MedEase: AI-Assisted Diagnostic Workflow

Made by Cheng-Yuan Li, David Gu, Amisha Sao, Ritwic Verma for HackGT XI

Description

MedEase: AI-Assisted Diagnostic Workflow is an innovative platform designed to streamline the workflow of emergency department physicians by reducing the time spent on data entry and increasing the focus on patient care. The website utilizes Retrieval-Augmented Generation Large Language Models (RAG-LLMs) integrated with medical databases to take patient medical data and generate a differential diagnosis.

By automating note-taking and reducing the number of manual entries required, MedEase enables physicians to quickly fill out relevant entry forms using the AI-generated outputs. This enhanced efficiency allows doctors to spend more time in direct patient care, potentially increasing hospital revenue while improving patient outcomes.

Table of Contents

1. Frontend
2. Backend
3. Dependencies
4. Installation
5. Usage
6. Downloading shadcn/ui files
7. Contributing
8. License

Project Structure

EMR-Automatic/
├── backend/
│   ├── main.py
│   └── ... (other backend files)
├── frontend/
│   ├── src/
│   │   ├── srcForDashboard/
│   │   │   ├── pdf-upload.tsx
│   │   │   └── ... (other dashboard source files)
│   │   ├── styles/
│   │   │   ├── global.css
│   │   │   └── ... (other style files)
│   │   └── ... (other frontend source files)
│   ├── dashboard.astro
│   └── ... (other frontend files)
└── README.md

Key Files

backend/main.py:

The main backend file that sets up the Flask application, handles HTTP requests, and connects to the MongoDB database.

frontend/src/srcForDashboard/pdf-upload.tsx:

A React component for uploading PDFs and selecting templates. It includes functionality for handling file uploads and displaying a list of templates.

frontend/src/styles/global.css:

The global CSS file that contains styles applied across the entire frontend application.

frontend/dashboard.astro:

The main dashboard file written in Astro. It sets up the HTML structure, imports necessary components and icons, and includes the navigation bar and sidebar for the dashboard.

Dependencies

Frontend

• React
• Next.js
• lucide-react

Backend

• Flask
• Flask-CORS
• PyMongo
• Werkzeug

Installation

Backend (Flask)

1. Clone the repository.

   git clone https://github.com/your-repository-name.git

2. Navigate to the backend directory and set up a virtual environment:

   cd backend
   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`

3. Install the backend dependencies:

   pip install -r requirements.txt

Frontend (Next.js)

1. Navigate to the frontend directory:

   cd frontend

2. Install the dependencies:

   npm install

Usage

Running the Backend

1. Ensure the virtual environment is activated.
2. Run the Flask app:

   flask run

Running the Frontend

1. Navigate to the frontend directory:

   cd frontend

2. Start the Next.js development server:

   npm run dev

Downloading shadcn/ui files

To ensure that all UI elements are generated correctly using shadcn/ui, follow these steps:

1. Install the shadcn/ui package:

   npm install @shadcn/ui

2. Run the following command to generate the required UI components in your project:

   npx shadcn-ui init

3. Customize and build the components by running:

   npx shadcn-ui build

After following these steps, the Button, Input, Progress, and other UI components should be correctly configured.

Contributing

Contributions are welcome! Please submit a pull request or open an issue for any suggestions or improvements.