Skip to content

AI-powered app that transcribes medical consultations, extracts clinical insights, and generates detailed assessments and prescriptions.

Notifications You must be signed in to change notification settings

jash0803/echo-med

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ECHO-MED: Enhanced Clinical Hearing & Observation – Medical Evaluation & Documentation

ECHO-MED is an innovative Streamlit web app that leverages AI to:

  • Transcribe medical consultations (via audio upload or direct recording)
  • Extract key patient information
  • Generate comprehensive clinical assessments
  • Create precise, downloadable prescriptions

Features

  • Audio Input: Upload or record audio for doctor-patient consultations
  • PDF Upload: Add past medical records for richer context
  • AI Transcription: Uses OpenAI Whisper for accurate transcription
  • Clinical Assessment: Extracts chief complaints, patient data, history, differential diagnosis, and summary
  • Prescription Generator: Produces a structured prescription and downloadable PDF

Setup

  1. Clone the repository:
    git clone <your-repo-url>
    cd <your-repo-directory>
  2. Install dependencies:
    pip install -r requirements.txt
  3. Set up OpenAI API Key:
    • Create a .env file in the project root:
      OPENAI_API_KEY=your_openai_api_key_here
      

Usage

Run the app with:

streamlit run app.py
  • Use the sidebar to navigate between About, Clinical Assessment, and Prescription Generator.
  • Upload or record audio as prompted.
  • Optionally upload past medical records (PDF) for clinical assessment.
  • Download generated prescriptions as PDF.

Requirements

  • Python 3.8+
  • See requirements.txt for all dependencies.

License

MIT

About

AI-powered app that transcribes medical consultations, extracts clinical insights, and generates detailed assessments and prescriptions.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages