Integrated Cardiovascular Monitoring and Prediction System

Cardiolytics is a smart and scalable web-based health monitoring system that integrates real-time IoT devices, ensemble learning models, and a document-grounded AI chatbot to support cardiovascular homecare and predictive health services.

Example UI: Landing Page Cardiolytics

✨ Integrated Monitoring System — Comprehensive blood pressure monitoring using ESP32 (with simulated data), EMQX, and Kafka.

🧠 Hybrid Ensemble Model — Cardiovascular risk prediction powered by advanced ensemble models.

💬 Document-aware Chatbot — Intelligent Q&A chatbot leveraging PDF documents with Gemini and Pinecone integration.

👥 Role-based Access — Secure, role-specific access for Patients and Admins with authentication support.

🛠 Tech Stack — Flask, Jinja, MySQL, MQTT, Node-RED, and more.

git clone https://github.com/tmuchlissin/cardiolytics_home_care.git
cd cardiolytics_home_care

python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt          # Core Flask environment
pip install -r requirements_el.txt       # Optional: Ensemble model dependencies

flask db init
flask db migrate
flask db upgrade

• Open src/esp_simulator.ino in Arduino IDE
• Flash to ESP32 device
• Ensure .env MQTT credentials are correct

• Go to http://localhost:1880
• Import flow from src/flows.json

export FLASK_APP=backend/app.py
export FLASK_ENV=development
flask run

🌐 Visit: http://localhost:5000

High-level Workflow of Cardiolytics System

This project is licensed under the MIT License © 2025 T. Muchlissin

• Flask
• Pinecone
• Google Gemini
• Node-RED
• ESP32

💬 For research collaboration or demo requests, feel free to open an issue or contact me via GitHub.