🧠 Multi-Disease Predictor

A full-stack Machine Learning application that allows users to predict 8 different diseases based on user inputs. The system is designed with a modular backend in FastAPI and a responsive frontend in React with TailwindCSS, and includes functionality for online learning via user feedback and retraining!

---

---

🚀 Features

• 🩺 Predicts the likelihood of:
  • Anemia
  • Cardiovascular Disease
  • Heart Disease
  • Hepatitis C
  • Liver Disease
  • Lung Cancer
  • Stroke
  • Thyroid Disease
• ⚡ Built with FastAPI backend and Vite+React frontend
• 🔁 Supports user feedback and model retraining via /submit_data/{disease} and /retrain/{disease} APIs
• 🧪 MLflow integration for experiment tracking
• 🐳 Dockerized for seamless deployment

---

🧰 Tech Stack

Layer	Technologies
Frontend
Backend
ML Models
MLOps
DevOps

---

🏗️ Project Structure

multi-disease-predictor/
├── backend/               # FastAPI server + ML models + retraining
├── frontend/              # React (Vite + TailwindCSS) UI
├── models/                # Pretrained ML models
├── notebooks/             # Jupyter Notebooks for experiments
├── mlruns/                # MLflow runs
├── mlartifacts/           # MLflow artifacts
├── data/                  # Raw and processed datasets
├── docs/                  # Sphinx documentation
├── docker-compose.yml     # Docker orchestration
└── tests/                 # API test scripts

---

🖥️ Local Setup

🔧 Prerequisites

Python 3.10+

Node.js 18+

Docker (for containerized deployment)

pip or conda

🐍 Backend

#Create virtualenv and activate

python3 -m venv venv
source venv/bin/activate

Install dependencies

pip install -r requirements.txt

Start FastAPI server

cd backend
uvicorn main_2:app --reload

🌐 Frontend

cd frontend
npm install
npm run dev

🐳 Run with Docker Compose

docker-compose up --build

Backend: http://localhost:8000

Frontend: http://localhost:3000

🤝 Contributors

Thanks to these amazing people :

Name	GitHub Profile
Rohit Kshirsagar	@rohitkshirsagar19
Parth Lhase	@LhaseParth2610
Rishabh Kothari	@RishabhK103
Prajwal Kumbhar	@prajwalkumbhar29

🪪 License

This project is licensed under the MIT License. See the LICENSE file for details.