Heart Rate Variability based Classification of Normal and Hypertension Cases by Linear-nonlinear Method

M. G. Poddar; Vinod Kumar; Yash Paul Sharma

doi:10.14429/dsj.64.7867

M. G. Poddar Department of Electrical Engineering, Indian Institute of Technology Roorkee
Vinod Kumar Department of Electrical Engineering, Indian Institute of Technology Roorkee
Yash Paul Sharma Post Graduate Institute of Medical Education and Research, Chandigarh

DOI: https://doi.org/10.14429/dsj.64.7867

Keywords: Heart rate variability, RR tachogram, hypertension, time domain, frequency domain, nonlinear, support vector machine classifier

Abstract

The aim of this study is to analyse and compare the heart rate variability (HRV) of normal and hypertension cases using time domain, frequency domain, and nonlinear methods. For short term HRV analysis, a five-minute electrocardiogram (ECG) of 57 normal and 56 hypertension subjects were recorded with prior verification of their clinical status by a cardiologist. Most time domain features of hypertension cases have clearly reduced values over normal subjects, frequency domain features, like power in different spectral bands, also have the distinguishable decreased values, whereas sympathovagal balance has clear edge over hypertension cases than normal cases. Nonlinear parameters of Poincare plot, approximate entropy and sample entropy, have higher values in normal cases when compared with hypertension cases. Support vector machine-based binary system classifies these two classes with 100 per cent accuracy and 100 per cent sensitivity when all time domain, frequency domain, and nonlinear features were used. It may work as a better predictor for in patients with hypertension.

Science Journal, Vol. 64, No. 6, November 2014, pp.542-548, DOI:http://dx.doi.org/10.14429/dsj.64.7867

Author Biographies

M. G. Poddar, Department of Electrical Engineering, Indian Institute of Technology Roorkee

Mr M.G. Poddar obtained BE in Instrumentation Technology from Basaveshwar Engineering College, Bagalkot, in 1997 and ME Instrumentation from Shri Guru Govind Singh Institute of Engineering and Technology, Nanded, in 2005. Currently pursuing his PhD at Biomedical Instrumentation Laboratory, Electrical Engineering Department, IIT Roorkee. His research interests include biomedical signal processing, medical instrumentation and digital signal processing and telemedicine.

Vinod Kumar, Department of Electrical Engineering, Indian Institute of Technology Roorkee

Dr Vinod Kumar obtained BSc (Electrical Engineering) from Punjab University in 1973, ME (Measurement & Instrumentation), and PhD from University of Roorkee in 1975 and 1984, respectively. Currently working as a Professor, Department of Electrical Engineering, IIT Roorkee, since 1995. He has guided 23 Doctoral and more than 100 Master’s Thesis and has more than 150 research publications in internationally reputed journals and conference proceedings. He is a Senior Member of IEEE, USA. His research interests include biomedical signal and image processing, digital signal processing and telemedicine.

Yash Paul Sharma, Post Graduate Institute of Medical Education and Research, Chandigarh

Dr Yash Paul Sharma obtained MBBS from Glancy Medical College, Amritsar, in 1984, MD (Medicine) from Rajendra Govt. Medical College and Hospital, Patiala in 1990, DM (Cardiology) from PGIMER, Chandigarh, in 1996. Working as Additional Professor and Head, Department of Cardiology, PGIMER, Chandigarh, since 2008. He has more than 30 research publication in reputed journals and conferences. His research areas include cardiovascular diseases, Cardio signal and image processing and cardio telemedicine.