Diagnosis of multiclass tachycardia beats using recurrence quantification analysis and ensemble classifiers

Usha Desai, Roshan Joy Martis, U. Rajendra Acharya, C. Gurudas Nayak, G. Seshikala, Ranjan Shetty K

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Atrial Fibrillation (A-Fib), Atrial Flutter (AFL) and Ventricular Fibrillation (V-Fib) are fatal cardiac abnormalities commonly affecting people in advanced age and have indication of life-threatening condition. To detect these abnormal rhythms, Electrocardiogram (ECG) signal is most commonly visualized as a significant clinical tool. Concealed non-linearities in the ECG signal can be clearly unraveled using Recurrence Quantification Analysis (RQA) technique. In this paper, RQA features are applied for classifying four classes of ECG beats namely Normal Sinus Rhythm (NSR), A-Fib, AFL and V-Fib using ensemble classifiers. The clinically significant (p<0.05) features are ranked and fed independently to three classifiers viz. Decision Tree (DT), Random Forest (RAF) and Rotation Forest (ROF) ensemble methods to select the best classifier. The training and testing of the feature set is accomplished using 10-fold cross-validation strategy. The RQA coefficients using ROF provided an overall accuracy of 98.37% against 96.29% and 94.14% for the RAF and DT, respectively. The results achieved evidently ratify the superiority of ROF ensemble classifier in the diagnosis of A-Fib, AFL and V-Fib. Precision of four classes is measured using class-specific accuracy (%) and reliability of the performance is assessed using Cohen's kappa statistic (K). The developed approach can be used in therapeutic devices and help the physicians in automatic monitoring of fatal tachycardia rhythms.

Original languageEnglish
Article number1640005
JournalJournal of Mechanics in Medicine and Biology
Volume16
Issue number1
DOIs
Publication statusPublished - 01-02-2016

Fingerprint

Classifiers
Electrocardiography
Decision trees
Statistics
Monitoring
Testing

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

Desai, Usha ; Martis, Roshan Joy ; Acharya, U. Rajendra ; Nayak, C. Gurudas ; Seshikala, G. ; Shetty K, Ranjan. / Diagnosis of multiclass tachycardia beats using recurrence quantification analysis and ensemble classifiers. In: Journal of Mechanics in Medicine and Biology. 2016 ; Vol. 16, No. 1.
@article{e12471c477884b238de991ff7b7a5f3e,
title = "Diagnosis of multiclass tachycardia beats using recurrence quantification analysis and ensemble classifiers",
abstract = "Atrial Fibrillation (A-Fib), Atrial Flutter (AFL) and Ventricular Fibrillation (V-Fib) are fatal cardiac abnormalities commonly affecting people in advanced age and have indication of life-threatening condition. To detect these abnormal rhythms, Electrocardiogram (ECG) signal is most commonly visualized as a significant clinical tool. Concealed non-linearities in the ECG signal can be clearly unraveled using Recurrence Quantification Analysis (RQA) technique. In this paper, RQA features are applied for classifying four classes of ECG beats namely Normal Sinus Rhythm (NSR), A-Fib, AFL and V-Fib using ensemble classifiers. The clinically significant (p<0.05) features are ranked and fed independently to three classifiers viz. Decision Tree (DT), Random Forest (RAF) and Rotation Forest (ROF) ensemble methods to select the best classifier. The training and testing of the feature set is accomplished using 10-fold cross-validation strategy. The RQA coefficients using ROF provided an overall accuracy of 98.37{\%} against 96.29{\%} and 94.14{\%} for the RAF and DT, respectively. The results achieved evidently ratify the superiority of ROF ensemble classifier in the diagnosis of A-Fib, AFL and V-Fib. Precision of four classes is measured using class-specific accuracy ({\%}) and reliability of the performance is assessed using Cohen's kappa statistic (K). The developed approach can be used in therapeutic devices and help the physicians in automatic monitoring of fatal tachycardia rhythms.",
author = "Usha Desai and Martis, {Roshan Joy} and Acharya, {U. Rajendra} and Nayak, {C. Gurudas} and G. Seshikala and {Shetty K}, Ranjan",
year = "2016",
month = "2",
day = "1",
doi = "10.1142/S0219519416400054",
language = "English",
volume = "16",
journal = "Journal of Mechanics in Medicine and Biology",
issn = "0219-5194",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "1",

}

Diagnosis of multiclass tachycardia beats using recurrence quantification analysis and ensemble classifiers. / Desai, Usha; Martis, Roshan Joy; Acharya, U. Rajendra; Nayak, C. Gurudas; Seshikala, G.; Shetty K, Ranjan.

In: Journal of Mechanics in Medicine and Biology, Vol. 16, No. 1, 1640005, 01.02.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Diagnosis of multiclass tachycardia beats using recurrence quantification analysis and ensemble classifiers

AU - Desai, Usha

AU - Martis, Roshan Joy

AU - Acharya, U. Rajendra

AU - Nayak, C. Gurudas

AU - Seshikala, G.

AU - Shetty K, Ranjan

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Atrial Fibrillation (A-Fib), Atrial Flutter (AFL) and Ventricular Fibrillation (V-Fib) are fatal cardiac abnormalities commonly affecting people in advanced age and have indication of life-threatening condition. To detect these abnormal rhythms, Electrocardiogram (ECG) signal is most commonly visualized as a significant clinical tool. Concealed non-linearities in the ECG signal can be clearly unraveled using Recurrence Quantification Analysis (RQA) technique. In this paper, RQA features are applied for classifying four classes of ECG beats namely Normal Sinus Rhythm (NSR), A-Fib, AFL and V-Fib using ensemble classifiers. The clinically significant (p<0.05) features are ranked and fed independently to three classifiers viz. Decision Tree (DT), Random Forest (RAF) and Rotation Forest (ROF) ensemble methods to select the best classifier. The training and testing of the feature set is accomplished using 10-fold cross-validation strategy. The RQA coefficients using ROF provided an overall accuracy of 98.37% against 96.29% and 94.14% for the RAF and DT, respectively. The results achieved evidently ratify the superiority of ROF ensemble classifier in the diagnosis of A-Fib, AFL and V-Fib. Precision of four classes is measured using class-specific accuracy (%) and reliability of the performance is assessed using Cohen's kappa statistic (K). The developed approach can be used in therapeutic devices and help the physicians in automatic monitoring of fatal tachycardia rhythms.

AB - Atrial Fibrillation (A-Fib), Atrial Flutter (AFL) and Ventricular Fibrillation (V-Fib) are fatal cardiac abnormalities commonly affecting people in advanced age and have indication of life-threatening condition. To detect these abnormal rhythms, Electrocardiogram (ECG) signal is most commonly visualized as a significant clinical tool. Concealed non-linearities in the ECG signal can be clearly unraveled using Recurrence Quantification Analysis (RQA) technique. In this paper, RQA features are applied for classifying four classes of ECG beats namely Normal Sinus Rhythm (NSR), A-Fib, AFL and V-Fib using ensemble classifiers. The clinically significant (p<0.05) features are ranked and fed independently to three classifiers viz. Decision Tree (DT), Random Forest (RAF) and Rotation Forest (ROF) ensemble methods to select the best classifier. The training and testing of the feature set is accomplished using 10-fold cross-validation strategy. The RQA coefficients using ROF provided an overall accuracy of 98.37% against 96.29% and 94.14% for the RAF and DT, respectively. The results achieved evidently ratify the superiority of ROF ensemble classifier in the diagnosis of A-Fib, AFL and V-Fib. Precision of four classes is measured using class-specific accuracy (%) and reliability of the performance is assessed using Cohen's kappa statistic (K). The developed approach can be used in therapeutic devices and help the physicians in automatic monitoring of fatal tachycardia rhythms.

UR - http://www.scopus.com/inward/record.url?scp=84991396801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991396801&partnerID=8YFLogxK

U2 - 10.1142/S0219519416400054

DO - 10.1142/S0219519416400054

M3 - Article

AN - SCOPUS:84991396801

VL - 16

JO - Journal of Mechanics in Medicine and Biology

JF - Journal of Mechanics in Medicine and Biology

SN - 0219-5194

IS - 1

M1 - 1640005

ER -