Title: Cardiac disease classification using heart rate signals

Authors: V. Mahesh, A. Kandaswamy, C. Vimal, B. Sathish

Addresses: Department of Information Technology, PSG College of Technology, Coimbatore, India. ' Department of Biomedical Engineering, PSG College of Technology, Coimbatore, India. ' Department of Biomedical Engineering, PSG College of Technology, Coimbatore, India. ' Department of Biomedical Engineering, PSG College of Technology, Coimbatore, India

Abstract: Heart rate and Heart Rate Variability (HRV) are important measures that reflect the state of the cardiovascular system. HRV analysis has gained prominence in the field of cardiology for detecting cardiac abnormalities. This paper presents the study made on the use of linear (time domain and frequency domain) and nonlinear measures of heart rate variability for accurate classification of certain cardiac diseases. Three different classifiers, viz. Random Forests, Logistic Model Tree and Multilayer Perceptron Neural Network have been used for the classification. Data for use in this work has been obtained from the standard ECG databases in the Physionet website. Classification has been attempted using linear parameters, nonlinear parameters and combined. The classification results indicate that the combination of linear and nonlinear measures is a better indicator of heart diseases than linear or nonlinear measures alone. The results obtained by this study are comparable with those obtained with other techniques cited in the literature.

Keywords: heart rate signals; discrete wavelet transforms; time domain analysis; frequency domain analysis; nonlinear analysis; HRV; heart rate variability; random forests classifier; logistic model tree; multilayer perceptron; cardiac disease classification; electronic healthcare; e-healthcare; cardiovascular system; cardiac abnormalities; neural networks.

DOI: 10.1504/IJEH.2010.034173

International Journal of Electronic Healthcare, 2010 Vol.5 No.3, pp.211 - 230

Published online: 16 Jul 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article