{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T11:33:58Z","timestamp":1793100838039,"version":"4.5.0"},"reference-count":58,"publisher":"IOP Publishing","issue":"10","license":[{"start":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T00:00:00Z","timestamp":1793059200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T00:00:00Z","timestamp":1793059200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Youth Science Fund Project of Guangxi Natural Science Foundation","award":["2026GXNSFBA00640198"],"award-info":[{"award-number":["2026GXNSFBA00640198"]}]},{"name":"Guangxi Science and Technology Base and Talent Special Project","award":["GuiKe AD21159003"],"award-info":[{"award-number":["GuiKe AD21159003"]}]},{"name":"National Natural Science Foundation of China","award":["62006055"],"award-info":[{"award-number":["62006055"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Physiol. Meas."],"published-print":{"date-parts":[[2026,10,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Automatic multi-label classification of 12-lead electrocardiograms (ECGs) remains challenging because of heterogeneous waveform morphology, long-range temporal dependencies, diagnosis-dependent inter-lead relationships, and severe label imbalance. This study develops an adaptive framework that jointly models temporal features and diagnosis-specific lead interactions.\n                    <jats:italic>Approach.<\/jats:italic>\n                    We propose a multi-scale residual-temporal network incorporating a diagnosis-conditioned, record-specific sparse lead graph. A shared temporal encoder independently extracts dynamic node features from each lead waveform. Learnable diagnosis prototypes participate in edge-score computation before message passing, generating a distinct graph for every recording and diagnostic category. For each target lead, only the top-\n                    <jats:italic>k<\/jats:italic>\n                    relationships are retained, while established lead connections are incorporated as a physiological soft prior with learnable strength. Prototype-guided graph predictions are integrated with global semantic predictions through class-wise gated fusion. Weighted asymmetric loss and validation-based class-specific thresholds address label imbalance.\n                    <jats:italic>Main results.<\/jats:italic>\n                    The model was evaluated on CPSC2018, G12EC, and Physikalisch-Technische Bundesanstalt extra-large (PTB-XL) across five multi-label settings. It achieved Macro-\n                    <jats:italic>F<\/jats:italic>\n                    1 scores of 0.8327 on nine-class CPSC2018, 0.5857 \u00b1 0.0142 on 30-class G12EC, and 0.7782, 0.6421, and 0.4910 on the 5-, 12-, and 23-class PTB-XL tasks, respectively. The corresponding absolute gains over the strongest listed Macro-\n                    <jats:italic>F<\/jats:italic>\n                    1 comparators were 0.0147, 0.1428, 0.0226, 0.1335, and 0.0102. Macro-AUPRC was highest in all five settings, although Hamming Loss on the 23-class PTB-XL task was 0.0025 higher than that of ECG-STAR. Ablation and paired-bootstrap analyses supported the contribution of diagnosis-conditioned graph modelling.\n                    <jats:italic>Significance.<\/jats:italic>\n                    Conditioning sparse lead relationships jointly on each recording and diagnostic category extends fixed or class-agnostic lead graphs and provides an adaptive representation of disease-dependent multi-lead evidence. Clinical generalisability requires validation on independent hospital cohorts.\n                  <\/jats:p>","DOI":"10.1088\/1361-6579\/aeb225","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T22:53:33Z","timestamp":1791500013000},"page":"105016","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-scale temporal feature fusion and lead-graph attention for multi-label classification of 12-lead ECGs"],"prefix":"10.1088","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6033-0216","authenticated-orcid":true,"given":"Feiyan","family":"Zhou","sequence":"first","affiliation":[{"name":"Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University"},{"name":"Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University"},{"name":"Guangxi Engineering Research Center of Educational Intelligent Technology"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Mingyang","family":"Li","sequence":"additional","affiliation":[{"name":"Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University"},{"name":"Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University"},{"name":"Guangxi Engineering Research Center of Educational Intelligent Technology"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]}],"member":"266","published-online":{"date-parts":[[2026,10,27]]},"reference":[{"key":"pmeaaeb225bib1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106160","type":"journal-article","article-title":"Deep neural networks generalization and fine-tuning for 12-lead ECG classification","volume":"93","author":"Avetisyan","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"pmeaaeb225bib2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacadv.2023.100686","type":"journal-article","article-title":"Clinical applications, methodology, and scientific reporting of electrocardiogram deep-learning models: a systematic review","volume":"2","author":"Avula","year":"2023","journal-title":"JACC Adv."},{"key":"pmeaaeb225bib3","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107599","type":"journal-article","article-title":"Multi-label arrhythmia classification using 12-lead ECG based on lead feature guide network","volume":"129","author":"Cheng","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"pmeaaeb225bib4","doi-asserted-by":"publisher","first-page":"9268","DOI":"10.1109\/CVPR.2019.00949","type":"conference-proceedings","article-title":"Class-balanced loss based on effective number of samples","author":"Cui","year":"2019"},{"key":"pmeaaeb225bib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107508","type":"journal-article","article-title":"Multi-label correlation guided feature fusion network for abnormal ECG diagnosis","volume":"233","author":"Ge","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"pmeaaeb225bib6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-63656-x","type":"journal-article","article-title":"xECGArch: a trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features","volume":"14","author":"Goettling","year":"2024","journal-title":"Sci. Rep."},{"key":"pmeaaeb225bib7","doi-asserted-by":"publisher","first-page":"e251","DOI":"10.1161\/CIRCULATIONAHA.108.191097","type":"journal-article","article-title":"AHA\/ACCF\/HRS recommendations for the standardization and interpretation of the electrocardiogram: part V: electrocardiogram changes associated with cardiac chamber hypertrophy","volume":"119","author":"Hancock","year":"2009","journal-title":"Circulation"},{"key":"pmeaaeb225bib8","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","type":"journal-article","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"Hannun","year":"2019","journal-title":"Nat. Med."},{"key":"pmeaaeb225bib9","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","type":"conference-proceedings","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"pmeaaeb225bib10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","type":"journal-article","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"pmeaaeb225bib11","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2021.811661","type":"journal-article","article-title":"Practical lessons on 12-lead ECG classification: meta-analysis of methods from PhysioNet\/computing in cardiology challenge 2020","volume":"12","author":"Hong","year":"2022","journal-title":"Front. Physiol."},{"key":"pmeaaeb225bib12","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","type":"conference-proceedings","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"pmeaaeb225bib13","doi-asserted-by":"publisher","first-page":"4700","DOI":"10.1109\/CVPR.2017.243)","type":"conference-proceedings","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"pmeaaeb225bib14","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1080\/14796678.2024.2354082","type":"journal-article","article-title":"Generalization challenges in electrocardiogram deep learning: insights from dataset characteristics and attention mechanism","volume":"20","author":"Huang","year":"2024","journal-title":"Future Cardiol."},{"key":"pmeaaeb225bib15","doi-asserted-by":"publisher","first-page":"3543","DOI":"10.18653\/v1\/N19-1357","type":"conference-proceedings","article-title":"Attention is not explanation","author":"Jain","year":"2019"},{"key":"pmeaaeb225bib16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/INDICON49873.2020.9342488)","type":"conference-proceedings","article-title":"An attention based hierarchical LSTM model for detection of myocardial infarction","author":"Jyotishi","year":"2020"},{"key":"pmeaaeb225bib17","doi-asserted-by":"publisher","first-page":"4661","DOI":"10.1109\/TSMC.2023.3257022","type":"journal-article","article-title":"An attentive spatio-temporal learning-based network for cardiovascular disease diagnosis","volume":"53","author":"Jyotishi","year":"2023","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"pmeaaeb225bib18","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1038\/s44325-025-00078-2","type":"journal-article","article-title":"Generalizability of electrocardiographic artificial intelligence","volume":"2","author":"Karabayir","year":"2025","journal-title":"npj Cardiovasc. Health"},{"key":"pmeaaeb225bib19","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1016\/j.jacc.2007.01.024","type":"journal-article","article-title":"Recommendations for the standardization and interpretation of the electrocardiogram: part I: the electrocardiogram and its technology","volume":"49","author":"Kligfield","year":"2007","journal-title":"J. Am. Coll. Cardiol."},{"key":"pmeaaeb225bib20","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1109\/JBHI.2023.3246241","type":"journal-article","article-title":"sCL-ST: supervised contrastive learning with semantic transformations for multiple lead ECG arrhythmia classification","volume":"27","author":"Le","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pmeaaeb225bib21","doi-asserted-by":"publisher","DOI":"10.1056\/AIoa2401033","type":"journal-article","article-title":"An electrocardiogram foundation model built on over 10 million recordings","volume":"2","author":"Li","year":"2025","journal-title":"NEJM AI"},{"key":"pmeaaeb225bib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.102999","type":"journal-article","article-title":"Multimodal fusion of spatial-temporal and frequency representations for enhanced ECG classification","volume":"118","author":"Liu","year":"2025a","journal-title":"Inf. Fusion"},{"key":"pmeaaeb225bib23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2025.122273","type":"journal-article","article-title":"ECG-STAR: spatio-temporal attention residual networks for multi-label ECG abnormality classification","volume":"717","author":"Liu","year":"2025b","journal-title":"Inf. Sci."},{"key":"pmeaaeb225bib24","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1166\/jmihi.2018.2442)","type":"journal-article","article-title":"An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection","volume":"8","author":"Liu","year":"2018","journal-title":"J. Med. Imaging Health Inform."},{"key":"pmeaaeb225bib25","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","type":"conference-proceedings"},{"key":"pmeaaeb225bib26","doi-asserted-by":"publisher","first-page":"ooaf122","DOI":"10.1093\/jamiaopen\/ooaf122","type":"journal-article","article-title":"ECG-FM: an open electrocardiogram foundation model","volume":"8","author":"McKeen","year":"2025","journal-title":"JAMIA Open"},{"key":"pmeaaeb225bib27","doi-asserted-by":"publisher","first-page":"2350","DOI":"10.1016\/j.jacc.2023.11.007","type":"journal-article","article-title":"Global burden of cardiovascular diseases and risks, 1990\u20132022","volume":"82","author":"Mensah","year":"2023","journal-title":"J. Am. Coll. Cardiol."},{"key":"pmeaaeb225bib28","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106141","type":"journal-article","article-title":"Deep learning for ECG classification: a comparative study of 1D and 2D representations and multimodal fusion approaches","volume":"93","author":"Narotamo","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"pmeaaeb225bib29","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/s11886-024-02062-1","type":"journal-article","article-title":"Artificial intelligence interpretation of the electrocardiogram: a state-of-the-art review","volume":"26","author":"Ose","year":"2024","journal-title":"Curr. Cardiol. Rep."},{"key":"pmeaaeb225bib30","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/abc960","type":"journal-article","article-title":"Classification of 12-lead ECGs: the physionet\/computing in cardiology challenge 2020","volume":"41","author":"Perez Alday","year":"2020","journal-title":"Physiol. Meas."},{"key":"pmeaaeb225bib31","doi-asserted-by":"publisher","DOI":"10.13026\/dvyd-kd57","type":"journal-article","article-title":"Classification of 12-lead ECGs: The PhysioNet\/Computing in Cardiology Challenge 2020","volume":"41","author":"Perez Alday","year":"2022","journal-title":"PhysioNet"},{"key":"pmeaaeb225bib32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108406","type":"journal-article","article-title":"Conv-RGNN: an efficient convolutional residual graph neural network for ECG classification","volume":"257","author":"Qiang","year":"2024","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmeaaeb225bib33","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110545","type":"journal-article","article-title":"Label correlation embedding guided network for multi-label ECG arrhythmia diagnosis","volume":"270","author":"Ran","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"pmeaaeb225bib34","doi-asserted-by":"publisher","first-page":"1760","DOI":"10.1038\/s41467-020-15432-4","type":"journal-article","article-title":"Automatic diagnosis of the 12-lead ECG using a deep neural network","volume":"11","author":"Ribeiro","year":"2020","journal-title":"Nat. Commun."},{"key":"pmeaaeb225bib35","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/ICCV48922.2021.00015","type":"conference-proceedings","article-title":"Asymmetric loss for multi-label classification","author":"Ridnik","year":"2021"},{"key":"pmeaaeb225bib36","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1109\/ICCV.2017.74","type":"conference-proceedings","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"pmeaaeb225bib37","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1038\/s41569-020-00503-2","type":"journal-article","article-title":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management","volume":"18","author":"Siontis","year":"2021","journal-title":"Nat. Rev. Cardiol."},{"key":"pmeaaeb225bib38","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589)","type":"journal-article","article-title":"Super-convergence: very fast training of neural networks using large learning rates","volume":"11006","author":"Smith","year":"2019","journal-title":"Proc. SPIE"},{"key":"pmeaaeb225bib39","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1109\/JBHI.2020.3022989","type":"journal-article","article-title":"Deep learning for ECG analysis: benchmarks and insights from PTB-XL","volume":"25","author":"Strodthoff","year":"2021"},{"key":"pmeaaeb225bib40","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.jacc.2008.12.013","type":"journal-article","article-title":"AHA\/ACCF\/HRS recommendations for the standardization and interpretation of the electrocardiogram: part III: intraventricular conduction disturbances","volume":"53","author":"Surawicz","year":"2009","journal-title":"J. Am. Coll. Cardiol."},{"key":"pmeaaeb225bib41","article-title":"Omni-scale CNNs: a simple and effective kernel size configuration for time series classification","author":"Tang","year":"2022","type":"conference-proceedings"},{"key":"pmeaaeb225bib42","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121497","type":"journal-article","article-title":"IM-ECG: an interpretable framework for arrhythmia detection using multi-lead ECG","volume":"237","author":"Tao","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"pmeaaeb225bib43","first-page":"5998","type":"conference-proceedings","article-title":"Attention is all you need","volume":"vol 30","author":"Vaswani","year":"2017"},{"key":"pmeaaeb225bib44","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018","type":"conference-proceedings"},{"key":"pmeaaeb225bib45","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1016\/j.jacc.2008.12.016","type":"journal-article","article-title":"AHA\/ACCF\/HRS recommendations for the standardization and interpretation of the electrocardiogram: part VI: acute ischemia\/infarction","volume":"53","author":"Wagner","year":"2009","journal-title":"J. Am. Coll. Cardiol."},{"key":"pmeaaeb225bib46","doi-asserted-by":"publisher","first-page":"154","DOI":"10.13026\/kfzx-aw45","type":"journal-article","article-title":"PTB-XL, a large publicly available electrocardiograph","volume":"7","author":"Wagner","year":"2022","journal-title":"dataset Scientific data"},{"key":"pmeaaeb225bib47","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41597-020-0495-6","type":"journal-article","article-title":"PTB-XL, a large publicly available electrocardiography dataset","volume":"7","author":"Wagner","year":"2020","journal-title":"Sci. Data"},{"key":"pmeaaeb225bib48","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123869","type":"journal-article","article-title":"PM2ECGCN: parallelized spatial-temporal structures of multi-lead ECG with graph convolution network for multi-center cardiac disease diagnosis","volume":"250","author":"Wang","year":"2024a","journal-title":"Expert Syst. Appl."},{"key":"pmeaaeb225bib49","doi-asserted-by":"publisher","first-page":"578","DOI":"10.3390\/bioengineering11060578","type":"journal-article","article-title":"Visualized lead selection for arrhythmia classification based on a lead activation heatmap using multi-lead ECGs","volume":"11","author":"Wang","year":"2024b","journal-title":"Bioengineering"},{"key":"pmeaaeb225bib50","doi-asserted-by":"publisher","first-page":"2461","DOI":"10.1109\/JBHI.2020.2981526","type":"journal-article","article-title":"Deep multi-scale fusion neural network for multi-class arrhythmia detection","volume":"24","author":"Wang","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pmeaaeb225bib51","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","type":"journal-article","article-title":"CBAM: convolutional block attention module","volume":"11211","author":"Woo","year":"2018","journal-title":"Comput. Vision\u2014ECCV"},{"key":"pmeaaeb225bib52","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2026.123370","type":"journal-article","article-title":"ECG-GTMD: a CVD diagnosis model based on graph-transformer with multi-domain fusion of spatiotemporal and band features","volume":"744","author":"Xia","year":"2026","journal-title":"Inf. Sci."},{"key":"pmeaaeb225bib53","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1109\/TETCI.2023.3235374","type":"journal-article","article-title":"A multi-view multi-scale neural network for multi-label ECG classification","volume":"7","author":"Yang","year":"2023","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"pmeaaeb225bib54","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.inffus.2019.06.024","type":"journal-article","article-title":"Multi-class arrhythmia detection from 12-lead varied-length ECG using attention-based time-incremental convolutional neural network","volume":"53","author":"Yao","year":"2020","journal-title":"Inf. Fusion"},{"key":"pmeaaeb225bib55","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1038\/s41597-020-0386-x","type":"journal-article","article-title":"A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients","volume":"7","author":"Zheng","year":"2020","journal-title":"Sci. Data"},{"key":"pmeaaeb225bib56","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.ymeth.2023.10.013","type":"journal-article","article-title":"DAMS-Net: dual attention and multi-scale information fusion network for 12-lead ECG classification","volume":"220","author":"Zhou","year":"2023","journal-title":"Methods"},{"key":"pmeaaeb225bib57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106551","type":"journal-article","article-title":"Open-world electrocardiogram classification via domain knowledge-driven contrastive learning","volume":"179","author":"Zhou","year":"2024","journal-title":"Neural. Netw."},{"key":"pmeaaeb225bib58","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1038\/s41746-025-02074-3","type":"journal-article","article-title":"Diagnosis of cardiac conditions from 12-lead electrocardiogram through natural language supervision","volume":"8","author":"Zhou","year":"2025","journal-title":"npj Digit. Med."}],"container-title":["Physiological Measurement"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T10:54:36Z","timestamp":1793098476000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/aeb225"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,27]]},"references-count":58,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,27]]},"published-print":{"date-parts":[[2026,10,30]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6579\/aeb225","relation":{},"ISSN":["0967-3334","1361-6579"],"issn-type":[{"value":"0967-3334","type":"print"},{"value":"1361-6579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,27]]},"assertion":[{"value":"Multi-scale temporal feature fusion and lead-graph attention for multi-label classification of 12-lead ECGs","name":"article_title","label":"Article Title"},{"value":"Physiological Measurement","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-06-16","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-08","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}