Automated Detection of Normal and Cardiac Heart Disease Using Chaos Attributes and Online Sequential Extreme Learning Machine

Abstract

Cardiovascular diseases (CVDs) are major reason of mortality in the world population, and the numeral of cases is up surging every year. The mortality rate due to coronary artery disease (CAD) and congestive heart failure (CHF) is higher than any other type of CVDs. Therefore, an early detection and diagnosis of CAD and CHF patients are essential. For this, an automated noninvasive approach has been proposed to detect CAD and CHF patients using attributes extracted from heart rate variability (HRV) signal. The automated scheme is based on chaos attributes extracted from heart rate variability signal (HRV), dimension reduction of attributes such as Generalized Discriminant Analysis (GDA) and online sequential extreme learning machine(OSELM). For this study, the HRV database of normal sinus rhythm (NSR), CHF, and CAD subjects have been taken from physionet.org website. The numerical results have shown that GDA with Gaussian kernel function and OSELM with sine activation function achieved accuracy (AC) of 99.34% and sensitivity (SE) of 99.32% for NSR-CAD group, and AC and SE of 100% were achieved for NSR-CHF group.