Heart Attack Risk Prediction Using Machine Learning and SHAP Explainability

Heart disease remains one of the leading causes of mortality worldwide. Early detection of heart
attack risk is crucial for timely intervention. In this study, we employ Random Forest and XGBoost
models for predictive analysis of patient health data. In addition, SHAP explainability enhances
the interpretation of the model, identifying key risk factors such as cholesterol levels, age, and
blood pressure. Our final XGBoost model achieves 87% accuracy, demonstrating reliable predictive
capabilities.