HCM-PhenotypeNet: Deep Multimodal Phenotyping of Hypertrophic Cardiomyopathy from Echocardiographic Video and Clinical Data
- 1Imam Mohammad Ibn Saud Islamic University (IMSIU)
Abstract
BackgroundHypertrophic cardiomyopathy (HCM) is a heterogeneous condition with variable morphology and symptoms, leading to adverse outcomes such as atrial fibrillation, heart failure and sudden cardiac death. Data-driven phenotyping may help refine risk stratification and guide management.
ObjectivesTo propose an automated machine learning framework (HCM-PhenotypeNet) that integrates echocardiographic video and clinical data to identify clinically meaningful HCM phenotypes.
MethodsWe developed a multimodal pipeline using a deep neural network to extract features from 1,553 echocardiography video clips, combined with >100 clinical variables from 156 HCM patients. Patient-level vectors were reduced using UMAP and clustered using Deep Embedded Clustering (DEC). Cluster quality was assessed using internal validation metrics, and clusters were characterized through statistical comparisons and association rule mining.
ResultsThe cohort included 156 HCM patients (mean age 53.6 {+/-} 13.9 years, 40.4% female) with pre-served systolic function and diverse racial/ethnic backgrounds. The optimal pipeline (DEC with 4 clusters) yielded phenogroups with strong separation (silhouette{approx} 0.89): (A) Advanced Obstructive/Metabolic phenotype; (B) Early-onset, Genotype Positive phenotype; (C) Late-onset, mild non-obstructive phenotype; and (D) Hypertrophic Heart Failure-predominant phenotype. Whilst there was no mortality difference, there was a trend towards increased heart failure and atrial fibrillation burden in the Advanced Obstructive/Metabolic and Heart Failure-predominant subgroups.
ConclusionsHCM-PhenotypeNet enabled automated identification of four clinically relevant HCM subgroups. These phenogroups highlight the heterogeneity of HCM and may support personalized risk stratification and management but require validation in larger cohorts.
Related
- Atypical echocardiographic phenotype of end-stage hypertrophic cardiomyopathy: a case series
- Non-Echocardiographic Evaluation of Hypertrophic Cardiomyopathy
- Multimodality Imaging in Hypertrophic Cardiomyopathy: From Phenotyping to Precision Clinical Management.
- Contrasting Echocardiographic Trajectories with and Without Tafamidis in Wild-Type Transthyretin Amyloid Cardiomyopathy: A Real-World Observational Study with Two-Dimensional Speckle-Tracking Analysis
- A late bloom at the apex: development of apical hypertrophic cardiomyopathy phenotype in advanced age
BibTeX
@misc{almadani2026hcmphenotypenet,
title = {{HCM-PhenotypeNet: Deep Multimodal Phenotyping of Hypertrophic Cardiomyopathy from Echocardiographic Video and Clinical Data}},
author = {A. S. Almadani and A. Sarwar and E. Agu and M. Ahluwalia and J. Kpodonu},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.13.26362954},
url = {https://www.medrxiv.org/content/10.64898/2026.09.13.26362954v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - HCM-PhenotypeNet: Deep Multimodal Phenotyping of Hypertrophic Cardiomyopathy from Echocardiographic Video and Clinical Data
AU - A. S. Almadani
AU - A. Sarwar
AU - E. Agu
AU - M. Ahluwalia
AU - J. Kpodonu
PY - 2026
DA - 2026/09/13
PB - medRxiv
DO - 10.64898/2026.09.13.26362954
UR - https://www.medrxiv.org/content/10.64898/2026.09.13.26362954v1
AB - BackgroundHypertrophic cardiomyopathy (HCM) is a heterogeneous condition with variable morphology and symptoms, leading to adverse outcomes such as atrial fibrillation, heart failure and sudden cardiac death. Data-driven phenotyping may help refine risk stratification and guide management. ObjectivesTo propose an automated machine learning framework (HCM-PhenotypeNet) that integrates echocardiographic video and clinical data to identify clinically meaningful HCM phenotypes. MethodsWe developed a multimodal pipeline using a deep neural network to extract features from 1,553 echocardiography video clips, combined with >100 clinical variables from 156 HCM patients. Patient-level vectors were reduced using UMAP and clustered using Deep Embedded Clustering (DEC). Cluster quality was assessed using internal validation metrics, and clusters were characterized through statistical comparisons and association rule mining. ResultsThe cohort included 156 HCM patients (mean age 53.6 {+/-} 13.9 years, 40.4% female) with pre-served systolic function and diverse racial/ethnic backgrounds. The optimal pipeline (DEC with 4 clusters) yielded phenogroups with strong separation (silhouette{approx} 0.89): (A) Advanced Obstructive/Metabolic phenotype; (B) Early-onset, Genotype Positive phenotype; (C) Late-onset, mild non-obstructive phenotype; and (D) Hypertrophic Heart Failure-predominant phenotype. Whilst there was no mortality difference, there was a trend towards increased heart failure and atrial fibrillation burden in the Advanced Obstructive/Metabolic and Heart Failure-predominant subgroups. ConclusionsHCM-PhenotypeNet enabled automated identification of four clinically relevant HCM subgroups. These phenogroups highlight the heterogeneity of HCM and may support personalized risk stratification and management but require validation in larger cohorts.
ER -