Looking Beyond Accuracy: A Holistic Benchmark of ECG Foundation Models

TL;DR

This paper presents a comprehensive benchmarking framework for ECG foundation models, combining performance and representation analysis to evaluate their generalizability and robustness across diverse datasets and data scarcity scenarios.

Contribution

It introduces a novel benchmarking methodology that integrates performance metrics with representation-level analysis using SHAP and UMAP for ECG foundation models.

Findings

Benchmarking protocol reveals detailed insights into model representations.

Models show varying degrees of generalizability across datasets.

Representation analysis helps understand model robustness in data-scarce settings.

Abstract

The electrocardiogram (ECG) is a cost-effective, highly accessible and widely employed diagnostic tool. With the advent of Foundation Models (FMs), the field of AI-assisted ECG interpretation has begun to evolve, as they enable model reuse across different tasks by relying on embeddings. However, to responsibly employ FMs, it is crucial to rigorously assess to which extent the embeddings they produce are generalizable, particularly in error-sensitive domains such as healthcare. Although prior works have already addressed the problem of benchmarking ECG-expert FMs, they focus predominantly on the evaluation of downstream performance. To fill this gap, this study aims to find an in-depth, comprehensive benchmarking framework for FMs, with a specific focus on ECG-expert ones. To this aim, we introduce a benchmark methodology that complements performance-based evaluation with representation-level analysis, leveraging SHAP and UMAP techniques. Furthermore, we rely on the methodology for carrying out an extensive evaluation of several ECG-expert FMs pretrained via state-of-the-art techniques over different cross-continental datasets and data availability settings; this includes ones featuring data scarcity, a fairly common situation in real-world medical scenarios. Experimental results show that our benchmarking protocol provides a rich insight of ECG-expert FMs' embedded patterns, enabling a deeper understanding of their representational structure and generalizability.