COMPARATIVE ASSESSMENT OF MACHINE LEARNING ALGORITHMS FOR HEART DISEASE PREDICTION

Abstract

Heart disease prediction is a complex and critical task in the field of medicine, considering the alarming rate at which people succumb to heart-related issues. The rapid advancements in data science offer a promising avenue for processing vast healthcare datasets. Automating the prediction process can help mitigate associated risks and enable timely patient alerts. This study leverages the heart disease dataset from the UCI machine learning repository to develop an automated prediction system. By employing various data mining techniques including Naive Bayes, Decision Tree, Logistic Regression, and Random Forest, the system aims to predict the likelihood of heart disease and categorize the patient's risk level. Through a comprehensive comparative analysis, this paper evaluates the performance of these machine learning algorithms. The experimental results underscore the superiority of the Random Forest algorithm, achieving an impressive accuracy rate of 90.16% in contrast to the other algorithms studied.