AnyECG: Evolved ECG Foundation Model for Holistic Health Profiling

TL;DR

AnyECG is a comprehensive AI model trained on millions of ECGs that can detect a wide range of diseases, predict future health risks, and identify comorbidities, advancing holistic health profiling.

Contribution

This work introduces AnyECG, a novel foundation model for holistic health profiling using ECGs, capable of systemic disease detection and long-term risk prediction, surpassing prior single-disease focused models.

Findings

Achieved AUROC > 0.7 for 306 diseases

Demonstrated robust prediction of future disease risks

Revealed novel disease associations and comorbidity patterns

Abstract

Background: Artificial intelligence enabled electrocardiography (AI-ECG) has demonstrated the ability to detect diverse pathologies, but most existing models focus on single disease identification, neglecting comorbidities and future risk prediction. Although ECGFounder expanded cardiac disease coverage, a holistic health profiling model remains needed. Methods: We constructed a large multicenter dataset comprising 13.3 million ECGs from 2.98 million patients. Using transfer learning, ECGFounder was fine-tuned to develop AnyECG, a foundation model for holistic health profiling. Performance was evaluated using external validation cohorts and a 10-year longitudinal cohort for current diagnosis, future risk prediction, and comorbidity identification. Results: AnyECG demonstrated systemic predictive capability across 1172 conditions, achieving an AUROC greater than 0.7 for 306 diseases. The model revealed novel disease associations, robust comorbidity patterns, and future disease risks. Representative examples included high diagnostic performance for hyperparathyroidism (AUROC 0.941), type 2 diabetes (0.803), Crohn disease (0.817), lymphoid leukemia (0.856), and chronic obstructive pulmonary disease (0.773). Conclusion: The AnyECG foundation model provides substantial evidence that AI-ECG can serve as a systemic tool for concurrent disease detection and long-term risk prediction.