MedExplain AI is a next-generation, mobile-first healthcare application that uses Optical Character Recognition (OCR) and Generative AI to analyze medical reports, extract key biomarkers, and provide empathetic, human-readable medical insights in multiple languages.
- 📸 Smart Extraction: Upload a PDF/image or use the native device camera to scan medical reports. Uses
Tesseract OCRandOpenCVto parse complex medical data. - 🧠 AI Doctor Notes: Powered by
Google Gemini 1.5, it translates clinical jargon into easy-to-understand summaries, risk levels, and actionable health recommendations. - 🌍 Multi-Language Support: Generates insights in English, Spanish, Hindi, and Tamil.
- 🎙️ Voice AI Integration: Features built-in Text-to-Speech (TTS) to read reports aloud and Speech-to-Text (STT) so patients can ask questions using their voice.
- 💬 Context-Aware Chatbot: A built-in AI assistant that answers personalized questions based specifically on the uploaded report.
- 🛡️ Bulletproof Fallback: If API limits are reached, the app seamlessly degrades to an offline algorithmic fallback mode, ensuring zero downtime for the user experience.
- 📱 Mobile-First UI: A beautiful, responsive glassmorphism UI built with Tailwind CSS and Chart.js.
- Frontend: HTML5, Tailwind CSS, Chart.js, Web Speech API
- Backend: Python, FastAPI, Uvicorn
- AI / ML: Google Generative AI (Gemini Pro / Flash), Pytesseract, OpenCV
- Python 3.9+
- Tesseract OCR installed on your machine.
git clone https://github.com/aarthi04115/MedExplain_AI.git
cd MedExplain_AIpip install -r requirements.txtCreate a .env file in the root directory and add your Google Gemini API Key:
GEMINI_API_KEY=your_google_gemini_api_key_here
TESSERACT_CMD=C:\Program Files\Tesseract-OCR\tesseract.exepython app.pyThe app will automatically launch in your default web browser at http://127.0.0.1:8000.
MedExplain AI is a portfolio project designed for educational and demonstrative purposes. It is not a substitute for professional medical advice, diagnosis, or treatment.