Application of Machine Learning for Heart Disease Classification Using Naive Bayes

The Naive Bayes classifier uses an approximation of a Bayes theorem by combining previous knowledge with new ones. The purpose of this research is to develop machine learning using Naive Bayes classification techniques and as a decision system in producing fast and accurate classification accuracy in diagnosing cardiovascular diseases such as heart disease. Cardiovascular disease is the leading cause of death, 32% of all global deaths, of which 85% are caused by stroke and heart disease. Based on the results of the analysis, it was found that the accuracy of classification accuracy in the training data on patient data was classified as having and not having heart disease, respectively 83,21% and 83,1%. In data testing, the percentage of patient data classified as having and not having heart disease was 83,78% and 87,50%, respectively. Based on the AUC values ​​in the training data and testing data, they are 83,15% and 85,24%, respectively. So, from these results, it can be concluded that the Naive Bayes method is good for classifying heart disease patient data.