Performance of an automatic arrhythmia classification algorithm: Comparison to the ALTITUDE electrophysiologist panel adjudications

Deepa Mahajan, Yanting Dong, Leslie A. Saxon, Yong-Mei Cha, Francis Roosevelt Gilliam, Samuel J Asirvatham, David A. Cesario, Paul W. Jones, Milan Seth, Brian D. Powell

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Introduction Adjudication of thousands of implantable cardioverter defibrillator (ICD)-treated arrhythmia episodes is labor intensive and, as a result, is most often left undone. The objective of this study was to evaluate an automatic classification algorithm for adjudication of ICD-treated arrhythmia episodes. Methods The algorithm uses a machine learning algorithm and was developed using 776 arrhythmia episodes. The algorithm was validated on 131 dual-chamber ICD shock episodes from 127 patients adjudicated by seven electrophysiologists (EPs). Episodes were classified by panel consensus as ventricular tachycardia/ventricular fibrillation (VT/VF) or non-VT/VF, with the resulting classifications used as the reference. Subsequently, each episode electrogram (EGM) data was randomly assigned to three EPs without the atrial lead information, and to three EPs with the atrial lead information. Those episodes were also classified by the automatic algorithm with and without atrial information. Agreement with the reference was compared between the three EPs consensus group and the algorithm. Results The overall agreement with the reference was similar between three-EP consensus and the algorithm for both with atrial EGM (94% vs 95%, P = 0.87) and without atrial EGM (90% vs 91%, P = 0.91). The odds of accurate adjudication, after adjusting for covariates, did not significantly differ between the algorithm and EP consensus (odds ratio 1.02, 95% confidence interval: 0.97-1.06). Conclusions This algorithm performs at a level comparable to an EP panel in the adjudication of arrhythmia episodes treated by both dual- and single-chamber ICDs. This type of algorithm has the potential for automated analysis of clinical ICD episodes, and adjudication of EGMs for research studies and quality analyses.

Original languageEnglish (US)
Pages (from-to)889-899
Number of pages11
JournalPACE - Pacing and Clinical Electrophysiology
Volume37
Issue number7
DOIs
StatePublished - 2014

Fingerprint

Cardiac Arrhythmias
Implantable Defibrillators
Cardiac Electrophysiologic Techniques
Ventricular Fibrillation
Ventricular Tachycardia
Tachycardia
Shock
Odds Ratio
Confidence Intervals
Research

Keywords

  • computing
  • CRT
  • database
  • defibrillators
  • electrocardiogram
  • ICD

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine

Cite this

Performance of an automatic arrhythmia classification algorithm : Comparison to the ALTITUDE electrophysiologist panel adjudications. / Mahajan, Deepa; Dong, Yanting; Saxon, Leslie A.; Cha, Yong-Mei; Gilliam, Francis Roosevelt; Asirvatham, Samuel J; Cesario, David A.; Jones, Paul W.; Seth, Milan; Powell, Brian D.

In: PACE - Pacing and Clinical Electrophysiology, Vol. 37, No. 7, 2014, p. 889-899.

Research output: Contribution to journalArticle

Mahajan, Deepa ; Dong, Yanting ; Saxon, Leslie A. ; Cha, Yong-Mei ; Gilliam, Francis Roosevelt ; Asirvatham, Samuel J ; Cesario, David A. ; Jones, Paul W. ; Seth, Milan ; Powell, Brian D. / Performance of an automatic arrhythmia classification algorithm : Comparison to the ALTITUDE electrophysiologist panel adjudications. In: PACE - Pacing and Clinical Electrophysiology. 2014 ; Vol. 37, No. 7. pp. 889-899.
@article{c2a9d706f9bb4c4a809449c138eeaf08,
title = "Performance of an automatic arrhythmia classification algorithm: Comparison to the ALTITUDE electrophysiologist panel adjudications",
abstract = "Introduction Adjudication of thousands of implantable cardioverter defibrillator (ICD)-treated arrhythmia episodes is labor intensive and, as a result, is most often left undone. The objective of this study was to evaluate an automatic classification algorithm for adjudication of ICD-treated arrhythmia episodes. Methods The algorithm uses a machine learning algorithm and was developed using 776 arrhythmia episodes. The algorithm was validated on 131 dual-chamber ICD shock episodes from 127 patients adjudicated by seven electrophysiologists (EPs). Episodes were classified by panel consensus as ventricular tachycardia/ventricular fibrillation (VT/VF) or non-VT/VF, with the resulting classifications used as the reference. Subsequently, each episode electrogram (EGM) data was randomly assigned to three EPs without the atrial lead information, and to three EPs with the atrial lead information. Those episodes were also classified by the automatic algorithm with and without atrial information. Agreement with the reference was compared between the three EPs consensus group and the algorithm. Results The overall agreement with the reference was similar between three-EP consensus and the algorithm for both with atrial EGM (94{\%} vs 95{\%}, P = 0.87) and without atrial EGM (90{\%} vs 91{\%}, P = 0.91). The odds of accurate adjudication, after adjusting for covariates, did not significantly differ between the algorithm and EP consensus (odds ratio 1.02, 95{\%} confidence interval: 0.97-1.06). Conclusions This algorithm performs at a level comparable to an EP panel in the adjudication of arrhythmia episodes treated by both dual- and single-chamber ICDs. This type of algorithm has the potential for automated analysis of clinical ICD episodes, and adjudication of EGMs for research studies and quality analyses.",
keywords = "computing, CRT, database, defibrillators, electrocardiogram, ICD",
author = "Deepa Mahajan and Yanting Dong and Saxon, {Leslie A.} and Yong-Mei Cha and Gilliam, {Francis Roosevelt} and Asirvatham, {Samuel J} and Cesario, {David A.} and Jones, {Paul W.} and Milan Seth and Powell, {Brian D.}",
year = "2014",
doi = "10.1111/pace.12367",
language = "English (US)",
volume = "37",
pages = "889--899",
journal = "PACE - Pacing and Clinical Electrophysiology",
issn = "0147-8389",
publisher = "Wiley-Blackwell",
number = "7",

}

TY - JOUR

T1 - Performance of an automatic arrhythmia classification algorithm

T2 - Comparison to the ALTITUDE electrophysiologist panel adjudications

AU - Mahajan, Deepa

AU - Dong, Yanting

AU - Saxon, Leslie A.

AU - Cha, Yong-Mei

AU - Gilliam, Francis Roosevelt

AU - Asirvatham, Samuel J

AU - Cesario, David A.

AU - Jones, Paul W.

AU - Seth, Milan

AU - Powell, Brian D.

PY - 2014

Y1 - 2014

N2 - Introduction Adjudication of thousands of implantable cardioverter defibrillator (ICD)-treated arrhythmia episodes is labor intensive and, as a result, is most often left undone. The objective of this study was to evaluate an automatic classification algorithm for adjudication of ICD-treated arrhythmia episodes. Methods The algorithm uses a machine learning algorithm and was developed using 776 arrhythmia episodes. The algorithm was validated on 131 dual-chamber ICD shock episodes from 127 patients adjudicated by seven electrophysiologists (EPs). Episodes were classified by panel consensus as ventricular tachycardia/ventricular fibrillation (VT/VF) or non-VT/VF, with the resulting classifications used as the reference. Subsequently, each episode electrogram (EGM) data was randomly assigned to three EPs without the atrial lead information, and to three EPs with the atrial lead information. Those episodes were also classified by the automatic algorithm with and without atrial information. Agreement with the reference was compared between the three EPs consensus group and the algorithm. Results The overall agreement with the reference was similar between three-EP consensus and the algorithm for both with atrial EGM (94% vs 95%, P = 0.87) and without atrial EGM (90% vs 91%, P = 0.91). The odds of accurate adjudication, after adjusting for covariates, did not significantly differ between the algorithm and EP consensus (odds ratio 1.02, 95% confidence interval: 0.97-1.06). Conclusions This algorithm performs at a level comparable to an EP panel in the adjudication of arrhythmia episodes treated by both dual- and single-chamber ICDs. This type of algorithm has the potential for automated analysis of clinical ICD episodes, and adjudication of EGMs for research studies and quality analyses.

AB - Introduction Adjudication of thousands of implantable cardioverter defibrillator (ICD)-treated arrhythmia episodes is labor intensive and, as a result, is most often left undone. The objective of this study was to evaluate an automatic classification algorithm for adjudication of ICD-treated arrhythmia episodes. Methods The algorithm uses a machine learning algorithm and was developed using 776 arrhythmia episodes. The algorithm was validated on 131 dual-chamber ICD shock episodes from 127 patients adjudicated by seven electrophysiologists (EPs). Episodes were classified by panel consensus as ventricular tachycardia/ventricular fibrillation (VT/VF) or non-VT/VF, with the resulting classifications used as the reference. Subsequently, each episode electrogram (EGM) data was randomly assigned to three EPs without the atrial lead information, and to three EPs with the atrial lead information. Those episodes were also classified by the automatic algorithm with and without atrial information. Agreement with the reference was compared between the three EPs consensus group and the algorithm. Results The overall agreement with the reference was similar between three-EP consensus and the algorithm for both with atrial EGM (94% vs 95%, P = 0.87) and without atrial EGM (90% vs 91%, P = 0.91). The odds of accurate adjudication, after adjusting for covariates, did not significantly differ between the algorithm and EP consensus (odds ratio 1.02, 95% confidence interval: 0.97-1.06). Conclusions This algorithm performs at a level comparable to an EP panel in the adjudication of arrhythmia episodes treated by both dual- and single-chamber ICDs. This type of algorithm has the potential for automated analysis of clinical ICD episodes, and adjudication of EGMs for research studies and quality analyses.

KW - computing

KW - CRT

KW - database

KW - defibrillators

KW - electrocardiogram

KW - ICD

UR - http://www.scopus.com/inward/record.url?scp=84904048975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904048975&partnerID=8YFLogxK

U2 - 10.1111/pace.12367

DO - 10.1111/pace.12367

M3 - Article

C2 - 24527748

AN - SCOPUS:84904048975

VL - 37

SP - 889

EP - 899

JO - PACE - Pacing and Clinical Electrophysiology

JF - PACE - Pacing and Clinical Electrophysiology

SN - 0147-8389

IS - 7

ER -