Automatic identification of cardiac health using modeling techniques: A comparative study

U. Rajendra Acharya, Meena Sankaranarayanan, Jagadish Nayak, Chen Xiang, Toshiyo Tamura

Research output: Contribution to journalArticle

72 Citations (Scopus)

Abstract

Heart rate variability (HRV), a widely adopted quantitative marker of the autonomic nervous system can be used as a predictor of risk of cardiovascular diseases. Moreover, decreased heart rate variability (HRV) has been associated with an increased risk of cardiovascular diseases. Hence in this work HRV signal is used as the base signal for predicting the risk of cardiovascular diseases. The present study concerns nine cardiac classes that include normal sinus rhythm (NSR), congestive heart failure (CHF), atrial fibrillation (AF), ventricular fibrillation (VF), preventricular contraction (PVC), left bundle branch block (LBBB), complete heart block (CHB), ischemic/dilated cardiomyopathy (ISCH) and sick sinus syndrome (SSS). A total of 352 cardiac subjects belonging to the nine classes were analyzed in the frequency domain. The fast Fourier transforms (FFT) and three other modeling techniques namely, autoregressive (AR) model, moving average (MA) model and the autoregressive moving average (ARMA) model are used to estimate the power spectral densities of the RR interval variability. The spectral parameters obtained from the spectral analysis of the HRV signals are used as the input parameters to the artificial neural network (ANN) for classification of the different cardiac classes. Our findings reveal that the ARMA modeling technique seems to give better resolution and would be more promising for clinical diagnosis.

Original languageEnglish
Pages (from-to)4571-4582
Number of pages12
JournalInformation Sciences
Volume178
Issue number23
DOIs
Publication statusPublished - 01-12-2008
Externally publishedYes

Fingerprint

Heart Rate Variability
Cardiac
Comparative Study
Health
Modeling
Autonomic Nervous System
Congestive Heart Failure
Cardiomyopathy
Atrial Fibrillation
Ventricular Fibrillation
Autoregressive Moving Average Model
Moving Average Model
Power Spectral Density
Autoregressive Moving Average
Fast Fourier transform
Autoregressive Model
Spectral Analysis
Frequency Domain
Artificial Neural Network
Predictors

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Software
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

Acharya, U. R., Sankaranarayanan, M., Nayak, J., Xiang, C., & Tamura, T. (2008). Automatic identification of cardiac health using modeling techniques: A comparative study. Information Sciences, 178(23), 4571-4582. https://doi.org/10.1016/j.ins.2008.08.006
Acharya, U. Rajendra ; Sankaranarayanan, Meena ; Nayak, Jagadish ; Xiang, Chen ; Tamura, Toshiyo. / Automatic identification of cardiac health using modeling techniques : A comparative study. In: Information Sciences. 2008 ; Vol. 178, No. 23. pp. 4571-4582.
@article{fc46d32d0c244a8b8fa6bf19755307d3,
title = "Automatic identification of cardiac health using modeling techniques: A comparative study",
abstract = "Heart rate variability (HRV), a widely adopted quantitative marker of the autonomic nervous system can be used as a predictor of risk of cardiovascular diseases. Moreover, decreased heart rate variability (HRV) has been associated with an increased risk of cardiovascular diseases. Hence in this work HRV signal is used as the base signal for predicting the risk of cardiovascular diseases. The present study concerns nine cardiac classes that include normal sinus rhythm (NSR), congestive heart failure (CHF), atrial fibrillation (AF), ventricular fibrillation (VF), preventricular contraction (PVC), left bundle branch block (LBBB), complete heart block (CHB), ischemic/dilated cardiomyopathy (ISCH) and sick sinus syndrome (SSS). A total of 352 cardiac subjects belonging to the nine classes were analyzed in the frequency domain. The fast Fourier transforms (FFT) and three other modeling techniques namely, autoregressive (AR) model, moving average (MA) model and the autoregressive moving average (ARMA) model are used to estimate the power spectral densities of the RR interval variability. The spectral parameters obtained from the spectral analysis of the HRV signals are used as the input parameters to the artificial neural network (ANN) for classification of the different cardiac classes. Our findings reveal that the ARMA modeling technique seems to give better resolution and would be more promising for clinical diagnosis.",
author = "Acharya, {U. Rajendra} and Meena Sankaranarayanan and Jagadish Nayak and Chen Xiang and Toshiyo Tamura",
year = "2008",
month = "12",
day = "1",
doi = "10.1016/j.ins.2008.08.006",
language = "English",
volume = "178",
pages = "4571--4582",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",
number = "23",

}

Acharya, UR, Sankaranarayanan, M, Nayak, J, Xiang, C & Tamura, T 2008, 'Automatic identification of cardiac health using modeling techniques: A comparative study', Information Sciences, vol. 178, no. 23, pp. 4571-4582. https://doi.org/10.1016/j.ins.2008.08.006

Automatic identification of cardiac health using modeling techniques : A comparative study. / Acharya, U. Rajendra; Sankaranarayanan, Meena; Nayak, Jagadish; Xiang, Chen; Tamura, Toshiyo.

In: Information Sciences, Vol. 178, No. 23, 01.12.2008, p. 4571-4582.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic identification of cardiac health using modeling techniques

T2 - A comparative study

AU - Acharya, U. Rajendra

AU - Sankaranarayanan, Meena

AU - Nayak, Jagadish

AU - Xiang, Chen

AU - Tamura, Toshiyo

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Heart rate variability (HRV), a widely adopted quantitative marker of the autonomic nervous system can be used as a predictor of risk of cardiovascular diseases. Moreover, decreased heart rate variability (HRV) has been associated with an increased risk of cardiovascular diseases. Hence in this work HRV signal is used as the base signal for predicting the risk of cardiovascular diseases. The present study concerns nine cardiac classes that include normal sinus rhythm (NSR), congestive heart failure (CHF), atrial fibrillation (AF), ventricular fibrillation (VF), preventricular contraction (PVC), left bundle branch block (LBBB), complete heart block (CHB), ischemic/dilated cardiomyopathy (ISCH) and sick sinus syndrome (SSS). A total of 352 cardiac subjects belonging to the nine classes were analyzed in the frequency domain. The fast Fourier transforms (FFT) and three other modeling techniques namely, autoregressive (AR) model, moving average (MA) model and the autoregressive moving average (ARMA) model are used to estimate the power spectral densities of the RR interval variability. The spectral parameters obtained from the spectral analysis of the HRV signals are used as the input parameters to the artificial neural network (ANN) for classification of the different cardiac classes. Our findings reveal that the ARMA modeling technique seems to give better resolution and would be more promising for clinical diagnosis.

AB - Heart rate variability (HRV), a widely adopted quantitative marker of the autonomic nervous system can be used as a predictor of risk of cardiovascular diseases. Moreover, decreased heart rate variability (HRV) has been associated with an increased risk of cardiovascular diseases. Hence in this work HRV signal is used as the base signal for predicting the risk of cardiovascular diseases. The present study concerns nine cardiac classes that include normal sinus rhythm (NSR), congestive heart failure (CHF), atrial fibrillation (AF), ventricular fibrillation (VF), preventricular contraction (PVC), left bundle branch block (LBBB), complete heart block (CHB), ischemic/dilated cardiomyopathy (ISCH) and sick sinus syndrome (SSS). A total of 352 cardiac subjects belonging to the nine classes were analyzed in the frequency domain. The fast Fourier transforms (FFT) and three other modeling techniques namely, autoregressive (AR) model, moving average (MA) model and the autoregressive moving average (ARMA) model are used to estimate the power spectral densities of the RR interval variability. The spectral parameters obtained from the spectral analysis of the HRV signals are used as the input parameters to the artificial neural network (ANN) for classification of the different cardiac classes. Our findings reveal that the ARMA modeling technique seems to give better resolution and would be more promising for clinical diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=54849380800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=54849380800&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2008.08.006

DO - 10.1016/j.ins.2008.08.006

M3 - Article

AN - SCOPUS:54849380800

VL - 178

SP - 4571

EP - 4582

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

IS - 23

ER -