Skip to content

owsam22/diabetes-risk-engine

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🏥 HealthCheck: AI-Driven Diabetes Risk Engine

HealthCheck is a state-of-the-art Clinical Decision Support (CDS) application designed to predict diabetes risk using Machine Learning and provide personalized health strategies via Generative AI.

live site: https://diabetes-risk-engine.vercel.app/

Live Site API Status

HealthCheck Dashboard


✨ Key Features

  • 🧠 Predictive Analytics: Real-time risk assessment using a Random Forest ML model trained on clinical patient data.
  • ✨ AI-Powered Guidance: Personalized diet, exercise, and lifestyle suggestions generated by gpt-oss-120b via OpenRouter.
  • 🎛️ What-If Simulator: Interactive "sandbox" with dynamic sliders to model how improving metrics (BMI, Glucose) changes risk probability.
  • 📈 Patient History: Track metabolic trends over time with high-definition charts (Recharts).
  • 🔐 Secure Access: JWT-based authentication with encrypted password storage.
  • 📊 Data Freedom: Export complete assessment history to CSV for clinical review.
  • 🌿 Human-Centric UI: A "clinical-modern" light theme built with Tailwind CSS, focused on readability and professional aesthetics.

📸 Interface Preview

(Left) Diagnostic Result Page | (Right) Interactive What-If Simulator


🛠️ Tech Stack

  • Frontend: React 18 (Vite), Tailwind CSS, Zustand, Recharts, Lucide Icons.
  • Backend: Flask (Python), Scikit-Learn (Random Forest), JWT Extended.
  • AI: OpenRouter API (gpt-oss-120b:free).
  • Database: MongoDB Atlas.
  • Deployment: Vercel (Frontend) & Render (Backend).

🧬 How it Works: The ML Model

Unlike simple "if/else" calculators, HealthCheck utilizes a Random Forest Classifier trained on high-dimensional clinical data. When you submit biometric data, the backend:

  1. Pre-processes inputs (one-hot encoding categorical variables).
  2. Analyzes the feature set against the trained model weights.
  3. Calculates an exact probability percentage for diabetes risk.

🚀 Getting Started

To run locally:

  1. Clone the repo.
  2. Setup .env in app/ with MONGO_URI, JWT_SECRET_KEY, and OPENROUTER_API_KEY.
  3. In app/: pip install -r requirements.txt & python app.py.
  4. In frontend/: npm install & npm run dev.

🔗 Connect With Me

  

🤝 Credits & Authorship

Developed and maintained by owsam22 (Sam).


📜 Disclaimer

This tool is for educational and simulation purposes only. It is not a substitute for professional medical advice, diagnosis, or treatment. Always consult with a qualified healthcare provider for any medical concerns.


Made with ❤️ for Healthcare Innovation

About

🩺 Predictive Health Intelligence | A high-precision machine learning engine designed to assess diabetes risk through multi-dimensional data analysis. Bridging the gap between clinical data and preventative AI. 🧪💻

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors