TolerantECG: A Foundation Model for Imperfect Electrocardiogram
This addresses diagnostic uncertainty in heart disease detection for medical applications, representing an incremental improvement in robustness.
The paper tackles the problem of ECG diagnostic errors due to noise or missing leads by proposing TolerantECG, a foundation model robust to such imperfections, which achieves top or second-best performance on the PTB-XL dataset and highest performance on the MIT-BIH Arrhythmia Database.
The electrocardiogram (ECG) is an essential and effective tool for diagnosing heart diseases. However, its effectiveness can be compromised by noise or unavailability of one or more leads of the standard 12-lead recordings, resulting in diagnostic errors or uncertainty. To address these challenges, we propose TolerantECG, a foundation model for ECG signals that is robust to noise and capable of functioning with arbitrary subsets of the standard 12-lead ECG. TolerantECG training combines contrastive and self-supervised learning frameworks to jointly learn ECG signal representations alongside their corresponding knowledge-retrieval-based text report descriptions and corrupted or lead-missing signals. Comprehensive benchmarking results demonstrate that TolerantECG consistently ranks as the best or second-best performer across various ECG signal conditions and class levels in the PTB-XL dataset, and achieves the highest performance on the MIT-BIH Arrhythmia Database.