Transferring Clinical Knowledge into ECGs Representation

TL;DR

This paper introduces a three-stage training method that transfers clinical knowledge from multimodal data into ECG models, improving interpretability and accuracy for clinical diagnosis without needing additional data at inference.

Contribution

The novel three-stage training paradigm effectively incorporates multimodal clinical data into ECG models, enhancing interpretability and diagnostic performance.

Findings

Outperforms standard signal-only models in multi-label diagnosis classification.

Bridges performance gap towards fully multimodal models using only ECG at inference.

Provides physiologically grounded explanations for model predictions.

Abstract

Deep learning models have shown high accuracy in classifying electrocardiograms (ECGs), but their black box nature hinders clinical adoption due to a lack of trust and interpretability. To address this, we propose a novel three-stage training paradigm that transfers knowledge from multimodal clinical data (laboratory exams, vitals, biometrics) into a powerful, yet unimodal, ECG encoder. We employ a self-supervised, joint-embedding pre-training stage to create an ECG representation that is enriched with contextual clinical information, while only requiring the ECG signal at inference time. Furthermore, as an indirect way to explain the model's output we train it to also predict associated laboratory abnormalities directly from the ECG embedding. Evaluated on the MIMIC-IV-ECG dataset, our model outperforms a standard signal-only baseline in multi-label diagnosis classification and successfully bridges a substantial portion of the performance gap to a fully multimodal model that requires all data at inference. Our work demonstrates a practical and effective method for creating more accurate and trustworthy ECG classification models. By converting abstract predictions into physiologically grounded \emph{explanations}, our approach offers a promising path toward the safer integration of AI into clinical workflows.