arXiv:2605. 29977v2 Announce Type: replace-cross Abstract: High-fidelity ECG interpretation is increasingly reliant on massive foundation models, yet their deployment in clinical edge-care remains hindered by extreme computational demands.
By Dang Nguyen Hong, Nhi Ngoc-Yen Nguyen, Huy-Hieu Pham
The paper introduces Graph-CMMC, a graph-based pseudo‑multimodal contrastive learning framework for 12‑lead ECG representations. It transforms ECG waveforms into Gramian Angular Difference Field (GADF) images to create complementary views, then aligns these views while modeling inter‑lead dependencies with a graph module. Experiments on coronary artery occlusion classification show that Graph-CMMC performs competitively with supervised methods, highlighting the value of GADF representations and explicit graph modeling for robust ECG analysis.
By Mengyu Wang, Kozo Okada, Takafumi Goto, Natsuko Jinba, Hiroki Yamaya, Kiyoshi Hibi, Tomoki Hamagami
The paper introduces LYNX-ECG, a graph neural network that represents each heartbeat as a sparse visibility graph of timestamped turning points, enabling accurate ECG classification while providing auditable, clinically grounded explanations. On the CODE-Test dataset, LYNX-ECG achieves a macro F1 score of 0.889, outperforming five baselines including the ECGFounder foundation model, and its graphs require only about 14% of the storage needed for full-sample graphs. Because each graph node corresponds to a specific ECG time, clinicians can delete waveform regions or alter beat timing to audit predictions, with the clinically expected region proving strongest evidence in over 90% of correct conduction disorder predictions.
"whyItMatters":"The model’s ability to pair high classification accuracy with transparent, testable explanations directly addresses the need for clinically interpretable AI in ECG analysis."
By Artur Xavier, Guilherme Henrique Gomes Evangelista, Aitazaz Khan, Antonio Luiz Pinho Ribeiro, Mohammed J. Zaki, Srinivasan Parthasarathy, Wagner Meira Jr
BEAT-Net is a supervised biomimetic framework for ECG diagnosis that incorporates QRS-centered tokenization and a hierarchical architecture mirroring a cardiologist’s workflow. It processes heartbeat sequences through morphological, spatial, temporal, and transformer-based stages, achieving an AUC of 0.924 on large benchmarks while using only 0.7 million parameters. The model outperforms the 39.5‑million‑parameter HeartLang foundation model on morphological form classification and demonstrates superior cross‑dataset generalization with only 35% of the training data.
By Runze Ma, Haonan Lyu, Shunbo Jia, Qiang Yang, Muzi Xu, Jiaqi Zhang, Zihe Luo, Caizhi Liao
arXiv:2607. 01145v2 Announce Type: replace Abstract: Data analysis in the medical domain often encounters scenarios involving a limited target dataset and a large, unannotated dataset with a general distribution.
By Siwon Kim
arXiv:2606. 10802v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) typically require extensive datasets for effective training.
By Naoki Nonaka, Jun Seita