Revisiting Abnormalities of Ventricular Depolarization: Redefining Phenotypes and Associated Outcomes Using Tree‐Based Dimensionality Reduction
Authors:
- Mehak GurnaniMGMehak Gurnani
- Konstantinos PatlatzoglouKPKonstantinos Patlatzoglou
- Joseph BarkerJBJoseph Barker
- Libor PastikaLPLibor Pastika
- Boroumand ZeidaabadiBZBoroumand Zeidaabadi
- Paolo InglesePIPaolo Inglese
- Ahran D. ArnoldAAAhran D. Arnold
- Declan O'REganDODeclan O'REgan
- Zachary WhinnettZWZachary Whinnett
Open Access
- 1 July 2025
- journal article
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 14 (13) , e040814
Abstract
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 P 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.Keywords
This publication has 46 references indexed in Scilit:
- Machine learning of ECG waveforms and cardiac magnetic resonance for response and survival after cardiac resynchronization therapyComputers in Biology and Medicine, 2024
- BRAVEHEART: Open-source software for automated electrocardiographic and vectorcardiographic analysisComputer Methods and Programs in Biomedicine, 2023
- Artificial intelligence–enabled electrocardiogram to distinguish atrioventricular re-entrant tachycardia from atrioventricular nodal re-entrant tachycardiaCardiovascular Digital Health Journal, 2023
- Characteristics and long‐term prognosis of patients with reduced, mid‐range, and preserved ejection fraction: A systemic review and meta‐analysisClinical Cardiology, 2022
- Clinical and prognostic implications of phenomapping in patients with heart failure receiving cardiac resynchronization therapyArchives of Cardiovascular Diseases, 2021
- Why Test for Proportional Hazards?JAMA, 2020
- The Prognostic Significance of Right Bundle Branch Block: A Meta‐analysis of Prospective Cohort StudiesClinical Cardiology, 2015
- Ventricular Conduction Defects and the Risk of Incident Heart Failure in the Atherosclerosis Risk in Communities (ARIC) StudyJournal of Cardiac Failure, 2015
- Defining Left Bundle Branch Block in the Era of Cardiac Resynchronization TherapyThe American Journal of Cardiology, 2011
- CLINICAL OBSERVATIONS ON DEFECTIVE CONDUCTION IN THE BRANCHES OF THE AURICULOVENTRICULAR BUNDLEArchives of internal medicine (1908), 1914