Heart Disease Prediction Using Decision Tree Variants: A Comparative Analysis

Heart diseases (CVDs) persist a precede cause of fatality rate worldwide, necessitating accurate and explainable prediction model for early diagnosis and intercession. This study inquire the effectiveness of several decision tree algorithms, CART, ID3, and CHAID, C 4.5 and C 5.0 in auspicate heart disease. Using clinical datasets such as the Cleveland Heart Disease dataset, the models are evaluated establish on primal operation metrics like accuracy, recall, precision and F1. Pros and cons of each variant is done through comparative analysis, with CART demonstrating robustness in binary classification and CHAID excelling in handling categorical features. Random Forest algorithm produces high accuracy in predicting the heart disease. The findings underscore the importance of decision Tree algorithms as interpretable, efficient, and true shaft in medical diagnostics, providing a foundation for tangible - humankind clinical applications.