A hybrid machine learning approach to localizing the origin of ventricular tachycardia using 12-lead electrocardiograms.
Active learning
Disentangled representation learning
Electrocardiogram
Pace-mapping
Ventricular tachycardia
Journal
Computers in biology and medicine
ISSN: 1879-0534
Titre abrégé: Comput Biol Med
Pays: United States
ID NLM: 1250250
Informations de publication
Date de publication:
11 2020
11 2020
Historique:
received:
07
08
2020
revised:
17
09
2020
accepted:
17
09
2020
pubmed:
2
10
2020
medline:
22
6
2021
entrez:
1
10
2020
Statut:
ppublish
Résumé
Machine learning models may help localize the site of origin of ventricular tachycardia (VT) using 12-lead electrocardiograms. However, population-based models suffer from inter-subject anatomical variations within ECG data, while patient-specific models face the open challenge of what pacing data to collect for training. This study presents and validates the first hybrid model that combines population and patient-specific machine learning for rapid "computer-guided pace-mapping". A population-based deep learning model was first trained offline to disentangle inter-subject variations and regionalize the site of VT origin. Given a new patient with a target VT, an on-line patient-specific model -- after being initialized by the population-based prediction -- was then built in real time by actively suggesting where to pace next and improving the prediction with each added pacing data, progressively guiding pace-mapping towards the site of VT origin. The population model was trained on pace-mapping data from 38 patients and the patient-specific model was subsequently tuned on one patient. The resulting hybrid model was tested on a separate cohort of eight patients in localizing 1) 193 LV endocardial pacing sites, and 2) nine VTs with clinically determined exit sites. The hybrid model achieved a localization error of 5.3 ± 2.6 mm using 5.4 ± 2.5 pacing sites in localizing LV pacing sites, achieving a significantly higher accuracy with a significantly smaller amount of training sites in comparison to models without active guidance. The presented hybrid model has the potential to assist rapid pace-mapping of interventional targets in VT.
Sections du résumé
BACKGROUND
Machine learning models may help localize the site of origin of ventricular tachycardia (VT) using 12-lead electrocardiograms. However, population-based models suffer from inter-subject anatomical variations within ECG data, while patient-specific models face the open challenge of what pacing data to collect for training.
METHODS
This study presents and validates the first hybrid model that combines population and patient-specific machine learning for rapid "computer-guided pace-mapping". A population-based deep learning model was first trained offline to disentangle inter-subject variations and regionalize the site of VT origin. Given a new patient with a target VT, an on-line patient-specific model -- after being initialized by the population-based prediction -- was then built in real time by actively suggesting where to pace next and improving the prediction with each added pacing data, progressively guiding pace-mapping towards the site of VT origin.
RESULTS
The population model was trained on pace-mapping data from 38 patients and the patient-specific model was subsequently tuned on one patient. The resulting hybrid model was tested on a separate cohort of eight patients in localizing 1) 193 LV endocardial pacing sites, and 2) nine VTs with clinically determined exit sites. The hybrid model achieved a localization error of 5.3 ± 2.6 mm using 5.4 ± 2.5 pacing sites in localizing LV pacing sites, achieving a significantly higher accuracy with a significantly smaller amount of training sites in comparison to models without active guidance.
CONCLUSION
The presented hybrid model has the potential to assist rapid pace-mapping of interventional targets in VT.
Identifiants
pubmed: 33002841
pii: S0010-4825(20)30344-9
doi: 10.1016/j.compbiomed.2020.104013
pmc: PMC7606703
mid: NIHMS1633340
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
104013Subventions
Organisme : NHLBI NIH HHS
ID : R15 HL140500
Pays : United States
Informations de copyright
Copyright © 2020 Elsevier Ltd. All rights reserved.
Références
Heart Rhythm. 2020 Apr;17(4):567-575
pubmed: 31669770
Pacing Clin Electrophysiol. 2012 Dec;35(12):1516-27
pubmed: 22897344
Arrhythm Electrophysiol Rev. 2018 Jun;7(2):111-117
pubmed: 29967683
JACC Clin Electrophysiol. 2017 Jul;3(7):687-699
pubmed: 29759537
IEEE Trans Biomed Eng. 2018 Jul;65(7):1662-1671
pubmed: 28952932
IEEE Trans Biomed Eng. 2020 May;67(5):1505-1516
pubmed: 31494539
IEEE Trans Med Imaging. 2019 May;38(5):1172-1184
pubmed: 30418900
Heart Rhythm. 2005 Apr;2(4):443-6
pubmed: 15851350
Ann Biomed Eng. 2019 Feb;47(2):403-412
pubmed: 30465152
Heart Rhythm. 2012 Mar;9(3):330-4
pubmed: 22001707
Mayo Clin Proc. 2009 Mar;84(3):289-97
pubmed: 19252119