Premium
Performance of an Automatic Arrhythmia Classification Algorithm: Comparison to the ALTITUDE Electrophysiologist Panel Adjudications
Author(s) -
MAHAJAN DEEPA,
DONG YANTING,
SAXON LESLIE A.,
CHA YONGMEI,
GILLIAM Francis ROOSEVELT,
ASIRVATHAM SAMUEL J.,
CESARIO DAVID A.,
JONES PAUL W.,
SETH MILAN,
POWELL BRIAN D.
Publication year - 2014
Publication title -
pacing and clinical electrophysiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.686
H-Index - 101
eISSN - 1540-8159
pISSN - 0147-8389
DOI - 10.1111/pace.12367
Subject(s) - medicine , algorithm , cardiology , atrial fibrillation , implantable cardioverter defibrillator , adjudication , ventricular tachycardia , odds ratio , atrial tachycardia , confidence interval , catheter ablation , computer science , political science , law
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.