Towards Automated Diagnosis of Inherited Arrhythmias: Combined Arrhythmia Classification Using Lead-Aware Spatial Attention Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sigfstead, Sophie, Jiang, River, Davies, Brianna, Laksman, Zachary W. M., Cadrin-Tourigny, Julia, Tadros, Rafik, Khan, Habib, Atallah, Joseph, Steinberg, Christian, Sanatani, Shubhayan, Talajic, Mario, Krishnan, Rahul, Krahn, Andrew D., Cheung, Christopher C.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914247673380864
author Sigfstead, Sophie
Jiang, River
Davies, Brianna
Laksman, Zachary W. M.
Cadrin-Tourigny, Julia
Tadros, Rafik
Khan, Habib
Atallah, Joseph
Steinberg, Christian
Sanatani, Shubhayan
Talajic, Mario
Krishnan, Rahul
Krahn, Andrew D.
Cheung, Christopher C.
author_facet Sigfstead, Sophie
Jiang, River
Davies, Brianna
Laksman, Zachary W. M.
Cadrin-Tourigny, Julia
Tadros, Rafik
Khan, Habib
Atallah, Joseph
Steinberg, Christian
Sanatani, Shubhayan
Talajic, Mario
Krishnan, Rahul
Krahn, Andrew D.
Cheung, Christopher C.
contents Arrhythmogenic right ventricular cardiomyopathy (ARVC) and long QT syndrome (LQTS) are inherited arrhythmia syndromes associated with sudden cardiac death. Deep learning shows promise for ECG interpretation, but multi-class inherited arrhythmia classification with clinically grounded interpretability remains underdeveloped. Our objective was to develop and validate a lead-aware deep learning framework for multi-class (ARVC vs LQTS vs control) and binary inherited arrhythmia classification, and to determine optimal strategies for integrating ECG foundation models within arrhythmia screening tools. We assembled a 13-center Canadian cohort (645 patients; 1,344 ECGs). We evaluated four ECG foundation models using three transfer learning approaches: linear probing, fine-tuning, and combined strategies. We developed lead-aware spatial attention networks (LASAN) and assessed integration strategies combining LASAN with foundation models. Performance was compared against the established foundation model baselines. Lead-group masking quantified disease-specific lead dependence. Fine-tuning outperformed linear probing and combined strategies across all foundation models (mean macro-AUROC 0.904 vs 0.825). The best lead-aware integrations achieved near-ceiling performance (HuBERT-ECG hybrid: macro-AUROC 0.990; ARVC vs control AUROC 0.999; LQTS vs control AUROC 0.994). Lead masking demonstrated physiologic plausibility: V1-V3 were most critical for ARVC detection (4.54% AUROC reduction), while lateral leads were preferentially important for LQTS (2.60% drop). Lead-aware architectures achieved state-of-the-art performance for inherited arrhythmia classification, outperforming all existing published models on both binary and multi-class tasks while demonstrating clinically aligned lead dependence. These findings support potential utility for automated ECG screening pending validation.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07124
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Automated Diagnosis of Inherited Arrhythmias: Combined Arrhythmia Classification Using Lead-Aware Spatial Attention Networks
Sigfstead, Sophie
Jiang, River
Davies, Brianna
Laksman, Zachary W. M.
Cadrin-Tourigny, Julia
Tadros, Rafik
Khan, Habib
Atallah, Joseph
Steinberg, Christian
Sanatani, Shubhayan
Talajic, Mario
Krishnan, Rahul
Krahn, Andrew D.
Cheung, Christopher C.
Machine Learning
I.2.6; I.5.1; J.3
Arrhythmogenic right ventricular cardiomyopathy (ARVC) and long QT syndrome (LQTS) are inherited arrhythmia syndromes associated with sudden cardiac death. Deep learning shows promise for ECG interpretation, but multi-class inherited arrhythmia classification with clinically grounded interpretability remains underdeveloped. Our objective was to develop and validate a lead-aware deep learning framework for multi-class (ARVC vs LQTS vs control) and binary inherited arrhythmia classification, and to determine optimal strategies for integrating ECG foundation models within arrhythmia screening tools. We assembled a 13-center Canadian cohort (645 patients; 1,344 ECGs). We evaluated four ECG foundation models using three transfer learning approaches: linear probing, fine-tuning, and combined strategies. We developed lead-aware spatial attention networks (LASAN) and assessed integration strategies combining LASAN with foundation models. Performance was compared against the established foundation model baselines. Lead-group masking quantified disease-specific lead dependence. Fine-tuning outperformed linear probing and combined strategies across all foundation models (mean macro-AUROC 0.904 vs 0.825). The best lead-aware integrations achieved near-ceiling performance (HuBERT-ECG hybrid: macro-AUROC 0.990; ARVC vs control AUROC 0.999; LQTS vs control AUROC 0.994). Lead masking demonstrated physiologic plausibility: V1-V3 were most critical for ARVC detection (4.54% AUROC reduction), while lateral leads were preferentially important for LQTS (2.60% drop). Lead-aware architectures achieved state-of-the-art performance for inherited arrhythmia classification, outperforming all existing published models on both binary and multi-class tasks while demonstrating clinically aligned lead dependence. These findings support potential utility for automated ECG screening pending validation.
title Towards Automated Diagnosis of Inherited Arrhythmias: Combined Arrhythmia Classification Using Lead-Aware Spatial Attention Networks
topic Machine Learning
I.2.6; I.5.1; J.3
url https://arxiv.org/abs/2601.07124