Detection of Heart Attack using Cross Wavelet Transformation and Support Vector Machine

Abstract

Ischemic heart disease is one of the leading causes of death in the world, and includes a wide range of transient forms, including incomplete blood supply to the heart muscle, which cause heart attacks and eventually sudden death. Identifying the main area of the myocardial infarction (MI) is a priority for the treatment of myocardial infarction. Electrocardiogram signal recording is a common method for monitoring cardiac function and widely used for detecting heart attack. In this study, using 10-part sections of the standard 12-lead electrocardiogram signal taken from the PhysioNet database, the diagnosis of the infarction was made possible. First, after removing the electrocardiogram (ECG) signal noises, by applying the Principal Component Analysis (PCA), the dimensions of the 12-lead electrocardiogram signal were reduced. Then the characteristic vector was created using the statistical properties of the wavelet cross spectrum (WCS) and the resulting wavelet coherence (WCOH) by the cross-wavelet transformation (XWT) method. In the next step, using a support vector machine, which is used as a classifier, the location of the heart attack is detected. The results show that the designed system to detect the incidence of MI has a sensitivity of 96.7% and a precision of 99%.