Heart rate variability analysis using a PCA-SVM classifier distinguished normal subjects from CAD patients with an accuracy of 91.67% and sensitivities of 86.67% and 96.67%, respectively.
Observational (n=124)
Does Heart Rate Variability (HRV) analysis combined with machine learning classifiers accurately diagnose coronary artery disease?
Heart rate variability analysis combined with PCA and SVM classifiers can accurately distinguish between normal subjects and patients with coronary artery disease.
Coronary artery disease (CAD) is a highly considered dangerous disease which may lead to myocardial infarction and even sudden cardiac death. The objective of this work is to evaluate the diagnostic performance features derived from linear and non-linear methods of Heart Rate Variability (HRV) analysis for classification software modules with Normal (NOR) subjects and CAD patients. The proposed methodology follows the recording of electrocardiogram from 60 NOR subjects and 64 CAD patients, RR interval tachogram generation, computing the features from time domain, frequency domain, non-linear methods and its analysis, feature dimension reduction by Principal Component Analysis (PCA) and classification by probabilistic neural network, K nearest neighbour and Support Vector Machine (SVM) classifiers. The results of the study indicate a clear difference in NOR subjects and CAD affected patients by using PCA-SVM classifier with an accuracy of 91.67%, sensitivity of 86.67% and 96.67% for NOR and CAD classes, respectively.
Poddar et al. (Tue,) conducted a observational in Coronary artery disease (n=124). Heart Rate Variability (HRV) analysis using PCA-SVM classifier vs. Normal subjects was evaluated on Classification accuracy. Heart rate variability analysis using a PCA-SVM classifier distinguished normal subjects from CAD patients with an accuracy of 91.67% and sensitivities of 86.67% and 96.67%, respectively.