TY  - EJOU
AU  - Mou, Qiuxiao 
AU  - Gui, Haoyu 
AU  - Tang, Xianghong 
AU  - Lu, Jianguang 

TI  - MCCGAA: Multimodal Channel Compression Graph Attention Alignment Network for ECG Zero-Shot Classification
T2  - Computers, Materials \& Continua

PY  - 2026
VL  - 87
IS  - 3
SN  - 1546-2226

AB  - Electrocardiogram (ECG) is a widely used non-invasive tool for diagnosing cardiovascular diseases. ECG zero-shot classification involves pre-training a model on a large dataset to classify unknown disease categories. However, existing ECG feature extraction networks often neglect key lead signals and spatial topology dependencies during cross-modal alignment. To address these issues, we propose a multimodal channel compression graph attention alignment network (MCCGAA). MCCGAA incorporates a channel attention module (CAM) to effectively integrate key lead features and a graph attention-based alignment network to capture spatial dependencies, enhancing cross-modal alignment. Additionally, MCCGAA employs a log-sum-exp loss function, improving classification performance and convergence over the original clip-style method. Experimental results show that MCCGAA outperforms current methods, achieving the highest classification accuracy across six publicly available datasets. MCCGAA holds promise for advancing ECG zero-shot classification and offering better decision support for researchers.
KW  - ECG zero-shot classification; contrastive learning; cross-modal alignment; graph attention network; channel attention mechanism

DO  - 10.32604/cmc.2026.076251