Automated Classification of Hypertension and Coronary Artery Disease Patients by PNN, KNN, and SVM Classifiers Using HRV Analysis

TLDR: The results obtained indicate that this computer aided classification system can be used as an additional diagnostic tool to effectively differentiate between the normal subjects and HTN and CAD affected patients.

Abstract: The hypertension (HTN) and coronary artery disease (CAD) are the major cardiovascular diseases existing globally. In the present work, the heart rate variability (HRV) of normal (NOR) subjects, HTN and CAD patients has been compared using linear and nonlinear features with different classifiers. The proposed work considers five minutes recordings of electrocardiogram (ECG) for processing of consecutive heartbeat (RR) interval tachogram, extracting the features from short term HRV data by linear and nonlinear methods, comparative analysis of HRV features and classification of controlled subjects from diseased patients like HTN and CAD using various classifiers. The analysis results indicate that all the three categories of data have distinguishable differences in entire set of features and classification results indicate that support vector machine (SVM) classifier achieves a classification accuracy of 96.67% and individual sensitivity values of 90%, 100% and 100% for NOR, HTN, and CAD classes respectively. The results obtained using the proposed methodology indicate that this computer aided classification system can be used as an additional diagnostic tool to effectively differentiate between the normal subjects and HTN and CAD affected patients.