Heart Disease Prediction by Machine Learning

The advancement and emergence of new technologies like analytics, artificial intelligence, and machine learning have greatly impacted several industries, including healthcare and automotive. In healthcare, these technologies have brought various benefits, such as clinical decision support, improved care coordination, and enhanced patient wellness. One significant challenge worldwide is heart disease, affecting millions of people. To improve prediction accuracy in healthcare, machine learning techniques like ensemble classifiers can be utilized. This research paper examines different ensemble methods (Bagging, MaxVoting, Boosting, Random Forest) as well as K-Nearest Neighbor Method, Naïve Bayes, Logistic Regression, Support Vector Machine, and Decision Tree, to accurately predict the occurrence of heart disease in a patient. The experimental results indicate that Max Voting (Ensemble Method) achieved the highest accuracy.