A production-ready full-stack Clinical AI web application that predicts cardiovascular disease risk using machine learning. Built with React, Flask, and Random Forest — trained on the UCI Heart Disease dataset.
⚠️ First load may take 30–50 seconds as the free server wakes up. Wait a moment and it will load fully.
- Clinician enters patient biometric data
- Flask API sends data to trained Random Forest model
- App returns risk score, confidence %, feature importance, and clinical recommendation
- Clinician downloads a full PDF assessment report
- Real-time cardiovascular risk prediction (0–100%)
- Risk classification: Low / Moderate / High / Critical
- Feature importance visualization (Recharts)
- PDF report download with full patient assessment
- Dark professional medical UI
- Fully containerized with Docker
| Layer | Technology |
|---|---|
| Frontend | React, TypeScript, Tailwind CSS |
| Backend | Python, Flask, REST API |
| ML Model | Scikit-learn, Random Forest |
| Data | UCI Heart Disease Dataset |
| Deployment | Docker, docker-compose, Render |
git clone https://github.com/bashirAI-lab/clinicalai
cd clinicalai
docker-compose upVisit http://localhost:5173
# Backend
cd backend
pip install -r requirements.txt
python train_model.py
python app.py
# Frontend (new terminal)
cd frontend
npm install
npm run dev- Algorithm: Random Forest Classifier
- Dataset: UCI Heart Disease (303 patients)
- Accuracy: 92%
- Features: Age, Gender, Blood Pressure, Cholesterol, Heart Rate, Blood Sugar, Chest Pain Type, ECG Results
Abdalla Bashir Mahmoud ML Engineer | Clinical AI Specialist GitHub · Portfolio · Live Demo