Comparative Analysis of Naive Bayes, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM) Algorithms for Classification of Heart Disease Patients

Abstract

Heart disease is still the leading cause of death. In this study, we tried to test several factors that can identify patients with heart disease using 3 classification algorithms: Naive Bayes, K-Nearest Neighbors (KNN), and Support Vector Machine (SVM).  The purpose of this study is to find out which algorithm can produce the highest accuracy in classifying, analyzing, and obtaining confusion matrix values along with the accuracy of predicting heart disease based on several factors or other comorbidities that the patient has, ranging from BMI to the patient's skin cancer status.  From the results of trials conducted by the SVM algorithm, it has the highest accuracy value, which is 92% while the Naive Bayes algorithm is the lowest with an accuracy value of 88%.