HealthDecode

HealthDecode is an AI-powered web application that helps patients better understand their medical reports. Upload a medical report image or PDF and receive a structured, plain-English interpretation — including findings, conditions, recommendations, and a downloadable PDF report.

Author

Mr. Yash Jadhav
NIPER Hyderabad
M.Tech — Medical Devices
AI Project

Features

1. Medical report upload — Supports PDF, JPG, PNG, and other image formats.
2. Backend OCR — PaddleOCR extracts text server-side with high accuracy.
3. AI Analysis — Google Gemini interprets the extracted text and returns structured medical insights.
4. Downloadable PDF Report — Generates a properly formatted, patient-friendly PDF with all findings, conditions, and recommendations.

Getting Started

Prerequisites

• Node.js (v18+)
• Python 3.10+

Installation

1. Clone the repository to your local machine.
2. Install frontend dependencies:

   npm install

3. Install backend dependencies:

   pip install -r backend/requirements.txt

4. Copy the example .env.example to .env at the project root and update values for your environment.

   cp .env.example .env
   # then edit .env and set real values (do NOT commit secrets)

5. (Optional) Create backend/.env for backend-only secrets or API keys, or place them in the root .env.

Running

Start the backend:

cd backend
python -m uvicorn main:app --host 0.0.0.0 --port 8000 --reload

Start the frontend:

npm run dev

Usage

1. Navigate to the HealthDecode web application.
2. Upload your medical report (image or PDF).
3. Click Analyse Report and wait for the AI to process it.
4. Review the structured report across tabs: Overview, Findings, Conditions, Recommendations.
5. Click Download PDF to save a formatted report.

License

This project is developed as part of an M.Tech AI project at NIPER Hyderabad.