Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AnyECG: Evolved ECG Foundation Model for Holistic Health Profiling

Jun Li, Hongling Zhu, Yujie Xiao, Qinghao Zhao, Yalei Ke, Gongzheng Tang, Guangkun Nie, Deyun Zhang, Jin Li, Canqing Yu, Shenda Hong

TL;DR

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.

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.

AnyECG: Evolved ECG Foundation Model for Holistic Health Profiling

TL;DR

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.

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.
Paper Structure (1 section, 3 equations, 6 figures)

This paper contains 1 section, 3 equations, 6 figures.

Table of Contents

  1. Diagnostic performance of AnyECG for ICD-10 diagnoses

Figures (6)

  • Figure 1: Overview of the development and results of AnyECG. (a) The source and composition of the dataset. The dataset we used included large-scale, multicenter, multinational ECG cohorts: 13,348,593 ECGs, 2,984,209 patients. (b) Representative results of AnyECG across different systems are presented. Outcome indicators for different diseases are shown across nine systems.
  • Figure 2: Boxplots for the overall internal test set performance of AnyECG on different disease systems.
  • Figure 3: Average diagnosis AUC values (y axis) as a function of training occurrences (x axis).
  • Figure 4: Prognostic stratification of major cardiometabolic cardiac events using AnyECG in the CKB cohort.
  • Figure 5: Prognostic stratification of systemic CKM diseases using AnyECG in the CKB cohort.
  • ...and 1 more figures