README.md

metadata

title: AI Clinical Notes
emoji: 🦀
colorFrom: yellow
colorTo: yellow
sdk: streamlit
sdk_version: 1.42.0
app_file: app.py
pinned: false

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

AI Clinical Notes

Created by Dr. Fernando Ly

Description

This application helps medical professionals automatically generate clinical notes from doctor-patient conversations. It uses:

• Whisper for speech-to-text transcription
• Mixtral-8x7B for clinical note generation
• Streamlit for the user interface

Features

• Real-time audio recording
• Automatic speech transcription
• AI-powered clinical note generation
• Clean and intuitive interface

Setup

System Dependencies

First, install the required system dependencies:

For Ubuntu/Debian:

sudo apt-get update
sudo apt-get install portaudio19-dev python3-pyaudio libasound2-dev

For other systems, check the PortAudio documentation for installation instructions.

Python Dependencies

1. Install the required Python dependencies:

pip install -r requirements.txt

2. Make sure you have a .env file with your Huggingface API token:

HUGGINGFACE_TOKEN=your_token_here

3. Run the application:

streamlit run app.py

Usage

1. Open the application in your web browser
2. Set the desired recording duration using the slider
3. Click "Start Recording" to begin capturing the conversation
4. Wait for the transcription and clinical notes to be generated
5. Review and verify the generated notes

Important Notes

• This is an AI-assisted tool. Always review and verify the generated notes
• Ensure you have proper consent before recording conversations
• Keep patient privacy and HIPAA compliance in mind when using this tool

License

This project is licensed under the MIT License.