Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality Reduction

Background Abnormal ventricular depolarization, evident as a broad QRS complex on an ECG, is traditionally categorized into left bundle‐branch block (LBBB) and right bundle‐branch block or nonspecific intraventricular conduction delay. This categorization, although physiologically accurate, may fail...

Full description

Saved in:
Bibliographic Details
Main Authors: Mehak Gurnani, Konstantinos Patlatzoglou, Joseph Barker, Derek Bivona, Libor Pastika, Ewa Sieliwonczyk, Boroumand Zeidaabadi, Paolo Inglese, Lara Curran, Ahran D. Arnold, Declan O'Regan, Zachary Whinnett, Kenneth C. Bilchick, Nicholas S. Peters, Daniel B. Kramer, Jonathan W. Waks, Arunashis Sau, Fu Siong Ng
Format: Article
Language:English
Published: Wiley 2025-07-01
Series:Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease
Subjects:
Online Access:https://www.ahajournals.org/doi/10.1161/JAHA.124.040814
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850075188501151744
author Mehak Gurnani
Konstantinos Patlatzoglou
Joseph Barker
Derek Bivona
Libor Pastika
Ewa Sieliwonczyk
Boroumand Zeidaabadi
Paolo Inglese
Lara Curran
Ahran D. Arnold
Declan O'Regan
Zachary Whinnett
Kenneth C. Bilchick
Nicholas S. Peters
Daniel B. Kramer
Jonathan W. Waks
Arunashis Sau
Fu Siong Ng
author_facet Mehak Gurnani
Konstantinos Patlatzoglou
Joseph Barker
Derek Bivona
Libor Pastika
Ewa Sieliwonczyk
Boroumand Zeidaabadi
Paolo Inglese
Lara Curran
Ahran D. Arnold
Declan O'Regan
Zachary Whinnett
Kenneth C. Bilchick
Nicholas S. Peters
Daniel B. Kramer
Jonathan W. Waks
Arunashis Sau
Fu Siong Ng
author_sort Mehak Gurnani
collection DOAJ
description Background Abnormal ventricular depolarization, evident as a broad QRS complex on an ECG, is traditionally categorized into left bundle‐branch block (LBBB) and right bundle‐branch block or nonspecific intraventricular conduction delay. This categorization, although physiologically accurate, may fail to capture the nuances of diseases subtypes. Methods We used unsupervised machine learning to identify and characterize novel broad QRS phenogroups. First, we trained a variational autoencoder on 1.1 million ECGs and discovered 51 latent features that showed high disentanglement and ECG reconstruction accuracy. We then extracted these features from 42 538 ECGs with QRS durations >120 milliseconds and employed a reversed graph embedding method to model population heterogeneity as a tree structure with different branches representing phenogroups. Results Six phenogroups were identified, including phenogroups of right bundle‐branch block and LBBB with varying risk of cardiovascular disease and mortality. The higher risk right bundle‐branch block phenogroup exhibited increased risk of cardiovascular death (adjusted hazard ratio [aHR], 1.46 [1.30–1.63], P<0.0001) and all‐cause mortality (aHR, 1.24 [1.16–1.33], P<0.0001) compared with the baseline phenogroup. Within LBBB ECGs, tree position predicted future cardiovascular disease risk differentially. Additionally, for subjects with LBBB undergoing cardiac resynchronization therapy, tree position predicted cardiac resynchronization therapy response independent of covariates, including QRS duration (adjusted odds ratio [aOR], 0.47 [0.25–0.86], P<0.05). Conclusions Our findings challenge the current paradigm, highlighting the potential for these phenogroups to enhance cardiac resynchronization therapy patient selection for subjects with LBBB and guide investigation and follow‐up strategies for subjects with higher risk right bundle‐branch block.
format Article
id doaj-art-71ee1545ec854ec2bfefecd204d24228
institution DOAJ
issn 2047-9980
language English
publishDate 2025-07-01
publisher Wiley
record_format Article
series Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease
spelling doaj-art-71ee1545ec854ec2bfefecd204d242282025-08-20T02:46:24ZengWileyJournal of the American Heart Association: Cardiovascular and Cerebrovascular Disease2047-99802025-07-01141310.1161/JAHA.124.040814Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality ReductionMehak Gurnani0Konstantinos Patlatzoglou1Joseph Barker2Derek Bivona3Libor Pastika4Ewa Sieliwonczyk5Boroumand Zeidaabadi6Paolo Inglese7Lara Curran8Ahran D. Arnold9Declan O'Regan10Zachary Whinnett11Kenneth C. Bilchick12Nicholas S. Peters13Daniel B. Kramer14Jonathan W. Waks15Arunashis Sau16Fu Siong Ng17National Heart and Lung Institute, Imperial College London London UKNational Heart and Lung Institute, Imperial College London London UKNational Heart and Lung Institute, Imperial College London London UKDepartment of Biomedical Engineering University of Virginia Charlottesville VA USANational Heart and Lung Institute, Imperial College London London UKNational Heart and Lung Institute, Imperial College London London UKNational Heart and Lung Institute, Imperial College London London UKIstituto Italiano di Tecnologia Genoa ItalyMRC Laboratory of Medical Sciences Imperial College London London UKNational Heart and Lung Institute, Imperial College London London UKMRC Laboratory of Medical Sciences Imperial College London London UKNational Heart and Lung Institute, Imperial College London London UKDepartment of Medicine University of Virginia Health System Charlottesville VA USANational Heart and Lung Institute, Imperial College London London UKRichard A. and Susan F. Smith Center for Outcomes Research in Cardiology, Beth Israel Deaconess Medical Center Harvard Medical School Boston MA USAHarvard‐Thorndike Electrophysiology Institute, Beth Israel Deaconess Medical Center Harvard Medical School Boston MA USANational Heart and Lung Institute, Imperial College London London UKNational Heart and Lung Institute, Imperial College London London UKBackground Abnormal ventricular depolarization, evident as a broad QRS complex on an ECG, is traditionally categorized into left bundle‐branch block (LBBB) and right bundle‐branch block or nonspecific intraventricular conduction delay. This categorization, although physiologically accurate, may fail to capture the nuances of diseases subtypes. Methods We used unsupervised machine learning to identify and characterize novel broad QRS phenogroups. First, we trained a variational autoencoder on 1.1 million ECGs and discovered 51 latent features that showed high disentanglement and ECG reconstruction accuracy. We then extracted these features from 42 538 ECGs with QRS durations >120 milliseconds and employed a reversed graph embedding method to model population heterogeneity as a tree structure with different branches representing phenogroups. Results Six phenogroups were identified, including phenogroups of right bundle‐branch block and LBBB with varying risk of cardiovascular disease and mortality. The higher risk right bundle‐branch block phenogroup exhibited increased risk of cardiovascular death (adjusted hazard ratio [aHR], 1.46 [1.30–1.63], P<0.0001) and all‐cause mortality (aHR, 1.24 [1.16–1.33], P<0.0001) compared with the baseline phenogroup. Within LBBB ECGs, tree position predicted future cardiovascular disease risk differentially. Additionally, for subjects with LBBB undergoing cardiac resynchronization therapy, tree position predicted cardiac resynchronization therapy response independent of covariates, including QRS duration (adjusted odds ratio [aOR], 0.47 [0.25–0.86], P<0.05). Conclusions Our findings challenge the current paradigm, highlighting the potential for these phenogroups to enhance cardiac resynchronization therapy patient selection for subjects with LBBB and guide investigation and follow‐up strategies for subjects with higher risk right bundle‐branch block.https://www.ahajournals.org/doi/10.1161/JAHA.124.040814bundle‐branch blockclusteringECGmachine learningphenotyping
spellingShingle Mehak Gurnani
Konstantinos Patlatzoglou
Joseph Barker
Derek Bivona
Libor Pastika
Ewa Sieliwonczyk
Boroumand Zeidaabadi
Paolo Inglese
Lara Curran
Ahran D. Arnold
Declan O'Regan
Zachary Whinnett
Kenneth C. Bilchick
Nicholas S. Peters
Daniel B. Kramer
Jonathan W. Waks
Arunashis Sau
Fu Siong Ng
Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality Reduction
Journal of the American Heart Association: Cardiovascular and Cerebrovascular Disease
bundle‐branch block
clustering
ECG
machine learning
phenotyping
title Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality Reduction
title_full Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality Reduction
title_fullStr Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality Reduction
title_full_unstemmed Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality Reduction
title_short Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality Reduction
title_sort revisiting abnormalities of ventricular depolarization redefining phenotypes and associated outcomes using tree based dimensionality reduction
topic bundle‐branch block
clustering
ECG
machine learning
phenotyping
url https://www.ahajournals.org/doi/10.1161/JAHA.124.040814
work_keys_str_mv AT mehakgurnani revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT konstantinospatlatzoglou revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT josephbarker revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT derekbivona revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT liborpastika revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT ewasieliwonczyk revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT boroumandzeidaabadi revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT paoloinglese revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT laracurran revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT ahrandarnold revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT declanoregan revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT zacharywhinnett revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT kennethcbilchick revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT nicholasspeters revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT danielbkramer revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT jonathanwwaks revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT arunashissau revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction
AT fusiongng revisitingabnormalitiesofventriculardepolarizationredefiningphenotypesandassociatedoutcomesusingtreebaseddimensionalityreduction