AI-powered multimodal disease screening platform using photo, voice, and symptom analysis. Offline, multilingual, privacy-first healthcare assistant for low-resource communities.
# 🩺 MediScan AI
**An offline-first, multimodal AI health-screening assistant for low-resource communities.**
---
## 🎯 What It Does
MediScan AI is a **privacy-first, multimodal health-screening platform** built for communities with limited access to doctors and stable internet. A patient can describe symptoms by **photo, voice, or text** — the system classifies the issue and generates a preliminary assessment, entirely **without sending data to the cloud**.
Built as a submission to **Samsung Solve for Tomorrow**.
## ✨ Key Features
- 🖼️ **Skin condition classification** — fine-tuned EfficientNet-B3 model for visual symptom screening
- 🎙️ **Voice-based symptom intake** — Whisper transcribes spoken symptoms in multiple languages
- 🧠 **RAG-powered symptom analysis** — BioMistral-7B + LangChain + FAISS retrieve relevant medical context before generating an assessment, reducing hallucination
- 📱 **Cross-platform mobile app** — Flutter frontend designed for low-end devices and intermittent connectivity
- 🔒 **Privacy by design** — inference runs locally/offline wherever possible; no raw patient data leaves the device unnecessarily
- 🌍 **Multilingual support** — built for accessibility across non-English-speaking communities
## 🏗️ Architecture
```
┌─────────────┐ ┌──────────────┐ ┌────────────────────┐
│ Flutter App │ ──▶ │ FastAPI │ ──▶ │ EfficientNet-B3 │ (image → classification)
│ (Patient UI)│ │ Backend │ ──▶ │ Whisper │ (voice → text)
└─────────────┘ │ │ ──▶ │ BioMistral-7B │ (RAG symptom analysis)
└──────────────┘ │ + LangChain + FAISS │
└────────────────────┘
```
## 🛠️ Tech Stack
| Layer | Technology |
|---|---|
| Backend | FastAPI (Python) |
| Image Model | PyTorch, EfficientNet-B3 |
| Speech-to-Text | OpenAI Whisper |
| Symptom Reasoning | BioMistral-7B, LangChain, FAISS (RAG) |
| Mobile Frontend | Flutter |
| License | Apache 2.0 |
## 🚀 Getting Started
```bash
# Clone the …