TAMER: A Tri-Modal Contrastive Alignment and Multi-Scale Embedding Refinement Framework for Zero-Shot ECG Diagnosis

Cardiovascular disease (CVD) diagnosis relies heavily on electrocardiograms (ECGs). However, most existing selfsupervised uni-modal methods suffer from limited representational capacity, while multi-modal frameworks are hindered by coarse-grained semantic alignment across modalities, thus restricting their generalizability in clinical settings. To address these limitations, we propose TAMER, a Tri-modal contrastive Alignment and Multiscale Embedding Refinement framework that jointly models ECG recordings, spectrograms, and diagnostic reports. TAMER is composed of three key components: First, the trimodal feature encoding and projection (TFEP) module employs modality-specific encoders to extract global and local features from ECG recordings, spectrograms, and diagnostic reports, and projects them into latent spaces. Then, the global-local temporal-spectral alignment (GLTSA) module captures complementary rhythm-and wave-level characteristics via contrastive alignment and attentive interaction between temporal and spectral modalities. Finally, the reportaware alignment and refinement (RAAR) module performs diagnostic-level alignment and wave-level refinement with clinical reports, enabling semantic enrichment of ECG representations. Extensive experiments on three public ECG datasets demonstrate that TAMER achieves state-of-theart zero-shot classification performance (AUC: 81.2%) and strong cross-domain generalization (AUC: 83.1%), outperforming existing uni-modal and multi-modal baseline methods.The source code is available at https://github.