The study investigates how different tokenization methods affect ECG Transformer models by comparing eight strategies across four backbone architectures on the CPSC2018 classification task. Physiology-aware tokenizations such as Median-beat and HeartLang achieve higher mean macro-AUCs (0.893 and 0.889) than point-wise and patch-wise approaches (0.822 and 0.824), while also reducing sequence length and training memory usage. Combining the two physiology-aware representations further improves macro-AUC by 8.2%.
By Jiawei Li, Fabio Bonassi, Johan Sundstr\"om, Thomas B. Sch\"on, Ant\^onio H. Ribeiro
The paper presents a hybrid CNN–state‑space–attention backbone designed for 12‑lead ECG classification, combining early waveform tokenization, mixed temporal dynamics modeling, and late global attention. It introduces an ECG‑oriented Joint‑Embedding Predictive Pretraining (JEPA) that samples span masks at latent resolution and predicts clean latent targets via a momentum encoder, avoiding waveform reconstruction. Experiments on CPSC2018, Chapman‑Shaoxing, and PTB‑XL, with pretraining on ~350K unlabeled CODE‑15 recordings, demonstrate strong supervised baselines and improved transfer, especially in low‑label scenarios and with LoRA adaptation.
By Yakoub Bazi, Sarah Aljuhani, Mohamad M. Al Rahhal, Mansour Zuair, Naif Alajlan
arXiv:2603. 19100v2 Announce Type: replace Abstract: Electroencephalography (EEG) enables non-invasive monitoring of brain activity across clinical and neurotechnology applications, yet building foundation models for EEG remains challenging due to differing electrode topologies and computational scalability, as Transformer architectures incur quadratic sequence complexity.
By Dana\'e Broustail, Anna Tegon, Thorir Mar Ingolfsson, Yawei Li, Luca Benini
RobECG-CL is a rank‑aware contrastive learning framework designed to learn robust representations for paper ECG images, which often suffer from varied layouts, physical artifacts, and limited labels. The method constructs progressively degraded views from standard 12‑lead ECG recordings and trains the model to maintain invariance to the same recording while respecting degradation ordering. In synthetic stress tests on CODE‑II and EchoNext, RobECG‑CL shows improved robustness under severe degradation and few‑shot transfer, outperforming other contrastive baselines and surpassing the waveform‑based foundation model ECG‑FM in a 1% labeled setting; it also achieves the best macro AUROC on 312 hospital samples with 37 labels.
By Yinghao Xie, Zhenbang Dai, Haojun Wang, Jinyu Cai, Fabio Bonassi, Hongwu Chen, Johan Sundstr\"om, Jiawei Li, Ant\^onio H. Ribeiro
arXiv:2608.30367v1 Announce Type: new
Abstract: Transformer-based electrocardiogram (ECG) models commonly tokenize waveforms into fixed temporal patches. Though convenient, fixed patching can split h...
By Ahmed Sameh, Nolan Wilson, Max Enderlein, Yogatheesan Varatharajah
arXiv:2609. 15498v1 Announce Type: new Abstract: Recurrent Transformers reusing their weights rather than stacking $L$ distinct layers are becoming widely adopted due to their parameter efficiency [1,2,3].
By Pawel Olszowiec, Michal Byra, Grzegorz Gruszczynski, Grzegorz Stefanski, Alberto Presta
arXiv:2608. 03597v1 Announce Type: new Abstract: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and is associated with increased risks of stroke, heart failure, and mortality.
By Amirhossein Taleshinosrati, Yangyang Wang, Atitaya Phoemsuk, Vahid Abolghasemi, Naser Hossein Motlagh, Sadasivan Puthusserypady, Daniel Teichmann, Abdolrahman Peimankar
The paper introduces R‑U‑Net, an ECG delineation model that combines a ResNet‑18 encoder with a U‑Net decoder. It demonstrates that this decoder design outperforms a ResNet‑18 + fully convolutional network baseline across 16 in‑domain settings and improves cross‑domain performance by 8.1 mIoU. Ablation studies reveal that the decoder contributes more to performance gains than the evaluated semi‑supervised learning methods.
By Joseph Scharpf, William Han, Chaojing Duan, Michael A. Rosenberg, Emerson Liu, Ding Zhao
arXiv:2607. 05009v1 Announce Type: cross Abstract: Complete digital 12-lead electrocardiograms (ECGs) are essential for AI-enabled cardiovascular assessment, yet many clinical ECG records, particularly those digitized from ECG images, remain incomplete because of short display formats, incomplete waveform digitization, lead loss, or signal corruption.
By Xiaocheng Fang, Haoyu Wang, Jieyi Cai, Qinghao Zhao, Jun Li, Shanwei Zhang, Guangkun Nie, Yujie Xiao, Shun Huang, Jiarui Jin, Hongmin Liu, Guodong Wang, Shuohua Chen, Liming Lin, Shouling Wu, Hongyan Li, Shenda Hong
arXiv:2607. 27404v1 Announce Type: new Abstract: Existing benchmarks for electrocardiogram foundation models primarily evaluate downstream predictive performance, providing limited insight into whether their internal representations can be faithfully decomposed, clinically interpreted, or reproduced across independent analyses.
By Yixuan Duan, Wei Qiu
arXiv:2607. 09680v1 Announce Type: cross Abstract: Continuous cardiac monitoring in wearable devices demands classifiers that are simultaneously accurate, energy-efficient, and deployable on resource-constrained hardware.
By Anh Tran, Khanh Tran, Cuong Do
arXiv:2601. 18798v2 Announce Type: replace-cross Abstract: ECG-Language Models (ELMs) extend recent advances in Multimodal Large Language Models (MLLMs) to automated ECG interpretation.
By William Han, Tony Chen, Chaojing Duan, Xiaoyu Song, Yihang Yao, Yuzhe Yang, Michael A. Rosenberg, Emerson Liu, Ding Zhao