Heart Disease: Application of the K-Nearest Neighbor (KNN) Method

The increasing prevalence of non-communicable diseases, especially heart disease, in Indonesia highlights the need to improve the effectiveness of medical procedures, especially for patients with heart disease.Data and information from the Ministry of Health of the Republic of Indonesia show that non-communicable diseases, especially heart disease, are the most prevalent diseases and account for 16% of all cases worldwide.The purpose of this study is to analyze the factors associated with the prevalence of heart disease in Indonesia, based on the frequency of gender, age, slope, blood sugar, and chest pain.This study uses the K-Nearest Neighbor algorithm method in data mining with several stages.Dataset, Preprocessing, and Clustering are stages that must be done in this research, this system is to capture patient information to be implemented.This challenge is applied by exploring some initial approaches to obtain the value of K.This is especially true for very large data.The results of this study can contribute to the understanding of data miningbased cardiac data analysis techniques using the K-Nearest Neighbor algorithm to improve the accuracy of diagnosing cardiac patients, with special attention to several types of frequencies that are key in this method.This study also obtained the results of the classification of heart disease datasets with 72.13% based on the maximum K value of KNN through the K-Nearest Neighbor clustering technique.