A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography

2026-05-25

AI Summary

This work addresses the limited generalization of existing AI models in electrocardiogram (ECG) analysis, particularly their inability to reliably detect subtle or rare cardiovascular conditions across diverse populations. To overcome this, the authors propose ECGCLIP, the first framework to introduce signal–language contrastive pretraining to the ECG domain. By leveraging large-scale paired ECG recordings and diagnostic reports, ECGCLIP aligns physiological signals with clinical semantics using a ResNet-based architecture enhanced with interpretability visualizations. The model achieves state-of-the-art performance across 89 downstream tasks—including 45 ECG diagnoses, 39 echocardiographic metrics, and 5 rare diseases—and matches full-data baselines using only 10% of the training data, demonstrating substantially improved generalization and data efficiency.

Abstract

Electrocardiography (ECG) is central to cardiovascular care, but conventional AI models are often restricted to common arrhythmias and may generalize poorly across populations or clinically subtle diseases. We developed ECG Contrastive Language-Image Pre-training (ECGCLIP), a signal-language contrastive learning framework that aligns ECG waveforms with expert diagnostic reports. ECGCLIP was pre-trained on 2,837,962 ECG studies from 1,324,856 patients and evaluated on a held-out internal test set plus nine independent external cohorts comprising about 1.5 million ECGs. Evaluation covered 89 downstream tasks, including 45 ECG diagnoses, 39 echocardiographic targets, and 5 rare cardiac diseases, using PRAUC as the primary metric. ECGCLIP consistently improved performance over random initialization and Merl-R18 baselines. On the internal test set, ECGCLIP-R34 achieved strong performance for atrial fibrillation (PRAUC 0.900) and ST-segment elevation myocardial infarction (PRAUC 0.383), with robust generalization across all external cohorts. It also improved low-prevalence and diagnostically elusive diseases, including Ebstein anomaly, constrictive pericarditis, dextrocardia, and cardiac amyloidosis, with internal PRAUC values of 0.253, 0.175, 0.121, and 0.201, respectively. ECGCLIP was data efficient, matching or exceeding full-dataset baseline performance with only 10% of training data. Feature visualization and saliency analysis suggested clinically meaningful representations aligned with established electrocardiographic criteria. These findings indicate that large-scale ECG-report contrastive pre-training can expand routine ECG interpretation beyond common arrhythmias toward broad cardiovascular assessment and opportunistic screening of echocardiographic and rare conditions.

Problem

• electrocardiography
• cardiovascular assessment
• rare cardiac diseases
• generalization
• broad-spectrum diagnosis

Innovation

• contrastive learning
• ECG-language alignment
• broad-spectrum cardiovascular assessment
• data-efficient pretraining
• rare cardiac disease detection