C-MELT: Contrastive Enhanced Masked Auto-Encoders for ECG-Language Pre-Training

Accurate interpretation of Electrocardiogram (ECG) signals is pivotal for diagnosing cardiovascular diseases. Integrating ECG signals with their accompanying textual reports holds immense potential to enhance clinical diagnostics through the combination of physiological data and qualitative insights. However, this integration faces significant challenges due to inherent modality disparities and the scarcity of labeled data for robust cross-modal learning. To address these obstacles, we propose C-MELT, a novel framework that pre-trains ECG and text data using a contrastive masked auto-encoder architecture. C-MELT uniquely combines the strengths of generative with enhanced discriminative capabilities to achieve robust cross-modal representations. This is accomplished through masked modality modeling, specialized loss functions, and an improved negative sampling strategy tailored for cross-modal alignment. Extensive experiments on five public datasets across diverse downstream tasks demonstrate that C-MELT significantly outperforms existing methods, achieving 15% and 2% increases in linear probing and zero-shot performance over state-of-the-art models, respectively. These results highlight the effectiveness of C-MELT, underscoring its potential to advance automated clinical diagnostics through multi-modal representations. Electrocardiograms (ECGs), obtained through non-invasive electrode placement, provide a critical window into the heart's electrical activity by measuring voltage differences across specific anatomical regions. The standard 12-lead ECG, which captures unique electrical potential differences from each lead, plays a vital role in diagnosing a wide spectrum of cardiac conditions, like arrhythmias. In recent years, significant progress has been made in leveraging deep learning techniques for automated ECG interpretation (Yan et al., 2019; Ebrahimi et al., 2020; Siontis et al., 2021).