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:2608. 12695v1 Announce Type: new Abstract: Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences.
By Ahmed Sameh, Ramzi Al-Sharawi, Yogatheesan Varatharajah
arXiv:2605. 31249v2 Announce Type: replace-cross Abstract: Electrocardiography (ECG) is a cornerstone of cardiac assessment, making the learning of informative ECG representations fundamental to tasks ranging from disease diagnosis to clinical report generation.
By Bosong Huang, Panzhen Zhao, Zengxiang Li, Patricia Lee, Wei Jin, Alan Wee-Chung Liew, Ming Jin, Shirui Pan
arXiv:2608. 14656v1 Announce Type: cross Abstract: Photoplethysmography (PPG) is widely used in consumer wearables because of its low cost and ease of acquisition.
By Zhongli Wu, Zhuangzhi Gao, He Zhao, Feixiang Zhou, Fu Wang, Jinru Ding, Yuankai Wang, Hongyi Qin, Gregory Y. H. Lip, Bil Kirmani, Yalin Zheng
arXiv:2607. 09749v1 Announce Type: cross Abstract: Foundation models have recently emerged as a powerful paradigm for learning transferable representations from large scale biomedical data, yet existing approaches for physiological waveforms primarily optimize reconstruction or forecasting objectives that do not explicitly preserve clinically meaningful waveform morphology.
By Saiyang Feng, Yuanyun Zhang, Shi Li
arXiv:2606. 09605v1 Announce Type: new Abstract: Foundation models offer a promising route to compress multi-modal physiological signals into compact representations of human health, with broad applications across sleep medicine, cardiology, neurology and other healthcare domains.
By Jonathan F. Carter, Lionel Tarassenko
TransECG-SSL is a self‑supervised framework that learns transferable heartbeat representations from unlabelled ECG data using a Transformer encoder pretrained with a hybrid objective of masked signal reconstruction and contrastive learning. The pretrained model is frozen and evaluated via linear probing on patient‑disjoint splits across three public ECG databases, showing that Hybrid SSL outperforms randomly initialized Transformers and source‑supervised pretraining. While cross‑dataset transfer improves performance over random baselines, it still falls short of target‑specific self‑supervised pretraining, and minority arrhythmia classes remain difficult under severe class imbalance.
By Ahtisham Ayyub, Fasih Haider, Muhammad Rehan Usman, Saturnino Luz, Christos Politis, Muhammad Arslan Usman
arXiv:2607. 23412v1 Announce Type: new Abstract: Electrocardiograms (ECGs) are widely used for cardiovascular risk prediction, yet models often fail to transfer across hospitals because of protocol, population, and measurement differences.
By Jie Lin, Weijie Sun, Sunil V. Kalmady, Anita Khalafbeigi, Abram Hindle, Padma Kaul, Russell Greiner
arXiv:2608. 05893v1 Announce Type: new Abstract: Electrocardiography (ECG) is one of the most widely used non-invasive tools for diagnosing cardiovascular disease, but transforming multi-lead ECG recordings into reliable clinical reports remains challenging.
By Akanta Das, Tasinul Islam Ahon, Ahmed Mahir Sultan Rumi, Md Mahbubur Rahman, Tausif Amim Shadly, Tanzima Hashem
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:2608. 14662v1 Announce Type: cross Abstract: Accurate recognition of pain using physiological signals remains a challenging problem due to pain's subjective nature and high inter-individual variability.
By Dominika Kunc, Przemys{\l}aw Kazienko, Stanis{\l}aw Saganowski
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