Computerized electrocardiogram data transformation enables effective algorithmic differentiation of wide QRS complex tachycardias.
non-invasive techniques-electrocardiography < clinical
ventricular tachycardia/fibrillation < basic
Journal
Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc
ISSN: 1542-474X
Titre abrégé: Ann Noninvasive Electrocardiol
Pays: United States
ID NLM: 9607443
Informations de publication
Date de publication:
01 2023
01 2023
Historique:
revised:
16
10
2022
received:
18
09
2022
accepted:
19
10
2022
pubmed:
22
11
2022
medline:
14
1
2023
entrez:
21
11
2022
Statut:
ppublish
Résumé
Accurate automated wide QRS complex tachycardia (WCT) differentiation into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) can be accomplished using calculations derived from computerized electrocardiogram (ECG) data of paired WCT and baseline ECGs. Develop and trial novel WCT differentiation approaches for patients with and without a corresponding baseline ECG. We developed and trialed WCT differentiation models comprised of novel and previously described parameters derived from WCT and baseline ECG data. In Part 1, a derivation cohort was used to evaluate five different classification models: logistic regression (LR), artificial neural network (ANN), Random Forests [RF], support vector machine (SVM), and ensemble learning (EL). In Part 2, a separate validation cohort was used to prospectively evaluate the performance of two LR models using parameters generated from the WCT ECG alone (Solo Model) and paired WCT and baseline ECGs (Paired Model). Of the 421 patients of the derivation cohort (Part 1), a favorable area under the receiver operating characteristic curve (AUC) by all modeling subtypes: LR (0.96), ANN (0.96), RF (0.96), SVM (0.96), and EL (0.97). Of the 235 patients of the validation cohort (Part 2), the Solo Model and Paired Model achieved a favorable AUC for 103 patients with (Solo Model 0.87; Paired Model 0.95) and 132 patients without (Solo Model 0.84; Paired Model 0.95) a corroborating electrophysiology procedure or intracardiac device recording. Accurate WCT differentiation may be accomplished using computerized data of (i) the WCT ECG alone and (ii) paired WCT and baseline ECGs.
Sections du résumé
BACKGROUND
Accurate automated wide QRS complex tachycardia (WCT) differentiation into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) can be accomplished using calculations derived from computerized electrocardiogram (ECG) data of paired WCT and baseline ECGs.
OBJECTIVE
Develop and trial novel WCT differentiation approaches for patients with and without a corresponding baseline ECG.
METHODS
We developed and trialed WCT differentiation models comprised of novel and previously described parameters derived from WCT and baseline ECG data. In Part 1, a derivation cohort was used to evaluate five different classification models: logistic regression (LR), artificial neural network (ANN), Random Forests [RF], support vector machine (SVM), and ensemble learning (EL). In Part 2, a separate validation cohort was used to prospectively evaluate the performance of two LR models using parameters generated from the WCT ECG alone (Solo Model) and paired WCT and baseline ECGs (Paired Model).
RESULTS
Of the 421 patients of the derivation cohort (Part 1), a favorable area under the receiver operating characteristic curve (AUC) by all modeling subtypes: LR (0.96), ANN (0.96), RF (0.96), SVM (0.96), and EL (0.97). Of the 235 patients of the validation cohort (Part 2), the Solo Model and Paired Model achieved a favorable AUC for 103 patients with (Solo Model 0.87; Paired Model 0.95) and 132 patients without (Solo Model 0.84; Paired Model 0.95) a corroborating electrophysiology procedure or intracardiac device recording.
CONCLUSION
Accurate WCT differentiation may be accomplished using computerized data of (i) the WCT ECG alone and (ii) paired WCT and baseline ECGs.
Identifiants
pubmed: 36409204
doi: 10.1111/anec.13018
pmc: PMC9833371
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e13018Informations de copyright
© 2022 The Authors. Annals of Noninvasive Electrocardiology published by Wiley Periodicals LLC.
Références
Data Brief. 2020 Apr 21;30:105515
pubmed: 32382594
JACC Clin Electrophysiol. 2022 Jul;8(7):831-839
pubmed: 35863808
J Electrocardiol. 2018 Nov - Dec;51(6):1103-1109
pubmed: 30497739
Ann Intern Med. 1988 Dec 1;109(11):905-12
pubmed: 3190044
Am J Med. 1978 Jan;64(1):27-33
pubmed: 623134
Heart Rhythm. 2020 Mar;17(3):431-438
pubmed: 31546028
J Am Coll Cardiol. 2017 Aug 29;70(9):1183-1192
pubmed: 28838369
J Electrocardiol. 2017 Sep - Oct;50(5):704-709
pubmed: 28506602
Circulation. 1965 Apr;31:551-6
pubmed: 14275993
J Am Heart Assoc. 2020 Jun 2;9(11):e016598
pubmed: 32427020
Lancet. 1994 Feb 12;343(8894):386-8
pubmed: 7905552
J Cardiol. 2012 May;59(3):307-12
pubmed: 22341435
J Cardiovasc Electrophysiol. 2020 Jan;31(1):185-195
pubmed: 31840870
J Electrocardiol. 2020 Jul - Aug;61:121-129
pubmed: 32599290
Heart Rhythm. 2008 Jan;5(1):89-98
pubmed: 18180024
Acad Emerg Med. 2000 Jul;7(7):769-73
pubmed: 10917326
Ann Noninvasive Electrocardiol. 2023 Jan;28(1):e13018
pubmed: 36409204
J Electrocardiol. 2022 Sep-Oct;74:32-39
pubmed: 35933848
Pacing Clin Electrophysiol. 2000 Oct;23(10 Pt 1):1519-26
pubmed: 11060873
Ann Noninvasive Electrocardiol. 2022 Jan;27(1):e12890
pubmed: 34562325
Pacing Clin Electrophysiol. 2019 Jun;42(6):625-633
pubmed: 30888071
Circulation. 1991 May;83(5):1649-59
pubmed: 2022022
J Electrocardiol. 2021 Mar-Apr;65:50-54
pubmed: 33503517
Am J Cardiol. 1988 Jun 1;61(15):1279-83
pubmed: 3376886
Heart Rhythm. 2010 Jul;7(7):922-6
pubmed: 20215043
Data Brief. 2019 Apr 17;24:103924
pubmed: 31061863
J Electrocardiol. 2019 May - Jun;54:61-68
pubmed: 30925275
Geriatrics. 1970 Nov;25(11):91-101
pubmed: 5474631