Boosting Algorithms Empowering Heart Disease Prediction for Enhanced Medical Accuracy

Heart disease remains a leading cause of mortality worldwide, necessitating accurate and reliable predictive models to aid early diagnosis and treatment. Traditional machine learning methods like LR and DT Classifiers offer reasonable recall rates but suffer from lower precision and accuracy. To address this challenge, we employed advanced boosting algorithms, specifically GradientBoostingClassifier and XGBClassifier, to enhance predictive accuracy in heart disease detection. Our study shows that these algorithms achieve accuracy rates above 93%, with precision exceeding 52%, and a significantly low False Positive Rate below 0.5%. However, the trade-off involves lower recall rates, suggesting some true cases remain undetected. Boosting algorithms thus provide a robust approach for heart disease prediction, though attention to false negatives is essential for comprehensive application.