{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T08:59:57Z","timestamp":1794387597554,"version":"4.9.0"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"18","license":[{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Fonds de la recherche du Qu\u00e9bec en Sant\u00e9","award":["312758"],"award-info":[{"award-number":["312758"]}]},{"name":"Des Groseillers-B\u00e9rard Interventional Cardiology Research"},{"name":"Chair"},{"DOI":"10.13039\/100007631","name":"Canadian Institute for Advanced Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007631","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IVADO Data Science Institute"},{"DOI":"10.13039\/501100020951","name":"Fonds de recherche du Qu\u00e9bec","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020951","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003151","name":"Nature et technologies","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003151","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Canadian Research Chair Tier 2 in Responsible Multi-Omics Data Science"},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["K23HL169839"],"award-info":[{"award-number":["K23HL169839"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["3OT2OD035404-01S3"],"award-info":[{"award-number":["3OT2OD035404-01S3"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["DP2HL174046"],"award-info":[{"award-number":["DP2HL174046"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000968","name":"AHA","doi-asserted-by":"publisher","award":["23CDA1050571"],"award-info":[{"award-number":["23CDA1050571"]}],"id":[{"id":"10.13039\/100000968","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000968","name":"AHA","doi-asserted-by":"publisher","award":["961045"],"award-info":[{"award-number":["961045"]}],"id":[{"id":"10.13039\/100000968","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background and Aims<\/jats:title>\n                    <jats:p>The 12-lead electrocardiogram (ECG) remains a cornerstone of cardiac diagnostics, yet existing artificial intelligence (AI) solutions for automated interpretation often lack generalizability, remain closed source, and are primarily trained using supervised learning (SL), which requires extensive labelled datasets and may limit adaptability across diverse clinical settings. Self-supervised learning (SSL) can potentially overcome these limitations by learning robust representations from unlabelled data. To address these challenges, this study developed and compared two open-source foundational ECG models: DeepECG-SL, a supervised multilabel ECG model, and DeepECG-SSL, a self-supervised model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Both models were trained on over 1 million ECGs using a standardized preprocessing pipeline and automated free-text extraction from ECG reports to predict 77 cardiac conditions. DeepECG-SSL leveraged unlabelled data through self-supervised contrastive learning and masked lead modelling before fine-tuning for downstream tasks, while DeepECG-SL was trained directly on labelled diagnostic data in an end-to-end fashion. Performance was evaluated across seven private, multilingual healthcare systems and four public ECG repositories, with assessment of fairness by age and sex, and investigation of privacy vulnerabilities as well as memory and compute requirements.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>DeepECG-SSL achieved micro-averaged area under the receiver operating characteristic curves (AUROCs) across all 77 cardiac conditions for ECG interpretation of 0.990 [95% confidence interval (CI): 0.990, 0.990] on the internal dataset (MHI-ds), 0.981 (95% CI: 0.981, 0.981) on external public datasets (UKB, CLSA, MIMIC-IV and PTB), and 0.983 (95% CI: 0.983, 0.983) on external private datasets (UW, UCSF, JGH, NYP, MGH, CSH and CHUM), while DeepECG-SL demonstrated AUROCs of 0.992 (95% CI: 0.992, 0.992), 0.980 (95% CI: 0.980, 0.980), and 0.983 (95% CI: 0.983, 0.984), respectively. Fairness analyses revealed minimal disparities (true-positive rate and false-positive rate difference &amp;lt;0.1) across age and sex groups for both models. DeepECG-SSL demonstrated superior performance on limited-data digital biomarker tasks, with the largest improvements in long QT syndrome (LQTS) genotype classification (AUROC 0.931 vs 0.850, P = .026, n = 127 ECGs) and 5 year atrial fibrillation risk prediction (AUROC 0.742 vs 0.734, P &amp;lt; 0.001, n = 132 050 ECGs), while achieving superior performance in left ventricular ejection fraction \u226440% classification (AUROC 0.926 vs 0.917, P &amp;lt; 0.001, n = 25 252 ECGs) and comparable performance in LQTS detection (AUROC 0.767 vs 0.735, P = 0.117, n = 934 ECGs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study establishes SSL as a promising paradigm for ECG analysis, particularly in settings with limited annotated data, enhancing accessibility, generalizability, and fairness in AI-driven cardiac diagnostics. By releasing model weights, preprocessing tools, and validation code, this work aims to support robust, data-efficient AI diagnostics across diverse clinical environments and questions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/eurheartj\/ehaf1119","type":"journal-article","created":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T12:38:14Z","timestamp":1766839094000},"page":"2174-2186","source":"Crossref","is-referenced-by-count":28,"title":["Foundation models for electrocardiogram interpretation: clinical implications"],"prefix":"10.1093","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7919-2508","authenticated-orcid":false,"given":"Alexis","family":"Nolin-Lapalme","sequence":"first","affiliation":[{"name":"Department of Biochemistry and Molecular Medicine, Faculty of Medicine, University of Montreal , Montreal, Quebec , H3C 3J7","place":["Canada"]},{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Mila\u2014Qu\u00e9bec AI Institute , Montreal, Quebec , H2S 3H1","place":["Canada"]},{"name":"Heartwise (Heartwise.ai), Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Achille","family":"Sowa","sequence":"additional","affiliation":[{"name":"Department of Biochemistry and Molecular Medicine, Faculty of Medicine, University of Montreal , Montreal, Quebec , H3C 3J7","place":["Canada"]},{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Heartwise (Heartwise.ai), Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacques","family":"Delfrate","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Heartwise (Heartwise.ai), Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Tastet","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"Corbin","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Merve","family":"Kulbay","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Department of Ophthalmology & Visual Sciences, McGill University , Montreal, QC H4A 3S5 ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derman","family":"Ozdemir","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Department of Internal Medicine\/Critical Care, Eastern New Mexico Medical Center , Roswell, NM ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Jeanne","family":"No\u00ebl","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois-Christophe","family":"Marois-Blanchet","sequence":"additional","affiliation":[{"name":"Center for the Integration and Analysis of Medical Data (CITADEL), Centre Hospitalier de L'Universit\u00e9 de Montr\u00e9al (CHUM) , Montreal, Quebec , H2X 0A9","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"Harvey","sequence":"additional","affiliation":[{"name":"Center for the Integration and Analysis of Medical Data (CITADEL), Centre Hospitalier de L'Universit\u00e9 de Montr\u00e9al (CHUM) , Montreal, Quebec , H2X 0A9","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Surbhi","family":"Sharma","sequence":"additional","affiliation":[{"name":"Electrophysiology Section, Division of Cardiology, University of Washington , Seattle, WA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minhaj","family":"Ansari","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Medicine, University of California-San Francisco , San Francisco, CA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"I Min","family":"Chiu","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center , Los Angeles, CA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentina","family":"D\u2019souza","sequence":"additional","affiliation":[{"name":"Data Sciences Platform, The Broad Institute of MIT and Harvard , Cambridge, MA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sam F","family":"Friedman","sequence":"additional","affiliation":[{"name":"Data Sciences Platform, The Broad Institute of MIT and Harvard , Cambridge, MA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Micha\u00ebl","family":"Chass\u00e9","sequence":"additional","affiliation":[{"name":"Center for the Integration and Analysis of Medical Data (CITADEL), Centre Hospitalier de L'Universit\u00e9 de Montr\u00e9al (CHUM) , Montreal, Quebec , H2X 0A9","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian J","family":"Potter","sequence":"additional","affiliation":[{"name":"Cardiovascular Center & Research Center, Centre Hospitalier de L'Universit\u00e9 de Montr\u00e9al (CHUM) , Montreal, Quebec ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Afilalo","sequence":"additional","affiliation":[{"name":"Division of Cardiology and Centre for Clinical Epidemiology, Jewish General Hospital, McGill University , Montreal, Quebec ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre Adil","family":"Elias","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Columbia University Irving Medical Center , New York, NY ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5636-2238","authenticated-orcid":false,"given":"Gilbert","family":"Jabbour","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mourad","family":"Bahani","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Pierre","family":"Dub\u00e9","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Department of Medicine, Faculty of Medicine, Universit\u00e9 de Montr\u00e9al, Montreal, Quebec ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9048-1239","authenticated-orcid":false,"given":"Patrick M","family":"Boyle","sequence":"additional","affiliation":[{"name":"Electrophysiology Section, Division of Cardiology, University of Washington , Seattle, WA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neal A","family":"Chatterjee","sequence":"additional","affiliation":[{"name":"Electrophysiology Section, Division of Cardiology, University of Washington , Seattle, WA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua","family":"Barrios","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Medicine, University of California-San Francisco , San Francisco, CA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geoffrey H","family":"Tison","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Medicine, University of California-San Francisco , San Francisco, CA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3813-7518","authenticated-orcid":false,"given":"David","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center , Los Angeles, CA ,","place":["USA"]},{"name":"Division of Research, Kaiser Permanente, Northern California, Pleasanton, CA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahnaz","family":"Maddah","sequence":"additional","affiliation":[{"name":"Data Sciences Platform, The Broad Institute of MIT and Harvard , Cambridge, MA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaan","family":"Khurshid","sequence":"additional","affiliation":[{"name":"Cardiovascular Disease Initiative, Broad Institute of Harvard University and MIT , Cambridge, MA ,","place":["USA"]},{"name":"Cardiovascular Research Center, Massachusetts General Hospital , Boston, MA ,","place":["USA"]},{"name":"Telemachus and Irene Demoulas Family Foundation Center for Cardiac Arrhythmias, Massachusetts General Hospital , Boston, MA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia","family":"Cadrin-Tourigny","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Department of Medicine, Faculty of Medicine, Universit\u00e9 de Montr\u00e9al, Montreal, Quebec ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1472-0258","authenticated-orcid":false,"given":"Rafik","family":"Tadros","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Department of Medicine, Faculty of Medicine, Universit\u00e9 de Montr\u00e9al, Montreal, Quebec ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4295-3339","authenticated-orcid":false,"given":"Julie","family":"Hussin","sequence":"additional","affiliation":[{"name":"Department of Biochemistry and Molecular Medicine, Faculty of Medicine, University of Montreal , Montreal, Quebec , H3C 3J7","place":["Canada"]},{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Heartwise (Heartwise.ai), Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Department of Medicine, Faculty of Medicine, Universit\u00e9 de Montr\u00e9al, Montreal, Quebec ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8490-0270","authenticated-orcid":false,"given":"Robert","family":"Avram","sequence":"additional","affiliation":[{"name":"Montreal Heart Institute , 5000 Rue B\u00e9langer, Montreal, Quebec , H1T 1C8","place":["Canada"]},{"name":"Department of Ophthalmology & Visual Sciences, McGill University , Montreal, QC H4A 3S5 ,","place":["Canada"]},{"name":"Department of Medicine, Faculty of Medicine, Universit\u00e9 de Montr\u00e9al, Montreal, Quebec ,","place":["Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,1,22]]},"reference":[{"key":"2026051513022730600_ehaf1119-B1","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1046\/j.1365-2281.1999.00195.x","article-title":"A confident decision support system for interpreting electrocardiograms","volume":"19","author":"Holst","year":"1999","journal-title":"Clin Physiol"},{"key":"2026051513022730600_ehaf1119-B2","doi-asserted-by":"publisher","first-page":"175","DOI":"10.3390\/jcdd10040175","article-title":"Current and future use of artificial intelligence in electrocardiography","volume":"10","author":"Mart\u00ednez-Sell\u00e9s","year":"2023","journal-title":"J Cardiovasc Dev Dis"},{"key":"2026051513022730600_ehaf1119-B3","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","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":"2026051513022730600_ehaf1119-B4","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1038\/s41591-021-01335-4","article-title":"Artificial intelligence\u2013enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial","volume":"27","author":"Yao","year":"2021","journal-title":"Nat Med"},{"key":"2026051513022730600_ehaf1119-B5","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1016\/j.cardfail.2022.12.016","article-title":"Electrocardiogram detection of pulmonary hypertension using deep learning","volume":"29","author":"Aras","year":"2023","journal-title":"J Card Fail"},{"key":"2026051513022730600_ehaf1119-B6","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1001\/jamacardio.2024.0039","article-title":"Deep learning\u2013augmented ECG analysis for screening and genotype prediction of congenital long QT syndrome","volume":"9","author":"Jiang","year":"2024","journal-title":"JAMA Cardiol"},{"key":"2026051513022730600_ehaf1119-B7","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2026051513022730600_ehaf1119-B8","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1038\/s41551-022-00914-1","article-title":"Self-supervised learning in medicine and healthcare","volume":"6","author":"Krishnan","year":"2022","journal-title":"Nat Biomed Eng"},{"key":"2026051513022730600_ehaf1119-B9","doi-asserted-by":"publisher","first-page":"3741","DOI":"10.1038\/s41467-023-39472-8","article-title":"Practical intelligent diagnostic algorithm for wearable 12-lead ECG via self-supervised learning on large-scale dataset","volume":"14","author":"Lai","year":"2023","journal-title":"Nat Commun"},{"key":"2026051513022730600_ehaf1119-B10","doi-asserted-by":"publisher","first-page":"105114","DOI":"10.1016\/j.compbiomed.2021.105114","article-title":"Self-supervised representation learning from 12-lead ECG data","volume":"141","author":"Mehari","year":"2022","journal-title":"Comput Biol Med"},{"key":"2026051513022730600_ehaf1119-B11","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"2026051513022730600_ehaf1119-B12","doi-asserted-by":"publisher","first-page":"7998","DOI":"10.1007\/s00330-022-08784-6","article-title":"Radiology artificial intelligence: a systematic review and evaluation of methods (RAISE)","volume":"32","author":"Kelly","year":"2022","journal-title":"Eur Radiol"},{"key":"2026051513022730600_ehaf1119-B13","doi-asserted-by":"publisher","author":"Pineau","DOI":"10.48550\/arXiv.2003.12206"},{"key":"2026051513022730600_ehaf1119-B14","doi-asserted-by":"publisher","author":"Oh","DOI":"10.48550\/arXiv.2203.06889"},{"key":"2026051513022730600_ehaf1119-B15","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1001\/jama.2013.281053","article-title":"World medical association declaration of Helsinki: ethical principles for medical research involving human subjects","volume":"310","author":"World Medical Association","year":"2013","journal-title":"JAMA"},{"key":"2026051513022730600_ehaf1119-B16","unstructured":"Ribeiro AH, Paixao GMM, Lima EM, Horta Ribeiro M, Pinto Filho MM, Gomes PR, et al \u00a0CODE-15%: a large scale annotated dataset of 12-lead ECGs. Zenodo. 10.5281\/zenodo.4916206."},{"key":"2026051513022730600_ehaf1119-B17","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Scientific Data"},{"key":"2026051513022730600_ehaf1119-B18","doi-asserted-by":"publisher","first-page":"1752","DOI":"10.1093\/ije\/dyz173","article-title":"Cohort profile: the Canadian Longitudinal Study on Aging (CLSA)","volume":"48","author":"Raina","year":"2019","journal-title":"Int J Epidemiol"},{"key":"2026051513022730600_ehaf1119-B19","doi-asserted-by":"publisher","first-page":"e1001779","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK biobank: an open access resource for identifying the causes of a wide range of Complex diseases of middle and old age","volume":"12","author":"Sudlow","year":"2015","journal-title":"PLoS Med"},{"key":"2026051513022730600_ehaf1119-B20","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41597-020-0495-6","article-title":"PTB-XL, a large publicly available electrocardiography dataset","volume":"7","author":"Wagner","year":"2020","journal-title":"Sci Data"},{"key":"2026051513022730600_ehaf1119-B21","doi-asserted-by":"publisher","first-page":"875","DOI":"10.3390\/ijerph13090875","article-title":"Review of studies concerning Electromagnetic Field (EMF) exposure assessment in Europe: low frequency fields (50 Hz\u2013100 kHz)","volume":"13","author":"Gaj\u0161ek","year":"2016","journal-title":"Int J Environ Res Public Health"},{"key":"2026051513022730600_ehaf1119-B22","author":"Chavan"},{"key":"2026051513022730600_ehaf1119-B23","doi-asserted-by":"publisher","first-page":"e30","DOI":"10.1016\/s0828-282x(10)70344-5","article-title":"Uncommon cause for a common electrocardiographic artifact","volume":"26","author":"Greutmann","year":"2010","journal-title":"Can J Cardiol"},{"key":"2026051513022730600_ehaf1119-B24","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/S0261-3794(99)00028-1","article-title":"Loess","volume":"19","author":"Jacoby","year":"2000","journal-title":"Elect Stud"},{"key":"2026051513022730600_ehaf1119-B25","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1016\/j.jacc.2007.01.024","article-title":"Recommendations for the standardization and interpretation of the electrocardiogram: part I: the electrocardiogram and its technology a scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinical Cardiology; the American College of Cardiology Foundation; and the Heart Rhythm Society endorsed by the International Society for Computerized Electrocardiology","volume":"49","author":"Kligfield","year":"2007","journal-title":"J Am Coll Cardiol"},{"key":"2026051513022730600_ehaf1119-B26","doi-asserted-by":"publisher","author":"Grattafiori","DOI":"10.48550\/arXiv.2407.21783"},{"key":"2026051513022730600_ehaf1119-B27","doi-asserted-by":"publisher","author":"Devlin","DOI":"10.48550\/arXiv.1810.04805"},{"key":"2026051513022730600_ehaf1119-B28","doi-asserted-by":"publisher","author":"Vaswani","DOI":"10.48550\/arXiv.1706.03762"},{"key":"2026051513022730600_ehaf1119-B29","doi-asserted-by":"publisher","author":"Gu","DOI":"10.48550\/arXiv.2312.00752"},{"key":"2026051513022730600_ehaf1119-B30","author":"Biewald","year":"2023"},{"key":"2026051513022730600_ehaf1119-B31","doi-asserted-by":"publisher","author":"Baevski","DOI":"10.48550\/arXiv.2006.11477"},{"key":"2026051513022730600_ehaf1119-B32","doi-asserted-by":"publisher","author":"Kiyasseh","DOI":"10.48550\/arXiv.2005.13249"},{"key":"2026051513022730600_ehaf1119-B33","doi-asserted-by":"publisher","first-page":"4920","DOI":"10.1093\/eurheartj\/ehae595","article-title":"Prediction of incident atrial fibrillation using deep learning, clinical models, and polygenic scores","volume":"45","author":"Jabbour","year":"2024","journal-title":"Eur Heart J"},{"key":"2026051513022730600_ehaf1119-B34","doi-asserted-by":"publisher","author":"Hardt","DOI":"10.48550\/arXiv.1610.02413"},{"issue":"7","key":"2026051513022730600_ehaf1119-B35","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2401033","article-title":"An electrocardiogram foundation model built on over 10 million recordings","volume":"2","author":"Li","year":"2025","journal-title":"NEJM AI"},{"key":"2026051513022730600_ehaf1119-B36","doi-asserted-by":"publisher","author":"McKeen","DOI":"10.48550\/arXiv.2408.05178"},{"key":"2026051513022730600_ehaf1119-B37","doi-asserted-by":"publisher","author":"Shokri","year":"2017","DOI":"10.1109\/SP.2017.41"},{"key":"2026051513022730600_ehaf1119-B38","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2026051513022730600_ehaf1119-B39","doi-asserted-by":"publisher","author":"Ribeiro","year":"2016","DOI":"10.1145\/2939672.2939778"},{"key":"2026051513022730600_ehaf1119-B40","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2020","journal-title":"Int J Comput Vis"},{"key":"2026051513022730600_ehaf1119-B41","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"2026051513022730600_ehaf1119-B42","doi-asserted-by":"publisher","first-page":"10.1007\/s12561-025-09505-5","DOI":"10.1007\/s12561-025-09505-5","article-title":"Weighted brier score\u2014an overall summary measure for risk prediction models with clinical utility consideration","author":"Zhu","year":"2025","journal-title":"Stat Biosci"},{"key":"2026051513022730600_ehaf1119-B43","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1002\/sim.2929","article-title":"Evaluating the added predictive ability of a new marker: from area under the ROC curve to reclassification and beyond","volume":"27","author":"Pencina","year":"2008","journal-title":"Stat Med"},{"key":"2026051513022730600_ehaf1119-B44","doi-asserted-by":"publisher","author":"Tan","DOI":"10.48550\/arXiv.2104.00298"},{"key":"2026051513022730600_ehaf1119-B45","doi-asserted-by":"publisher","author":"Adebayo","DOI":"10.48550\/arXiv.1810.03292"},{"key":"2026051513022730600_ehaf1119-B46","doi-asserted-by":"publisher","first-page":"101875","DOI":"10.1016\/j.xcrm.2024.101875","article-title":"Foundation model of ECG diagnosis: diagnostics and explanations of any form and rhythm on ECG","volume":"5","author":"Tian","year":"2024","journal-title":"Cell Rep Med"},{"key":"2026051513022730600_ehaf1119-B47","author":"Casusi","year":"2023"},{"key":"2026051513022730600_ehaf1119-B48","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.cjca.2024.09.018","article-title":"Deep learning-based 12-lead electrocardiogram for low left ventricular ejection fraction detection in patients","volume":"41","author":"Hou","year":"2024","journal-title":"Can J Cardiol"},{"key":"2026051513022730600_ehaf1119-B49","doi-asserted-by":"publisher","first-page":"e001459","DOI":"10.1136\/openhrt-2020-001459","article-title":"CHARGE-AF in a national routine primary care electronic health records database in the Netherlands: validation for 5-year risk of atrial fibrillation and implications for patient selection in atrial fibrillation screening","volume":"8","author":"Himmelreich","year":"2021","journal-title":"Open Heart"},{"key":"2026051513022730600_ehaf1119-B50","author":"Weill Cornell Medicine","year":"2025"},{"key":"2026051513022730600_ehaf1119-B51","doi-asserted-by":"publisher","author":"Suh","DOI":"10.48550\/arXiv.2211.12702"},{"key":"2026051513022730600_ehaf1119-B52","author":"Avram","year":"2025"},{"key":"2026051513022730600_ehaf1119-B53","author":"Avram","year":"2025"},{"key":"2026051513022730600_ehaf1119-B54","year":"2026"},{"key":"2026051513022730600_ehaf1119-B55","author":"Anumana AI","year":"2026"},{"key":"2026051513022730600_ehaf1119-B56","first-page":"1","volume-title":"Automata, Languages and Programming","author":"Dwork","year":"2006"}],"container-title":["European Heart Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/eurheartj\/article-pdf\/47\/18\/2174\/66531841\/ehaf1119.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/eurheartj\/article-pdf\/47\/18\/2174\/66531841\/ehaf1119.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T17:02:39Z","timestamp":1778864559000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/eurheartj\/article\/47\/18\/2174\/8436833"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,22]]},"references-count":56,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,1,22]]},"published-print":{"date-parts":[[2026,5,15]]}},"URL":"https:\/\/doi.org\/10.1093\/eurheartj\/ehaf1119","relation":{},"ISSN":["0195-668X","1522-9645"],"issn-type":[{"value":"0195-668X","type":"print"},{"value":"1522-9645","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5,7]]},"published":{"date-parts":[[2026,1,22]]}}}