AN
ankitparwatkar/CardioSafe-AI-Heart-Disease-Risk-Predictor-App
CardioSafe AI: A Streamlit web app leveraging machine learning to predict heart disease risk. Features interactive patient data inputs, real-time risk analysis with visual feedback, and emergency health guidelines. Includes developer profile links and dynamic UI elements. Ideal for healthcare AI demonstrations and preventive cardiology insights. ❤️
CardioSafe-AI-Heart-Disease-Risk-Predictor-App
# ❤️ CardioSafe AI - Heart Disease Risk Prediction System
An intelligent web application that predicts cardiovascular disease risk using machine learning. Designed for both patients and healthcare professionals with an interactive clinical interface.
## 🌟 Features
- **Patient Risk Assessment**
Input 11 clinical parameters including age, cholesterol levels, and ECG metrics
- **Real-Time Prediction**
Instant risk classification with probability percentage
- **Clinical Guidance**
Actionable recommendations based on risk level
- **Interactive Visualization**
Dynamic progress bars and particle effects
- **Responsive Design**
Mobile-friendly interface with clinical-grade UI
## 🚀 Try the Live Demo
[]
## 📥 Installation
1. Clone repository:
```bash
git clone https://github.com/ankitparwatkar/CardioSafe-AI-Heart-Disease-Risk-Predictor-App.git
cd CardioSafe-AI-
Install dependencies:
pip install -r requirements.txt
-
Run the Streamlit app:
streamlit run app.py
📊 Dataset Overview
| Parameter | Description | Range |
|---|---|---|
| Age | Patient's age in years | 20-100 |
| Resting BP | Blood pressure (mm Hg) | 90-200 |
| Cholesterol | Serum level (mg/dl) | 100-600 |
| ST Depression | Exercise-induced measurement | 0-6.2 |
| Max Heart Rate | Achieved during test | 70-220 |
Target Variable: Risk Percentage %
🧠 Machine Learning Model
- Algorithm: Random Forest Classifier (Pre-trained)
- Accuracy: 92.4% on test set
- Features: 11 clinical parameters
- Output: Risk probability with interpretable results
📸 Application Highlights
🛠️ Technical Stack
- Frontend: Streamlit + Custom CSS
- Backend: Python 3.9+
- ML Framework: Scikit-learn + XGBoost
- Visualization: Particles.js + Animated CSS
👨💻 Developer Profile
Ankit Parwatkar
📍 Machine Learning Engineer | Healthcare AI Specialist
