Classification of Heart Disease Diagnoses Using Gaussian Naïve Bayes

Abstract

Machine learning, which is part of artificial intelligence, has been widely applied in various fields, especially the medical field. Machine learning helps doctors make more accurate diagnoses. Heart disease is one of the highest causes of death in the world, so the need for accurate diagnosis is absolute for this disease. There are many algorithms that have been applied in machine learning to classify and detect heart disease, such as Linear Discriminant Analysis [1], KNN, Decision Tree, Random Forest [2], and Logistic Regression [3]. One classification algorithm that has not been implemented is Gaussian Naive Bayes. So, in this research the Gaussian Naive Bayes algorithm will be tested on the cardio health risk assessment dataset. From the research results of applying the Gaussian Naive Bayes algorithm to cardio health risk assessment data, accuracy was 0.87%, precision was 0.88%, recall was 0.90%, and f1-score was 0.89%.