Autonomic Features in Prediction of Coronary Artery Disease and Myocardial Infarction

Abstract

Atherosclerosis is one of the causes of the progression of cardiovascular diseases that lead to coronary artery diseases (CAD) and myocardial infarction (MI). The disease severity causes electrocardiogram (ECG) shape deformation leads to difficulty in R-wave detection required for heart rate variability (HRV) analysis. This limitation in the diagnosis of atherosclerotic events using ECG leads to computer-aided ECG-derived features in the prediction of CAD and MI. In this study, the lead-II ECG was recorded from CAD (N = 30), MI (N = 10), and control (N = 30) subjects. The ECG-derived heart rate variability (HRV) features were extracted. The HRV features-based support vector machine (SVM) and the artificial neural network (ANN) models have been optimized in the prediction of CAD and MI subjects. The present study revealed an efficacy of time-domain HRV parameters with the ANN model in the classification of CAD and MI subjects with an accuracy of 100% and 99.6%, respectively. While SVM presented an accuracy of 75.5% and 98.9%, respectively. The time-domain HRV parameter-based automated computer-aided diagnostic approach can be used in developing low-cost technology that may provide aid to clinicians in the screening of CAD and MI subjects.

Keywords:

• Artificial neural network
• Coronary artery disease
• Electrocardiogram
• Heart rate variability
• Myocardial infarction
• Support vector machine

Acknowledgment

The authors are thankful to Dr Prabin Kumar Shrivastava of Rajendra Institute of Medical Sciences, Ranchi to help in collecting electrocardiogram data. The authors are also thankful to Mr. Rohit Kumar of BIT, Ranchi for his support in implementing the machine learning technique. The authors are further thankful to UGC-CSIR for SRF to Mr Rahul Kumar, Birla Institute of Technology, Ranchi.

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Rahul Kumar

Rahul Kumar is pursuing his PhD degree from the Department of Bioengineering and Biotechnology, BIT Mesra, Ranchi, Jharkhand. He had completed his MSc in microbiology from Jiwaji University, India, and BSc medical laboratory technology from University Polytechnic, Birla Institute of Technology in the year 2015 and 2013, respectively. Email: [email protected]

Yogender Aggarwal

Yogender Aggarwal obtained his doctorate and a postgraduate degree from BIT Mesra, Ranchi in the area of biomedical instrumentation in 2011 and 2005, respectively. He completed a bachelor of applied sciences in instrumentation honors from the University of Delhi, Delhi. Presently he is employed as an assistant professor in the bioengineering and biotechnology Department of BIT Mesra, Ranchi.

Vinod Kumar Nigam

Vinod Kumar Nigam is working as an associate professor in the Bioengineering and Biotechnology Department, BIT, Mesra, Ranchi, Jharkhand. He completed his doctorate in biochemical engineering from Banaras Hindu University, Varanasi, India in 1999, Master of Science in biochemistry from Allahabad University, India in 1992. He had completed his Bachelor of Science degree from Allahabad University, India in 1988. Email: [email protected]