<![CDATA[This study presents a web-based Heart Disease Prediction System developed using Logistic Regression and Random Forest algorithms, enhanced with SHAP explainability. The system predicts the likelihood of heart disease based on key clinical parameters such as age, sex, chest pain type, blood pressure, cholesterol, and heart rate. SHAP values are integrated to provide transparent and interpretable explanations of model predictions. The Random Forest model demonstrated superior performance in capturing nonlinear relationships compared to Logistic Regression. The web application offers an interactive and user-friendly interface that displays correlation heatmaps, feature importance plots, and SHAP visualizations to aid in clinical interpretation. The results indicate that chest pain type, ST depression, and exercise-induced angina are among the most influential predictors. The proposed system successfully achieves accurate and explainable heart disease prediction, contributing to early diagnosis and decision support in healthcare.]]>
Copyrights © 2025
