The Implementation of Support Vector Machine Method for Heart Disease Classification

Abstract

Heart attack is one of the deadliest diseases recorded worldwide, with a reported 43.32% incidence and a mortality rate of 12.91%. In 2013, there were 61,682 cases of heart disease in Indonesia. The number of patients with this disease continues to rise, primarily due to a lack of knowledge or information about heart disease. Therefore, there is a need for a system that can provide information and early disease classification. This system can be used for classification when someone wants to know information or early symptoms of a heart attack. Classification involves creating a model used for grouping objects with similar characteristics into a predetermined class. One classification method is the Support Vector Machine (SVM). Hence, this research utilizes the SVM classification algorithm with the Radial Basis Function (RBF) kernel. The data consists of 200 samples obtained from the Nabire District Health Office in Papua. The testing phase involves using K-fold Cross Validation