Interpretable ECG manifolds link longitudinal electrical phenotypes to heart-failure risk in hypertrophic cardiomyopathy
- 1Universita di Pavia
Abstract
Hypertrophic cardiomyopathy (HCM) produces heterogeneous electrical phenotypes whose continuous organization, longitudinal evolution and clinical relevance remain poorly defined. We developed complementary variational-autoencoder representations to map HCM ECG morphology relative to physiological variation and characterize within-subject change. Using 5,194 normal-reference ECGs and 2,594 longitudinal visits from 650 individuals with HCM, we found that HCM overlapped the physiological manifold but extended towards its periphery, while an HCM-oriented manifold largely reorganized shared electrical modes. Mixed-effects models identified longitudinal drift in selected phenotypic axes. A lateral/frontal QRS-force coordinate remained time-dependent after censoring septal reduction therapy, atrial fibrillation and pacing, and lower values were associated with subsequent heart-failure risk in baseline and time-updated analyses. A time-conditioned change VAE identified four interpretable within-subject modes aligned with longer-term trajectories. Sarcomeric genotype was associated with phenotype position but not trajectory rate.
Related
- A late bloom at the apex: development of apical hypertrophic cardiomyopathy phenotype in advanced age
- Research trends and hotspot analysis of sudden cardiac death in hypertrophic cardiomyopathy : A bibliometric analysis
- Managing a mavacamten non-responder in obstructive hypertrophic cardiomyopathy: A case report
- Percutaneous endomyocardial ablation as a septal reduction strategy in symptomatic obstructive hypertrophic cardiomyopathy: A 20-year single-center observational experience.
- Transatrial air-assisted epicardial ventricular tachycardia ablation for hypertrophic cardiomyopathy and management of postprocedural right atrial thrombus.
BibTeX
@misc{cerveri2026interpretable,
title = {{Interpretable ECG manifolds link longitudinal electrical phenotypes to heart-failure risk in hypertrophic cardiomyopathy}},
author = {P. Cerveri and M. H. Taconne and V. Corino and L. Mainardi},
howpublished = {medRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.02.26367092},
url = {https://www.medrxiv.org/content/10.64898/2026.11.02.26367092v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Interpretable ECG manifolds link longitudinal electrical phenotypes to heart-failure risk in hypertrophic cardiomyopathy
AU - P. Cerveri
AU - M. H. Taconne
AU - V. Corino
AU - L. Mainardi
PY - 2026
DA - 2026/11/02
PB - medRxiv
DO - 10.64898/2026.11.02.26367092
UR - https://www.medrxiv.org/content/10.64898/2026.11.02.26367092v1
AB - Hypertrophic cardiomyopathy (HCM) produces heterogeneous electrical phenotypes whose continuous organization, longitudinal evolution and clinical relevance remain poorly defined. We developed complementary variational-autoencoder representations to map HCM ECG morphology relative to physiological variation and characterize within-subject change. Using 5,194 normal-reference ECGs and 2,594 longitudinal visits from 650 individuals with HCM, we found that HCM overlapped the physiological manifold but extended towards its periphery, while an HCM-oriented manifold largely reorganized shared electrical modes. Mixed-effects models identified longitudinal drift in selected phenotypic axes. A lateral/frontal QRS-force coordinate remained time-dependent after censoring septal reduction therapy, atrial fibrillation and pacing, and lower values were associated with subsequent heart-failure risk in baseline and time-updated analyses. A time-conditioned change VAE identified four interpretable within-subject modes aligned with longer-term trajectories. Sarcomeric genotype was associated with phenotype position but not trajectory rate.
ER -