Study of RF and SVM Machine Learning Model to Predict Heart Disease

Heart disease remains one of the leading causes of mortality worldwide, making early and accurate diagnosis essential for preventing severe complications. Recent advancements in machine learning have enabled clinicians to analyze complex patient data more effectively than traditional diagnostic approaches. This study evaluates two widely used machine learning models Random Forest (RF) and Support Vector Machine (SVM) for predicting heart disease using a curated clinical dataset. RF achieved an accuracy of 100%, while SVM achieved 98.87%. The study also integrates SHAP and LIME interpretability tools to provide transparent, clinically meaningful explanations. This combined focus on accuracy and explainability distinguishes the study from existing literature.