Electrocardiogram signals classification using random forest method for web-based smart healthcare

Abstract

Coronary heart is the highest cause of death in Indonesia reaching 26%. Therefore, to prevent the high mortality rate of coronary heart disease (CHD), early detection of CHD can be carried out. One way is to examine the electrocardiogram/electrocardiograph (ECG) recording. ECG hardware has been made in previous studies to record ECG signals. ECG research is an important study because it can detect cardiovascular disease. Cardiovascular diseases can be classified as arrhythmic diseases. Arrhythmia is a disorder that occurs in the heart rhythm. The method used to recognize and classify ECG signal patterns is the R-R interval (RRI) method. In this study, the ECG signal is classified as normal and abnormal. Abnormal means that a person has a heart rhythm disorder. The classification method used is random forest. The advantage of the random forest classifier is that it can handle noise and missing values and can handle large amounts of data. The accuracy of the ECG signal classification using the Random forest method is 96%. The contribution of this research is that early detection of heart rhythm disorders using an ECG can be monitored through the smart healthcare web.