A machine learning-based Python project to predict the risk of heart disease using patient data. Built with a Random Forest Classifier, it provides a probability-based risk assessment and insights into important features influencing heart disease.
- Predicts heart disease risk based on patient health metrics.
- Handles categorical and numerical features automatically.
- Provides confidence score along with prediction.
- Visualizes feature importance for better interpretability.
This project uses the Heart Disease UCI dataset, with the following features:
age,sex,cp,trestbps,chol,fbs,restecg,thalch,exang,oldpeak,slope,ca,thal,numnumis the target column (0 = No Heart Disease, 1 = Heart Disease)
Note: Some categorical features (sex, cp, fbs, restecg, exang, slope, thal) are encoded during preprocessing.
Clone this repository:
git clone <your-repo-url>
cd heart-risk-predictor