An Electrocardiogram Multi-task Benchmark with Comprehensive Evaluations and Insightful Findings

TL;DR

This paper evaluates the effectiveness of foundation models in ECG analysis, demonstrating their competitive performance and providing comprehensive insights into their capabilities and limitations for healthcare applications.

Contribution

It introduces a multi-task ECG benchmark and systematically compares foundation models with traditional deep learning models, offering new insights into their utility in physiological waveform analysis.

Findings

Foundation models achieve up to 80% accuracy in ECG tasks

Comprehensive analysis of model strengths and limitations

Publicly available dataset and code for further research

Abstract

In the process of patient diagnosis, non-invasive measurements are widely used due to their low risks and quick results. Electrocardiogram (ECG), as a non-invasive method to collect heart activities, is used to diagnose cardiac conditions. Analyzing the ECG typically requires domain expertise, which is a roadblock to applying artificial intelligence (AI) for healthcare. Through advances in self-supervised learning and foundation models, AI systems can now acquire and leverage domain knowledge without relying solely on human expertise. However, there is a lack of comprehensive analyses over the foundation models' performance on ECG. This study aims to answer the research question: "Are Foundation Models Useful for ECG Analysis?" To address it, we evaluate language/general time-series/ECG foundation models in comparison with time-series deep learning models. The experimental results show that general time-series/ECG foundation models achieve a top performance rate of 80%, indicating their effectiveness in ECG analysis. In-depth analyses and insights are provided along with comprehensive experimental results. This study highlights the limitations and potential of foundation models in advancing physiological waveform analysis. The data and code for this benchmark are publicly available at https://github.com/yuhaoxu99/ECGMultitasks-Benchmark.