PERFORMANCE OF CLASSIFICATION ALGORITHM IN THE PREDICTION OF HYPERTENSIVE HEART DISEASE

ABSTRACT

Hypertensive heart disease poses a significant health challenge globally, contributing substantially to cardiovascular morbidity and mortality. This study focuses on assessing the performance of classification algorithms in predicting chronic heart disease, particularly hypertensive heart disease. The introduction highlights the rising prevalence of hypertension, especially in African regions, and its association with cardiovascular illnesses. The main problem statement emphasizes the gap in research regarding the specific performance of classification algorithms for hypertensive heart disease prediction, despite their potential in healthcare data analysis. The research questions delve into optimizing feature selection techniques, comparing machine learning algorithms across different classifier, and identifying the most effective algorithm for predictive accuracy within each class. The aim and objectives revolve around evaluating three classification algorithms, optimizing feature sets, applying machine learning techniques, comparing algorithm performance, and determining the best algorithm based on metrics. The study's scope covers the utilization of chronic heart disease datasets due to time constraints, with WEKA as the chosen data mining tool. The significance of the study lies in enhancing early detection and intervention for hypertensive heart disease through classification algorithms, potentially improving patient outcomes and reducing healthcare burden.

Keywords: Classification Algorithm, Hypertensive Heart Disease, Feature Selection Techniques, Patient, WEKA.