cost of long-term supplements may also mount up.\nOutput:\n" }, { "from": "agent", "value": "We looked for trials comparing supplements with placebo (dummy). We included 11 randomised controlled trials (596 participants) when it was clear that the children or adults taking part had atopic eczema. In reviewing the trials, the main outcomes we looked for were evidence of improvement in the symptoms of eczema, such as itching or loss of sleep, in the short-term (i.e. six weeks). In the longer term, we wanted to see evidence of a reduced need for treatment for the eczema or a reduction in the number of flares. We also looked for evidence of any general improvement in the eczema and in individual symptoms. Overall, we found no convincing evidence that taking supplements improved the eczema of those involved. In general, studies were small with low numbers of participants and of poor quality in terms of the way they were run. Two trials of fish oil did find slight improvement for the participants in terms of the degree of itchiness and quality of life. However, these trials had small numbers, which means they had little chance of finding real differences if they did exist. That is why larger trials are needed before any recommendations can be made. We found no evidence of adverse (harmful) effects in those who took part in the trials. People sometimes think that supplements can at least do no harm; however, high doses of vitamin D, for example, can cause serious medical problems, and the safety of dietary supplements should not be assumed. The cost of supplements can also mount up." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: This review includes 15 trials with a total of 791 participants that have evaluated Pycnogenol® for the treatment of seven different chronic disorders. These included asthma (two studies; N = 86), attention deficit hyperactivity disorder (one study; N = 61), chronic venous insufficiency (two studies; N = 60), diabetes mellitus (four studies; N = 201), erectile dysfunction (one study; N = 21), hypertension (two studies; N = 69) and osteoarthritis (three studies; N = 293). Two of the studies were conducted exclusively in children; the others involved adults. Due to small sample size, limited numbers of trials per condition, variation in outcomes evaluated and outcome measures used, as well as the risk of bias in the included studies, no definitive conclusions regarding the efficacy or safety of Pycnogenol® are possible. Current evidence is insufficient to support Pycnogenol® use for the treatment of any chronic disorder. Well-designed, adequately powered trials are needed to establish the value of this treatment.\nOutput:\n" }, { "from": "agent", "value": "We chose to focus on Pycnogenol® as this supplement is a standardised product, many trials have been conducted, and it is extensively marketed internationally. Our review aimed to assess the efficacy and safety of Pycnogenol® as a treatment for chronic disorders. We identified 15 eligible randomised controlled trials with a total of 791 participants which addressed seven different chronic conditions: asthma (two studies); attention deficit hyperactivity disorder (one study), chronic venous insufficiency (two studies), diabetes (four studies), erectile dysfunction (one study), hypertension (two studies) and osteoarthritis (three studies). Due to small sample size, limited number of trials per condition, variation in outcomes evaluated and outcome measures used, as well as the risk of bias in the included studies, no definite conclusions regarding the efficacy and safety of Pycnogenol® are possible." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 11 RCTs in this review update (3352 participants older than 12 years with a diagnosis of CAP); 10 RCTs assessed nine antibiotic pairs (3321 participants) and one RCT assessed four antibiotics (31 participants) in people with CAP. The study quality was generally good, with some differences in the extent of the reporting. A variety of clinical, bacteriological and adverse events were reported. Overall, there was no significant difference in the efficacy of the various antibiotics. Studies evaluating clarithromycin and amoxicillin provided only descriptive data regarding the primary outcome. Though the majority of adverse events were similar between all antibiotics, nemonoxacin demonstrated higher gastrointestinal and nervous system adverse events when compared to levofloxacin, while cethromycin demonstrated significantly more nervous system side effects, especially dysgeusia, when compared to clarithromycin. Similarly, high-dose amoxicillin (1 g three times a day) was associated with higher incidence of gastritis and diarrhoea compared to clarithromycin, azithromycin and levofloxacin. Available evidence from recent RCTs is insufficient to make new evidence-based recommendations for the choice of antibiotic to be used for the treatment of CAP in outpatient settings. Pooling of study data was limited by the very low number of studies assessing the same antibiotic pairs. Individual study results do not reveal significant differences in efficacy between various antibiotics and antibiotic groups. However, two studies did find significantly more adverse events with use of cethromycin as compared to clarithromycin and nemonoxacin when compared to levofloxacin. Multi-drug comparisons using similar administration schedules are needed to provide the evidence necessary for practice recommendations. Further studies focusing on diagnosis, management, cost-effectiveness and misuse of antibiotics in CAP and LRTI are warranted in high-, middle- and low-income countries.\nOutput:\n" }, { "from": "agent", "value": "We identified 11 trials (with 3352 participants older than 12 years with a diagnosis of community-acquired pneumonia), fully published in peer-reviewed journals, focused on treatment of pneumonia in adolescents and adults treated in the community in outpatient settings. This included five new trials included since our last review published in 2009. None of the trials included antibiotics versus placebo; all trials included one or more antibiotics. All participants were diagnosed with pneumonia based upon clinical diagnosis by the physician and chest X-ray. All included trials were well conducted; nine of the 11 trials were sponsored by bio-pharmaceutical companies manufacturing the antibiotics used in the study, or their authors were closely linked with the company. Nine of the included trials compared different antibiotics and, hence, we could not combine the results of the individual trials to present our overall conclusion. There were some notable adverse events in seven studies: 1) erythromycin demonstrated significant gastrointestinal side effects compared to clarithromycin in two studies; 2) nemonoxacin demonstrated higher gastrointestinal (nausea, diarrhoea) and nervous system (dizziness, headache) adverse events compared to levofloxacin; 3) cethromycin demonstrated more side effects, especially a distortion of the sense of taste, than clarithromycin; 4) gastritis and diarrhoea were more common in the high-dose amoxicillin group (1 g three times a day) compared to the other three antibiotic groups (clarithromycin, azithromycin and levofloxacin). Unfortunately, there were not enough trials to compare the effects of different antibiotics for pneumonia acquired and treated in the community." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Eight trials, which included 1132 participants in total, met the inclusion criteria of this Cochrane review. These trials were at high risk of bias trials. One trial (which included five participants) did not contribute any data to this Cochrane review, and we excluded 13 participants in the remaining trials after randomisation; this left a total of 1114 participants, 510 randomised to non-surgical treatment and 604 to surgical treatment for analysis. The non-surgical treatment was definitive chemoradiotherapy in five trials and definitive radiotherapy in three trials. All participants were suitable for major surgery. Most of the data were from trials that compared chemoradiotherapy with surgery. There was no difference in long-term mortality between chemoradiotherapy and surgery (HR 0.88, 95% CI 0.76 to 1.03; 602 participants; four studies; low quality evidence). The long-term mortality was higher in radiotherapy than surgery (HR 1.39, 95% CI 1.18 to 1.64; 512 participants; three studies; very low quality evidence). There was no difference in long-term recurrence between non-surgical treatment and surgery (HR 0.96, 95% CI 0.80 to 1.16; 349 participants; two studies; low quality evidence). The difference between non-surgical and surgical treatments was imprecise for short-term mortality (RR 0.39, 95% CI 0.11 to 1.35; 689 participants; five studies; very low quality evidence), the proportion of participants with serious adverse in three months (RR 0.61, 95% CI 0.25 to 1.47; 80 participants; one study; very low quality evidence), and proportion of people with local recurrence at maximal follow-up (RR 0.89, 95% CI 0.70 to 1.12; 449 participants; three studies; very low quality evidence). The health-related quality of life was higher in non-surgical treatment between four weeks and three months after treatment (Spitzer Quality of Life Index; MD 0.93, 95% CI 0.24 to 1.62; 165 participants; one study; very low quality evidence). The difference between non-surgical and surgical treatments was imprecise for medium-term health-related quality of life (three months to two years after treatment) (Spitzer Quality of Life Index; MD −0.95, 95% CI −2.10 to 0.20; 62 participants; one study; very low quality of evidence). The proportion of people with dysphagia at the last follow-up visit prior to death was higher with definitive chemoradiotherapy compared to surgical treatment (RR 1.48, 95% CI 1.01 to 2.19; 139 participants; one study; very low quality evidence). Based on low quality evidence, chemoradiotherapy appears to be at least equivalent to surgery in terms of short-term and long-term survival in people with oesophageal cancer (squamous cell carcinoma type) who are fit for surgery and are responsive to induction chemoradiotherapy. However, there is uncertainty in the comparison of definitive chemoradiotherapy versus surgery for oesophageal cancer (adenocarcinoma type) and we cannot rule out significant benefits or harms of definitive chemoradiotherapy versus surgery. Based on very low quality evidence, the proportion of people with dysphagia at the last follow-up visit prior to death was higher with definitive chemoradiotherapy compared to surgery. Based on very low quality evidence, radiotherapy results in less long-term survival than surgery in people with oesophageal cancer who are fit for surgery. However, there is a risk of bias and random errors in these results, although the risk of bias in the studies included in this systematic review is likely to be lower than in non-randomised studies. Further trials at low risk of bias are necessary. Such trials need to compare endoscopic treatment with surgical treatment in early stage oesophageal cancer (carcinoma in situ and Stage Ia), and definitive chemoradiotherapy with surgical treatments in other stages of oesophageal cancer, and should measure and report patient-oriented outcomes. Early identification of responders to chemoradiotherapy and better second-line treatment for non-responders will also increase the need and acceptability of trials that compare definitive chemoradiotherapy with surgery.\nOutput:\n" }, { "from": "agent", "value": "Eight studies met the inclusion criteria of this Cochrane review, and seven studies provided information for the review. The non-surgical treatment was chemoradiotherapy only in five studies and radiotherapy only in three studies. We included a total of 1114 participants undergoing non-surgical treatment (510 participants) or surgical treatment (604 participants) in the various analysis in the seven studies that provided information. Methods similar to tossing a coin were used to decide whether a participant received non-surgical treatment or surgical treatment and ensure that the participants in the two groups were similar. Most trials included people who were healthy in aspects other than the condition requiring surgery. The evidence is current up to 4th March 2016. Most information was from trials that compared chemoradiotherapy with surgery. There was no difference in long-term deaths between chemoradiotherapy and surgery in people with oesophageal cancer who are fit for surgery. More people died in radiotherapy than surgery in people with oesophageal cancer who are fit for surgery in the long-term. There was no difference in long-term cancer recurrence between non-surgical treatment and surgery. The difference between non-surgical and surgical treatments were imprecise for short-term deaths, the percentage of participants with serious adverse in three months, and the percentage of participants who had recurrence of cancer in and around the food-pipe. The health-related quality of life (covering aspects such as activity, daily living, health, support of family and friends, and outlook) was higher in non-surgical treatment between four weeks and three months after treatment, although it is unclear what this difference means to the patient. The difference between non-surgical and surgical treatments were imprecise for medium-term health-related quality of life (three months to two years after treatment). Chemoradiotherapy only appears to be at least equivalent to surgery in terms of short-term and long-term survival in people with one type of oesophageal cancer called squamous cell cancer and who are fit for surgery. There is more uncertainty in the comparison of chemoradiotherapy only versus surgery for another type of oesophageal cancer called adenocarcinoma, and we cannot rule out significant benefits or harms of definitive chemoradiotherapy versus surgery in this type of oesophageal cancer. More people had difficulty in swallowing prior to their death after chemoradiotherapy treatment compared to surgical treatment. Radiotherapy only results in less long-term survival than surgery (about 40% increase risk of deaths). Further well-designed studies that measure outcomes that are important for patients are necessary. The quality of evidence was low or very low because the included studies were small and had errors in study design. As a result, there is a lot of uncertainty regarding the results." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included four randomised controlled trials (RCTs). We found evidence of missing data and poor reporting. When bifeprunox 20 mg was compared with placebo for schizophrenia, the drug resulted in a reduction of the Positive and Negative Syndrome Scale (PANSS) positive subscale score regarding positive symptoms (n = 549, 2 RCTs, MD -1.89, 95% CI -2.85 to -0.92, low-quality evidence) and the PANSS negative subscale regarding negative symptoms (n = 549, 2 RCTs, MD -1.53, 95% CI -2.37 to -0.69, low-quality evidence). There was a clear improvement regarding deterioration in the bifeprunox 20 mg group (n = 231, 1 RCT, RR 0.71 95% CI, 0.54 to 0.93, very low-quality evidence). The total number of participants with equal to or greater than 7% weight increase was similar between bifeprunox and placebo (n = 483, 1 RCT, RR 1.02 95% CI 0.31 to 3.33 moderate-quality evidence). There were no useable data for quality of life, economic outcomes, and service use. Our results showed some positive effects and a favourable adverse effect profile for bifeprunox, although there were few data overall and none were of high quality. It would seem that these data alone would not have been enough for the FDA to decide to halt progress of the drug to market. We can only assume that we are missing important data. Both the FDA and the relevant pharmaceutical companies have not made all relevant data accessible. As some of these trials also involved an additional haloperidol, olanzapine, quetiapine, or risperidone arm, these data are not only relevant to evaluation of bifeprunox. In not making all data accessible, it is hard to see how the FDA and the drug companies have fulfilled their full obligations to people with schizophrenia or their clinicians.\nOutput:\n" }, { "from": "agent", "value": "The Information Specialist of the Cochrane Schizophrenia Group searched the specialised register in October 2015. He ran an electronic search for trials that randomised people with schizophrenia to receive either bifeprunox or placebo, finding 42 records. The review authors screened these for inclusion in the review. Only four trials provided useable data, and these were of poor quality with some evidence of missing data. Two trials are completed but not yet published; we could not obtain any information from these trials that we could use in this review. The data available to us showed that bifeprunox improved participants' scores on both positive and negative symptom scales. Weight increase was similar between those receiving bifeprunox and those allocated to placebo. Data regarding the effects of bifeprunox are scarce. The data we found, which were of poor quality, showed no real evidence that bifeprunox is unsafe or ineffective. Its effects do not seem significantly different to other drugs that are currently on the market. More data on this compound exists but is not publicly available. We believe that the licencing authority in the USA must have had more information on which to base their important decision. The drug company also seemed to lose the will to move forward with bifeprunox. Whether or not the decision to prohibit access to a potentially useful drug was taken because of clear evidence of adverse effects, market calculations, or biases, it would seem an omission that all information upon which this decision was made is not in the public domain." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 22 studies with 1097 randomised participants. Twenty-one studies with 890 participants contributed data to meta-analyses. Participants in the studies had dementia of varying degrees of severity, and all were resident in institutions. Seven studies delivered an individual music intervention; the other studies delivered the intervention to groups of participants. Most interventions involved both active and receptive musical elements. The methodological quality of the studies varied. All were at high risk of performance bias and some were at high risk of detection or other bias. At the end of treatment, we found low-quality evidence that the interventions may improve emotional well-being and quality of life (standardised mean difference (SMD) 0.32, 95% confidence interval (CI) 0.02 to 0.62; 9 studies, 348 participants) and reduce anxiety (SMD –0.43, 95% CI –0.72 to –0.14; 13 studies, 478 participants). We found low-quality evidence that music-based therapeutic interventions may have little or no effect on cognition (SMD 0.15, 95% CI –0.06 to 0.36; 7 studies, 350 participants). There was moderate-quality evidence that the interventions reduce depressive symptoms (SMD –0.27, 95% CI –0.45 to –0.09; 11 studies, 503 participants) and overall behaviour problems (SMD –0.23, 95% CI –0.46 to –0.01; 10 studies, 442 participants), but do not decrease agitation or aggression (SMD –0.07, 95% CI –0.24 to 0.10; 14 studies, 626 participants). The quality of the evidence on social behaviour was very low, so effects were very uncertain. The evidence for long-term outcomes measured four or more weeks after the end of treatment was of very low quality for anxiety and social behaviour, and for the other outcomes, it was of low quality for little or no effect (with small SMDs, between 0.03 and 0.34). Providing people with dementia who are in institutional care with at least five sessions of a music-based therapeutic intervention probably reduces depressive symptoms and improves overall behavioural problems at the end of treatment. It may also improve emotional well-being and quality of life and reduce anxiety, but may have little or no effect on agitation or aggression or on cognition. We are uncertain about effects on social behaviour and about long-term effects. Future studies should examine the duration of effects in relation to the overall duration of treatment and the number of sessions.\nOutput:\n" }, { "from": "agent", "value": "We found 22 trials to include in the review and we were able to combine results for at least some outcomes from 890 people. All of the people in the trials stayed in nursing homes or hospitals. Some trials compared music-based treatments with usual care, and some compared them with other activities, such as cooking or painting. The quality of the trials and how well they were reported varied, and this affected our confidence in the results. First, we looked at outcomes immediately after a course of therapy ended. From our results, we could be moderately confident that music-based treatments improve symptoms of depression and overall behavioural problems, but not specifically agitated or aggressive behaviour. They may also improve anxiety and emotional well-being including quality of life, although we were less confident about these results. They may have little or no effect on cognition. We had very little confidence in our results on social interaction. Some studies also looked to see whether there were any lasting effects four weeks or more after treatment ended. However, there were few data and we were uncertain or very uncertain about the results. Further trials are likely to have a significant impact on what we know about the effects of music-based treatments for people with dementia, so continuing research is important." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Two trials met the inclusion criteria. Both trials commenced prior to the widespread availability of prostate-specific antigen (PSA) screening; hence the results may not be applicable to men with PSA-detected disease. One trial (N = 142), conducted in the US, was judged to be of poor quality. All cause (overall) mortality was not significantly different between RP and WW groups after fifteen years of follow up (Hazard Ratio (HR) 0.9 (95% Confidence Interval (CI) 0.56 to 1.43). The second trial (N = 695), conducted in Scandinavia, was judged to be of good quality. After 12 years of follow up, the trial results were compatible with a beneficial effect of RP on the risks of overall mortality, prostate cancer mortality and distant metastases compared with WW but the precise magnitude of the effect is uncertain as indicated by the width of the confidence intervals for all estimates (risk difference (RD) -7.1% (95% CI -14.7 to 0.5); RD -5.4% (95% CI -11.1 to 0.2); RD -6.7% (95% CI -13.2 to -0.2), respectively). Compared to WW, RP increased the absolute risks of erectile dysfunction (RD 35% (95% CI 25 to 45)) and urinary leakage (RD 27% (95% CI 17 to 37)). These estimates must be interpreted cautiously as they are derived from data obtained from a self-administered questionnaire survey of a sample of the trial participants (N = 326), no baseline quality of life data were obtained and nerve-sparing surgery was not routinely performed on trial participants undergoing RP. The existing trials provide insufficient evidence to allow confident statements to be made about the relative beneficial and harmful effects of RP and WW for patients with localised prostate cancer. The results of ongoing trials should help to inform treatment decisions for men with screen-detected localised prostate cancer.\nOutput:\n" }, { "from": "agent", "value": "Two completed randomised controlled trials were identified. One trial was considered to be of good quality whilst the second trial was of poor quality. The two trials commenced prior to the widespread use of the prostate-specific antigen (PSA) blood test as a screening test for prostate cancer, and hence did not involve many men with PSA-detected cancers. Ongoing trials (PIVOT; ProtecT; START) will provide evidence of the comparative effects of RP and observation protocols for men with PSA-detected cancers. The one good quality trial included in this review involved men with cancers detected by methods other than screening who were randomly allocated to either RP or WW and followed up for 12 years. This single trial does not provide sufficient evidence to allow confident statements to be made about the magnitude of any beneficial and harmful effects of RP compared with WW for men with clinically detected prostate cancers. The trial results indicate that RP is likely to reduce the risks of overall mortality, prostate-cancer mortality and distant metastases (cancer spread) compared to WW, but the magnitude of the effect is unclear. Furthermore, the risk reductions appear to have been limited to men less than 65 years of age. This trial also provides evidence that RP increases the risks of erectile dysfunction and urinary leakage. However, because of the manner in which the data on adverse effects were collected in the trial, confident statements cannot be made about how frequently these adverse effects occur. In addition, nerve-sparing surgery, which has the potential to reduce these complications, was not routinely performed on participants in the trial. A shared approach to decision-making is required whereby patients and their healthcare providers openly discuss the patient's personal values, preferences, and the limitations of the available evidence on potential benefits and potential harms of these treatment options." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Four studies evaluating rimonabant 20 mg versus rimonabant 5 mg versus placebo in addition to a hypocaloric diet lasting at least one year were included. Compared with placebo, rimonabant 20 mg produced a 4.9 kg greater reduction in body weight in trials with one-year results. Improvements in waist circumference, high-density lipoprotein cholesterol, triglyceride levels and systolic and diastolic blood pressure were also seen. However, the results with rimonabant 5 mg demonstrated a weight reduction which was only 1.3 kg greater when compared with placebo. No clinically relevant effects on plasma lipids and blood pressure were found. Rimonabant 20 mg caused significant more adverse effects both of general and serious nature, especially of nervous system, psychiatric or gastro-intestinal origin. Attrition rates were approximately 40% at the end of one year. The use of rimonabant after one year produces modest weight loss of approximately 5%. Even modest amounts of weight loss may be potentially beneficial. The observed results should be interpreted with some caution, though, since the evaluated studies presented some deficiencies in methodological quality. Studies with longer follow-ups after the end of treatment and of more rigorous quality should be done before definitive recommendations can be made regarding the role of this new medication in the management of overweight or obese patients.\nOutput:\n" }, { "from": "agent", "value": "Rimonabant is the first drug of a new class of medications that seems to reduce body weight and improve risk factors for diseases of the blood vessels and heart in people who are overweight or obese. We found four studies which evaluated weight loss, occurrence of disorders and adverse effects of treatment. The four studies involved 6625 people comparing rimonabant 20 mg with rimonabant 5 mg and placebo, in combination with a hypocaloric diet after one or two years of treatment. Greater weight loss and improvement in risk factors were seen after 20 mg of rimonabant. These results have to be interpreted with caution though, due to high discontinuation rates of study participants and the overall low quality of the included studies. We conclude that: 1. average weight loss with rimonabant appears modest, and 2. more rigorous studies examining the efficacy and safety of rimonabant are required to fully evaluate the benefit risk ratio of this new drug. In Europe, rimonabant is contraindicated for patients with severe depression and/or patients who are treated with antidepressive medications. Rimonabant is furthermore not recommended for patients with other untreated psychiatric conditions." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 50 studies with a total of 3704 participants. Forty studies (81%) were at high risk of bias, nine (18%) were at unclear risk of bias, with just one assessed as at low risk of bias. There were 34 different sedatives used with or without inhalational nitrous oxide. Dosages, mode of administration and time of administration varied widely. Studies were grouped into placebo-controlled, dosage and head-to-head comparisons. Meta-analysis of the available data for the primary outcome (behaviour) was possible for studies investigating oral midazolam versus placebo only. There is moderate-certainty evidence from six small clinically heterogeneous studies at high or unclear risk of bias, that the use of oral midazolam in doses between 0.25 mg/kg to 1 mg/kg is associated with more co-operative behaviour compared to placebo; standardized mean difference (SMD) favoured midazolam (SMD 1.96, 95% confidence interval (CI) 1.59 to 2.33, P < 0.0001, I2 = 90%; 6 studies; 202 participants). It was not possible to draw conclusions regarding the secondary outcomes due to inconsistent or inadequate reporting or both. There is some moderate-certainty evidence that oral midazolam is an effective sedative agent for children undergoing dental treatment. There is a need for further well-designed and well-reported clinical trials to evaluate other potential sedation agents. Further recommendations for future research are described and it is suggested that future trials evaluate experimental regimens in comparison with oral midazolam or inhaled nitrous oxide.\nOutput:\n" }, { "from": "agent", "value": "Authors from Cochrane Oral Health carried out this review and the evidence is up to date to 22 February 2018. A total of 50 randomised controlled trials were included with a total of 3704 participants. Within these studies 34 different sedatives were used, often with inhalational nitrous oxide as well. Dosages and delivery of these drugs varied widely. We grouped studies into those where drugs were compared to a placebo, where drugs were compared to other drugs or where different dosages of drugs were compared. Because all the studies were so different we could only carry out a meta-analysis for studies comparing oral midazolam to a placebo. The review showed that use of oral midazolam made patients more co-operative for dental treatment than a placebo drug. Where reported, adverse effects were few and minor. Oral midazolam probably improves behaviour of children during dental treatment. We evaluated other sedatives but there is insufficient evidence to draw any conclusions. There is some moderate-certainty evidence that midazolam administered in a drink of juice is effective." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Fifteen trials were included, six of which were added in this update. Three trials of a nursing intervention to manage breathlessness showed benefit in terms of symptom experience, performance status and emotional functioning. Four trials assessed structured nursing programmes and found positive effects on delay in clinical deterioration, dependency and symptom distress, and improvements in emotional functioning and satisfaction with care. Three trials assessed the effect of different psychotherapeutic, psychosocial and educational interventions in patients with lung cancer. One trial assessing counselling showed benefit for some emotional components of the illness but findings were not conclusive. One trial examined the effects of coaching sensory self monitoring and reporting on pain-related variables and found that although coaching increases the amount of pain data communicated to providers by patients with lung cancer, the magnitude of the effect is small and does not lead to improved efficacy of analgesics prescribed for each patient’s pain level. One trial compared telephone-based sessions of either caregiver-assisted coping skills training (CST) or education/support involving the caregiver and found that patients in both treatment conditions showed improvements in pain, depression, quality of life and self efficacy. Two trials assessed exercise programmes; one found a beneficial effect on self empowerment and the other study showed an increase in quadriceps strength but no significant changes for any measure of quality of life. One trial of nutritional interventions found positive effects for increasing energy intake, but no improvement in quality of life. Two small trials of reflexology showed some positive but short-lasting effects on anxiety and pain intensity. The main limitations of the studies included were the variability of the interventions assessed and the approaches to measuring the considered outcomes, and the lack of data reported in the trials regarding allocation of patients to treatment groups and blinding. Nurse follow-up programmes and interventions to manage breathlessness may produce beneficial effects. Counselling may help patients cope more effectively with emotional symptoms, but the evidence is not conclusive. Other psychotherapeutic, psychosocial and educational interventions can play some role in improving patients' quality of life. Exercise programmes and nutritional interventions have not shown relevant and lasting improvements of quality of life. Reflexology may have some beneficial effects in the short term.\nOutput:\n" }, { "from": "agent", "value": "This review found that nursing programmes and interventions to manage breathlessness may produce beneficial effects and that some psychotherapeutic, psychosocial and educational interventions can play some role in improving the quality of life of patients. Counselling may help patients to cope better with emotional symptoms and reflexology can have some short-term beneficial effects. The main limitations of the included studies were the variability of the interventions, the way results were measured and the lack of 'blinding' (ensuring that those who are measuring the patients' outcomes are not aware of which treatment the patient actually received)." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 24 studies that involved a total of 1787 participants. Studies reported on various types of acupuncture and related interventions including manual acupuncture and acupressure, ear acupressure, transcutaneous electrical acupuncture point stimulation, far-infrared radiation on acupuncture points and indirect moxibustion. CKD stages included pre-dialysis stage 3 or 4 and end-stage kidney disease on either haemodialysis or peritoneal dialysis. None of the included studies assessed pain outcomes, nor formally addressed occurrence of serious adverse events, although three studies reported three participant deaths and three hospitalisations as reasons for attrition. Three studies reported minor acupuncture-related harms; the remainder did not report if those events occurred. All studies were assessed at high or unclear risk of bias in terms of allocation concealment. Seventeen studies reported outcomes measured for only two months. There was very low quality of evidence that compared with routine care, manual acupressure reduced scores of the Beck Depression Inventory score (scale from 0 to 63) (3 studies, 128 participants: MD -4.29, 95% CI -7.48 to -1.11, I2 = 0%), the revised Piper Fatigue Scale (scale from 0 to 10) (3 studies, 128 participants: MD -1.19, 95% CI -1.77 to -0.60, I2 = 0%), and the Pittsburgh Sleep Quality Index (scale from 0 to 21) (4 studies, 180 participants: MD -2.46, 95% CI -4.23 to -0.69, I2 = 50%). We were unable to perform further meta-analyses because of the paucity of data and problems with clinical heterogeneity, such as different interventions, comparisons and timing of outcome measurements. There was very low quality of evidence of the short-term effects of manual acupressure as an adjuvant intervention for fatigue, depression, sleep disturbance and uraemic pruritus in patients undergoing regular haemodialysis. The paucity of evidence indicates that there is little evidence of the effects of other types of acupuncture for other outcomes, including pain, in patients with other stages of CKD. Overall high or unclear risk of bias distorts the validity of the reported benefit of acupuncture and makes the estimated effects uncertain. The incomplete reporting of acupuncture-related harm does not permit us to assess the safety of acupuncture and related interventions. Future studies should investigate the effects and safety of acupuncture for pain and other common symptoms in patients with CKD and those undergoing dialysis.\nOutput:\n" }, { "from": "agent", "value": "We searched the literature up to January 2016 and analysed 24 studies that involved 1787 participants. Of these, only seven studies provided data that could be combined for analysis. The studies reported that manual acupressure improved fatigue, depression and sleep disturbance when used as an adjunct to routine care for patients undergoing maintenance haemodialysis 4 weeks from baseline. No study assessed pain and most did not report whether adverse events of acupuncture occurred. Overall, we found very low quality evidence about the effectiveness of acupuncture for symptoms of CKD. Manual acupressure combined with routine care may provide short-term symptom relief from depressive mood, fatigue and sleep disturbance in patients undergoing haemodialysis. Findings from this review cannot support the benefits of other acupuncture techniques for patients with CKD because there were too few reliable studies. Pain is a common condition in patients with CKD. Thus, the potential role of acupuncture for pain control in patients with CKD deserves further research. Clinicians should carefully monitor the safety of acupuncture in patients with CKD unless sound evidence supports the safety of these interventions for CKD patients. All studies were assessed at high or unclear risk of bias, especially in terms of selection of participants and selective outcome reporting, which made the validity of their results doubtful." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Four trials (involving a total of 269 participants) were included. The participants were children with cystic fibrosis and their parents or caregivers in three trials and adults with cystic fibrosis in one trial. The trials compared four different self-management education interventions versus standard treatment: (1) a training programme for managing cystic fibrosis in general; (2) education specific to aerosol and airway clearance treatments; (3) disease-specific nutrition education; and (4) general and disease-specific nutrition education. Training children to manage cystic fibrosis in general had no statistically significant effects on weight after six to eight weeks, mean difference -7.74 lb (i.e. 3.51 kg) (95% confidence interval -35.18 to 19.70). General and disease-specific nutrition education for adults had no statistically significant effects on: pulmonary function (forced expiratory volume at one second), mean difference -5.00 % (95% confidence interval -18.10 to 8.10) at six months and mean difference -5.50 % (95% confidence interval -18.46 to 7.46) at 12 months; or weight, mean difference - 0.70 kg (95% confidence interval -6.58 to 5.18) at six months and mean difference -0.70 kg (95% confidence interval -6.62 to 5.22) at 12 months; or dietary fat intake scores, mean difference 1.60 (85% confidence interval -2.90 to 6.10) at six months and mean difference 0.20 (95% confidence interval -4.08 to 4.48) at 12 months. There is some limited evidence to suggest that self-management education may improve knowledge in patients with cystic fibrosis but not in parents or caregivers. There is also some limited evidence to suggest that self-management education may result in positively changing a small number of behaviours in both patients and caregivers. The available evidence from this review is of insufficient quantity and quality to draw any firm conclusions about the effects of self-management education for cystic fibrosis. Further trials are needed to investigate the effects of self-management education on a range of clinical and behavioural outcomes in children, adolescents and adults with cystic fibrosis and their caregivers.\nOutput:\n" }, { "from": "agent", "value": "We set out to review the effects of self-management education for cystic fibrosis on a range of health outcomes in individuals of all ages with cystic fibrosis and their caregivers. Our search for available evidence identified four trials, and all four compared a form of self-management education to standard treatment. The precise focus of self management differed between trials and included a training programme for managing cystic fibrosis, education on chest treatments, education on nutrition specific to cystic fibrosis, and education on general and disease-specific nutrition. Self-management education had no positive effects on lung function, weight, or intake of fatty food. There is some evidence to suggest that self-management education improves knowledge about cystic fibrosis and its management in patients with this condition and some self-management behaviours in patients and caregivers. However, due to the small number of trials in this review, and because of concerns about the quality of these trials, we are unable to reach any firm conclusions about the effects of self-management education for cystic fibrosis. We recommend that further trials are conducted to evaluate the effects of self-management education interventions." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Only one trial of limited quality compared a biphasic and monophasic preparation. The study examined 533 user cycles of a biphasic pill (500 μg norethindrone plus 35 μg ethinyl estradiol (EE) for 10 days, followed by 1000 μg norethindrone plus 35 μg EE for 11 days; Ortho 10/11) and 481 user cycles of a monophasic contraceptive pill (1500 μg norethindrone acetate plus 30 μg EE daily; Loestrin). The study found no significant differences in intermenstrual bleeding, amenorrhea and study discontinuation due to intermenstrual bleeding between the biphasic and monophasic oral contraceptive pills. Conclusions are limited by the identification of only one trial, the methodological shortcomings of that trial, and the absence of data on accidental pregnancies. However, the trial found no important differences in bleeding patterns between the biphasic and monophasic preparations studied. Since no clear rationale exists for biphasic pills and since extensive evidence is available for monophasic pills, the latter are preferred.\nOutput:\n" }, { "from": "agent", "value": "We did a computer search for studies of birth control pills with two phases versus pills with one phase. We also wrote to researchers and manufacturers to find other trials. We included randomized trials in any language. We found only one trial that looked at one-phase versus two-phase birth control pills. The study authors did not report all their methods. Many of the women dropped out of the trial, and the authors did not give the reasons. The pills did not differ in any major ways, including bleeding patterns and the numbers of women who stopped using the pills. This review did not find enough evidence to say if two-phase pills worked any better than one-phase types for birth control, bleeding patterns, or staying on the pill. The one trial report had method problems and lacked data on pregnancies. Therefore, one-phase pills are the better choice, since we have much more evidence for such pills and two-phase pills have no clear reason for use." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Two studies with a combined total of 288 participants met the inclusion criteria for this review. One study compared low molecular weight heparin with unfractionated heparin and found no difference between the treatments in the prevention of DVT (odds ratio (OR) 1.23, 95% confidence interval (CI) 0.28 to 5.35). No bleeding events or deaths occurred. This study was open label and therefore at a high risk of performance bias. Additionally, the method of randomisation was not reported and therefore the risk of selection bias was unclear. In the second study heparin did not significantly improve prevention of pulmonary embolism (OR 1.02, 95% CI 0.44 to 2.37) when compared to placebo. Furthermore, when the level of amputation was considered, the incidence of pulmonary embolism was similar between the two treatment groups: above knee amputation (OR 0.79, 95% CI 0.31 to 1.97) and below knee amputation (OR 1.53, 95% CI 0.09 to 26.43). Ten participants died during the study; five underwent a post-mortem and three were found to have had a recent pulmonary embolism, all of whom had been on placebo. Bleeding events were reported in less than 10% of participants in both treatment groups but specific data were not presented. This study did not report the methods used to conceal allocation of treatment and therefore it was unclear if selection bias occurred. However, this study appeared to be free from all other sources of bias. No study looked at mechanical prophylaxis. As only two studies were included in this review, each comparing different interventions, there is insufficient evidence to make any conclusions regarding the most effective thromboprophylaxis regimen in patients undergoing lower limb amputation. Further large-scale studies that are of good quality are required.\nOutput:\n" }, { "from": "agent", "value": "After searching for relevant studies, we found two studies with a combined total of 288 participants to be included in this review of evidence. One study compared two forms of the anticoagulant heparin. Low molecular weight heparin offered no significant improvement over unfractionated heparin in the prevention of DVT. Furthermore neither drug caused bleeding. However, in this study both the participants and study personnel were aware of which treatment was being administered. This may have biased the results. It is unclear if other bias was introduced in the study because the process of randomly allocating treatment was not adequately described. The second study concluded that heparin was not more effective in preventing a PE than placebo whether the amputation was above or below the knee. Bleeding occurred in less than 10% of each treatment group but the study authors did not report specific numbers and therefore this could not be analysed. This study did not report the methods used to conceal how treatment was allocated but it was judged to be free from other sources of bias. This review found that there are too few trials to determine the most effective strategy in preventing VTE in people undergoing amputation of the lower limb. No study looked at mechanical forms of preventing VTE, such as compression devices, and therefore it is not possible to make any conclusions about these. Further good quality and large-scale studies are required." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: A total of 59 studies, mostly of low quality, were included in the review, involving multiple treatment comparisons between sertraline and other antidepressant agents. Evidence favouring sertraline over some other antidepressants for the acute phase treatment of major depression was found, either in terms of efficacy (fluoxetine) or acceptability/tolerability (amitriptyline, imipramine, paroxetine and mirtazapine). However, some differences favouring newer antidepressants in terms of efficacy (mirtazapine) and acceptability (bupropion) were also found. In terms of individual side effects, sertraline was generally associated with a higher rate of participants experiencing diarrhoea. This systematic review and meta-analysis highlighted a trend in favour of sertraline over other antidepressive agents both in terms of efficacy and acceptability, using 95% confidence intervals and a conservative approach, with a random effects analysis. However, the included studies did not report on all the outcomes that were pre-specified in the protocol of this review. Outcomes of clear relevance to patients and clinicians were not reported in any of the included studies.\nOutput:\n" }, { "from": "agent", "value": "In the present review we assessed the evidence for the efficacy, acceptability and tolerability of sertraline in comparison with all other antidepressants in the acute-phase treatment of major depression. Fifty-nine randomised controlled trials (about 10,000 participants) were included in the review. The review showed evidence of differences in efficacy, acceptability and tolerability between sertraline and other antidepressants, with meta-analyses highlighting a trend in favour of sertraline over other antidepressants, both in terms of efficacy and acceptability, in a homogeneous sample of clinical trials, using conservative statistical methods. The included studies did not report on all the outcomes that were pre-specified in the protocol of this review. Outcomes of clear relevance to patients and clinicians, in particular, patients and their carers' attitudes to treatment, their ability to return to work and resume normal social functioning, were not reported in the included studies. Nevertheless, based on currently available evidence, results from this review suggest that sertraline might be a strong candidate as the initial choice of antidepressant in people with acute major depression." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Two new trials reporting three comparisons were found in the update. Nineteen trials are included in the review, reporting 22 oral versus intra-vaginal anti-fungal comparisons. No statistically significant differences were shown between oral and intra-vaginal anti-fungal treatment for clinical cure at short term (OR 0.94, 95% CI, 0.75 to 1.17) and long term (OR 1.07, 95% CI, 0.82 to 1.41) follow-up. No statistically significant differences for mycological cure were observed between oral and intra-vaginal treatment at short term (OR 1.15, 95% CI, 0.94 to 1.42). There was a statistically significant difference for long term follow-up (OR 1.29, 95% CI, 1.05 to 1.60) in favour of oral treatment, however the clinical significance of this result is uncertain. Two trials each reported one withdrawal from treatment due to an adverse reaction. Treatment preference data were poorly reported. No statistically significant differences were observed in clinical cure rates of anti-fungals administered by the oral and intra-vaginal routes for the treatment of uncomplicated vaginal candidiasis. No definitive conclusion can be made regarding the relative safety of oral and intra-vaginal anti-fungals for uncomplicated vaginal candidiasis. The decision to prescribe or recommend the purchase of an anti-fungal for oral or intra-vaginal administration should take into consideration: safety, cost and treatment preference. Unless there is a previous history of adverse reaction to one route of administration or contraindications, women who are purchasing their own treatment should be given full information about the characteristics and costs of treatment to make their own decision. If health services are paying the treatment cost, decision-makers should consider whether the higher cost of some oral anti-fungals is worth the gain in convenience, if this is the patient's preference.\nOutput:\n" }, { "from": "agent", "value": "The primary objective of this review was to assess the relative effectiveness of oral versus intra-vaginal anti-fungals for the treatment of uncomplicated vulvovaginal candidiasis. The secondary objectives of the review were to assess the cost-effectiveness, safety and patient preference of oral versus intra-vaginal anti-fungals. No statistically significant differences were observed in clinical cure rates of anti-fungals administered by the oral and intra-vaginal routes for the treatment of uncomplicated vaginal candidiasis. No definitive conclusion can be made regarding the relative safety of oral and intra-vaginal anti-fungals for uncomplicated vaginal candidiasis. The decision to prescribe or recommend the purchase of an anti-fungal for oral or intra-vaginal administration should take into consideration: safety, cost and treatment preference. Unless there is a previous history of adverse reaction to one route of administration or contraindications, women who are purchasing their own treatment should be given full information about the characteristics and costs of treatment to make their own decision. If health services are paying the treatment cost, decision-makers should consider whether the higher cost of some oral anti-fungals is worth the gain in convenience, if this is the patient's preference." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Eleven studies met the criteria, providing 14 comparisons, and capturing data on 4317 participants. Seven studies were RCTs, three were cluster non-RCTs, and one was a randomised cross-over design. Seven studies were carried out among school children (N = 3636), three among women of reproductive age (N = 648), and one among infants (N = 33). The studies used diverse types of food as vehicle for iodine delivery: biscuits, milk, fish sauce, drinking water, yoghourt, fruit beverage, seasoning powder, and infant formula milk. Daily amounts of iodine provided ranged from 35 µg/day to 220 µg/day; trial duration ranged from 11 days to 48 weeks. Five studies examined the effect of iodine fortification alone, two against the same unfortified food, and three against no intervention. Six studies evaluated the effect of cofortification of iodine with other micronutrients versus the same food without iodine but with different levels of other micronutrients. We assessed one study to be at low risk of bias for all bias domains, three at low risk of bias for all domains apart from selective reporting, and seven at an overall rating of high risk of bias. No study assessed the primary outcomes of death, mental development, cognitive function, cretinism, or hypothyroidism, or secondary outcomes of TSH or serum thyroglobulin concentration. Two studies reported the effects on goitre, one on physical development measures, and one on adverse effects. All studies assessed urinary iodine concentration. The effects of iodine fortification compared to control on goitre prevalence (OR 1.60, 95% CI 0.60 to 4.31; 1 non-RCT, 83 participants; very low-quality evidence), and five physical development measures were uncertain (1 non-RCT, 83 participants; very low-quality evidence): weight (MD 0.23 kg, 95% CI -6.30 to 6.77); height (MD -0.66 cm, 95% CI -4.64 to 3.33); weight-for-age (MD 0.05, 95% CI -0.59 to 0.69); height-for-age (MD -0.30, 95% CI -0.75 to 0.15); and weight-for-height (MD -0.21, 95% CI -0.51 to 0.10). One study reported that there were no adverse events observed during the cross-over trial (low-quality evidence). Pooled results from RCTs showed that urinary iodine concentration significantly increased following iodine fortification (SMD 0.59, 95% CI 0.37 to 0.81; 6 RCTs, 2032 participants; moderate-quality evidence). This is equivalent to an increase of 38.32 µg/L (95% CI 24.03 to 52.61 µg/L). This effect was not observed in the meta-analysis of non-RCTs (SMD 0.25, 95% CI -0.16 to 0.66; 3 non-RCTs, 262 participants; very low-quality evidence). Sensitivity analyses did not change the effect observed in the primary analyses. The evidence on the effect of iodine fortification of foods, beverages, condiments, or seasonings other than salt on reducing goitre, improving physical development measures, and any adverse effects is uncertain. However, our findings suggest that the intervention likely increases urinary iodine concentration. Additional, adequately powered, high-quality studies on the effects of iodine fortification of foods on these, and other important outcomes, as well as its efficacy and safety, are required.\nOutput:\n" }, { "from": "agent", "value": "We searched for articles from different sources including published research papers, unpublished reports, and through direct communication with experts and organisations working to address iodine and micronutrient deficiency. We last searched the databases in January 2018. Eleven studies, which captured data on 4317 participants (3636 children, 648 women of reproductive age, and 33 infants), met our inclusion criteria. The type of foods used as vehicle to deliver iodine differed between the studies, and included biscuits, milk, fish sauce, drinking water, yoghourt, fruit beverage, seasoning powder, and infant formula milk. The amount of iodine provided to participants ranged from 35 µg/day to 220 µg/day, and study duration ranged from 11 days to 48 weeks. Of the 11 studies included, five examined the effect of adding iodine alone to foods compared to either no intervention or the same foods without iodine; while six evaluated the effect of adding iodine plus other micronutrients to foods compared to the same foods without iodine, but with different levels of other micronutrients. No study evaluated the effect of adding iodine to foods on death, mental development, cognitive function, cretinism (a condition characterized by impaired control of physical movement and intellectual disability), hypothyroidism (underactive thyroid), thyroid-stimulating hormone concentration, or serum thyroglobulin concentration (these are biological markers that indicate the presence of iodine deficiency when concentration in the blood is high). Two studies reported on the effect of the intervention on goitre, one study assessed five physical development measures (weight, height, weight-for-age, height-for-age, and weight-for-height scores), and one examined adverse effects. All studies assessed urinary iodine concentration (the concentration of iodine secreted in the urine, which indicates the presence of iodine deficiency when concentration is low in a population group, rather than in an individual). We combined the data that met our requirements in these studies in a meta-analysis. We are uncertain of the effects of iodine fortification on the proportion of participants with goitre, or on any of the five physical development measures. One study reported narratively that no adverse effects were observed during the trial. We found a significant increase of 38.32 µg/L in urinary iodine concentration after adding iodine to foods, compared to the groups that did not have iodine added, from studies of higher quality. Using GRADE, we rated the quality of the evidence as very low for goitre and physical development measures, due to study limitations (risk of bias) and imprecise results, and low for adverse events due to indirectness and imprecise results. We rated the quality of the evidence for urinary iodine concentration, from studies in which participants were allocated to treatment groups at random (gold standard design for clinical research), as moderate. On the other hand, quality of the evidence for urinary iodine concentration from studies without this random element was rated as very low, due to study limitations and imprecise results. Overall, there is no clear evidence on the effect of the intervention on reducing the proportion of people with goitre, improving physical growth, or adverse events. However, our results show that adding iodine to foods likely increases urinary iodine concentration. Additional studies to better quantify the effect of the intervention on these outcomes, as well as other outcomes, are needed." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: We included 25 trials with 2505 participants randomised to the different pharmacological agents and inactive controls. All the trials were at unclear risk of bias. Most trials included only low anaesthetic risk people undergoing elective laparoscopic cholecystectomy. Participants were allowed to take additional analgesics as required in 24 of the trials. The pharmacological interventions in all the included trials were aimed at preventing pain after laparoscopic cholecystectomy. There were considerable differences in the pharmacological agents used and the methods of administration. The estimated effects of the intervention on the proportion of participants who were discharged as day-surgery, the length of hospital stay, or the time taken to return to work were imprecise in all the comparisons in which these outcomes were reported (very low quality evidence). There was no mortality in any of the groups in the two trials that reported mortality (183 participants, very low quality evidence). Differences in serious morbidity outcomes between the groups were imprecise across all the comparisons (very low quality evidence). None of the trials reported patient quality of life or time taken to return to normal activity. The pain at 4 to 8 hours was generally reduced by about 1 to 2 cm on the visual analogue scale of 1 to 10 cm in the comparisons involving the different pharmacological agents and inactive controls (low or very low quality evidence). The pain at 9 to 24 hours was generally reduced by about 0.5 cm (a modest reduction) on the visual analogue scale of 1 to 10 cm in the comparisons involving the different pharmacological agents and inactive controls (low or very low quality evidence). There is evidence of very low quality that different pharmacological agents including non-steroidal anti-inflammatory drugs, opioid analgesics, and anticonvulsant analgesics reduce pain scores in people at low anaesthetic risk undergoing elective laparoscopic cholecystectomy. However, the decision to use these drugs has to weigh the clinically small reduction in pain against uncertain evidence of serious adverse events associated with many of these agents. Further randomised clinical trials of low risk of systematic and random errors are necessary. Such trials should include important clinical outcomes such as quality of life and time to return to work in their assessment.\nOutput:\n" }, { "from": "agent", "value": "We identified 25 randomised clinical trials involving 2505 people undergoing laparoscopic cholecystectomy. Most participants in the trials were low anaesthetic risk people undergoing planned laparoscopic cholecystectomy. The choice of whether the participants received the different painkillers (or not) was determined by a method similar to the toss of coin so that the treatments compared were conducted in people who were as similar as possible. The treatments in all the included trials were aimed at decreasing the pain after laparoscopic cholecystectomy before the participants reported pain. Participants were allowed to take additional painkillers as required in most of the trials. There were no deaths in either group in three trials (183 participants) that reported deaths. The differences in the serious complications between the groups was imprecise in all the comparisons. None of the trials reported quality of life or the time taken to return to normal activity. The differences in length of hospital stay and the time taken to return to work was imprecise in all the comparisons that reported these. Pain was lower in the participants who received painkillers compared with those who received controls at 4 to 8 hours and at 9 to 24 hours as measured by the visual analogue scale (a chart that rates the amount of pain on a scale of 1 to 10). This is a modest reduction and is comparable to other methods of pain reduction such as administering local anaesthetics (drugs that numb part of the body, similar to the ones used by the dentist to prevent the people from feeling pain) during the operation. In summary, different painkillers reduce pain scores in low anaesthetic risk people undergoing elective laparoscopic cholecystectomy. However, the decision to use these drugs has to weigh the clinically small reduction in pain against uncertain evidence of serious adverse events associated with many of these agents. The overall quality of evidence was very low. Further trials are necessary. Such trials should include outcomes such as quality of life, the time taken to return to normal activity, and the time taken to return to work, which are important for the person undergoing laparoscopic cholecystectomy and the people who provide funds for the treatment." } ]

[ { "from": "human", "value": "***TASK***\nthe task is to simplify the input abstract of a biomedical literature\n\n***INPUT***\nthe input is the abstract of a biomedical literature\n\n***OUTPUT***\nthe output is the simplified abstract for the input abstract of a biomedical literature\n\n***DOCUMENTATION***\n\n***EXAMPLES***\n\nInput: Nine randomised clinical trials with 879 participants fulfilled our inclusion criteria. All trials were at high risk of bias, and we rated the evidence as low to very low quality. All of the included trials compared combined external beam radiotherapy plus chemoembolisation versus chemoembolisation alone in people with unresectable hepatocellular carcinoma; moreover, three of the trials compared external beam radiotherapy alone versus chemoembolisation alone. All trials were conducted in China. The median age in most of the included trials was around 52 years, and most trial participants were male. The median follow-up duration ranged from one to three years. None of the trials reported data on cancer-related mortality, quality of life, serious adverse events, or time to progression of the tumour. For the comparison of radiotherapy plus chemoembolisation versus chemoembolisation alone, the risk ratio for one-year all-cause mortality was 0.51 (95% confidence interval (CI) 0.41 to 0.62; P < 0.001; 9 trials; low-quality evidence); for complete response rate was 2.14 (95% CI 1.47 to 3.13; P < 0.001; 7 trials; low-quality evidence); and for overall response rate defined as complete response plus partial response was 1.58 (95% CI 1.40 to 1.78; P < 0.001; 7 trials; low-quality evidence), all in favour of combined treatment with external beam radiotherapy plus transarterial chemoembolisation and seemingly supported by our Trial Sequential Analysis. Additionally, the combined treatment was associated with a higher risk of elevated total bilirubin and elevated alanine aminotransferase. The risk ratio for the risk of elevated alanine aminotransferase was 1.41 (95% CI 1.08 to 1.84; P = 0.01; very low-quality evidence), while for elevated total bilirubin it was 2.69 (95% CI 1.34 to 5.40; P = 0.005; very low-quality evidence). For the comparison of radiotherapy versus chemoembolisation, the risk ratio for one-year all-cause mortality was 1.21 (95% CI 0.97 to 1.50; 3 trials; I2 = 0%; very low-quality evidence) which was not supported by our Trial Sequential Analysis. In addition, we found seven ongoing randomised clinical trials evaluating different external beam radiotherapy techniques for people with unresectable hepatocellular carcinoma. We found very low- and low-quality evidence suggesting that combined external beam radiotherapy and chemoembolisation may be associated with lower mortality and increased complete and overall response rates, despite an increased toxicity as expressed by a higher rise of bilirubin and alanine aminotransferase. A high risk of systematic errors (bias) as well as imprecision and inconsistency suggest that these findings should be considered cautiously and that high-quality trials are needed to assess further the role of external beam radiotherapy for unresectable hepatocellular carcinoma.\nOutput:\n" }, { "from": "agent", "value": "We searched the medical literature for randomised clinical trials (where people are allocated at random to one of two or more treatment groups) in order to perform an analysis of the role of radiotherapy administered externally for advanced liver cancer. We found nine randomised clinical trials including a total of 879 people with advanced liver cancer. All of the included trials were conducted in China. The average age in most of the included studies was around 52 years, and most trial participants were male. The average follow-up duration ranged from one to three years. All trials were at high risk of bias, and we rated the evidence as low to very low quality. Most of the included trials compared combined radiotherapy and chemoembolisation versus chemoembolisation alone. We also identified seven ongoing randomised clinical trials. The evidence is current to October 2016. When compared with chemoembolisation alone, combined radiotherapy plus chemoembolisation may be associated with fewer deaths and more tumour size reduction, despite being associated with an increased risk for non-life-threatening adverse effects such as a higher rise of bilirubin and alanine aminotransferase. Combined radiotherapy and chemoembolisation may be associated with fewer deaths and increased overall response, but also an increased risk of adverse effects, when compared with chemoembolisation alone. The low quality of evidence suggests that these results should be considered cautiously and that high-quality randomised trials should be performed to assess further the role of external beam radiotherapy for unresectable hepatocellular carcinoma." } ]