Heart disease is a leading cause of mortality worldwide, with early detection playing a critical role in reducing death rates. Accurate prediction of heart disease remains challenging due to complex medical data and the inability to provide continuous monitoring. Utilizing the Heart Disease dataset, various feature selection techniques, including ANOVA F-statistic (ANOVA FS), Chi-squared test (Chi2 FS), and Mutual Information (MI FS), were employed to identify significant predictors. Synthetic Minority Oversampling Technique (SMOTE) was applied to address data imbalance and enhance model performance. A comprehensive classification approach was undertaken using diverse machine learning models and ensemble methods. Among these, a Stacking Classifier combining Boosted Decision Trees, Extra Trees, and LightGBM achieved superior results, delivering 100% accuracy across all feature selection techniques. The high performance highlights the effectiveness of advanced ensemble learning in achieving reliable heart disease predictions, emphasizing the potential of integrating robust feature selection with sophisticated classification models for precise medical data analysis. This approach demonstrates the capacity to support early diagnosis and improved patient outcomes.
Mrs.Deepa et al. (Fri,) studied this question.