{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T05:11:47Z","timestamp":1794287507874,"version":"4.9.0"},"reference-count":26,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>We aimed to develop and externally validate a convolutional neural network (CNN) using sinus rhythm electrocardiograms (ECGs) and CHARGE-AF features to predict incident paroxysmal atrial fibrillation (AF), benchmarking its performance against the CHARGE-AF score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and results<\/jats:title>\n                    <jats:p>We curated 157 192 sinus ECGs from 76 986 patients within the New York University (NYU) Langone Health system, splitting data into training, validation, and test sets. Two cohorts, from suburban US outpatient practices and Greek tertiary hospitals, were used for external validation. The model utilizing the sinus ECG signal and all CHARGE-AF features achieved the highest test set area under the receiver operator curve (AUC) (0.89) and area under the precision recall curve (AUPRC) (0.69), outperforming the CHARGE-AF score alone. Model robustness was maintained in the external US cohort (AUC 0.90, AUPRC 0.67) and the European cohort (AUC 0.85, AUPRC 0.78). Subgroup analyses confirmed consistent performance across age, sex, and race strata. A CNN using ECG signals alone retained strong predictive ability, particularly when simulating missing or inaccurate clinical data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our CNN integrating sinus rhythm ECGs and CHARGE-AF features demonstrated superior predictive performance over traditional risk scoring alone for detecting incident paroxysmal AF. The model maintained accuracy across geographically and clinically diverse external validation cohorts, supporting its potential for broad implementation in AF screening strategies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ehjdh\/ztaf100","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:55:26Z","timestamp":1755777326000},"page":"1134-1144","source":"Crossref","is-referenced-by-count":4,"title":["Artificial intelligence\u2013enabled sinus electrocardiograms for the detection of paroxysmal atrial fibrillation benchmarked against the CHARGE-AF score"],"prefix":"10.1093","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7563-2430","authenticated-orcid":false,"given":"Constantine","family":"Tarabanis","sequence":"first","affiliation":[{"name":"Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital, Harvard Medical School , Boston, MA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vidya","family":"Koesmahargyo","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Tachmatzidis","sequence":"additional","affiliation":[{"name":"3rd Cardiology Department, Hippokrateion University Hospital, Aristotle University of Thessaloniki , Thessaloniki ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8041-4574","authenticated-orcid":false,"given":"Vasileios","family":"Sousonis","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Mitera Hospital Hygeia Group , Athens ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2423-4595","authenticated-orcid":false,"given":"Constantinos","family":"Bakogiannis","sequence":"additional","affiliation":[{"name":"3rd Cardiology Department, Hippokrateion University Hospital, Aristotle University of Thessaloniki , Thessaloniki ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Ronan","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott A","family":"Bernstein","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chirag","family":"Barbhaiya","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David S","family":"Park","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Douglas S","family":"Holmes","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Kushnir","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Yang","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony","family":"Aizer","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Larry A","family":"Chinitz","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2007-1928","authenticated-orcid":false,"given":"Stylianos","family":"Tzeis","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Mitera Hospital Hygeia Group , Athens ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vassilios","family":"Vassilikos","sequence":"additional","affiliation":[{"name":"3rd Cardiology Department, Hippokrateion University Hospital, Aristotle University of Thessaloniki , Thessaloniki ,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lior","family":"Jankelson","sequence":"additional","affiliation":[{"name":"Leon H. Charney Division of Cardiology, NYU Langone Health, New York University School of Medicine , New York, NY 10016 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"2025111918523577200_ztaf100-B1","doi-asserted-by":"crossref","first-page":"ITC33","DOI":"10.7326\/AITC201703070","article-title":"Atrial fibrillation","volume":"166","author":"Zimetbaum","year":"2017","journal-title":"Ann Intern Med"},{"key":"2025111918523577200_ztaf100-B2","doi-asserted-by":"crossref","first-page":"1609","DOI":"10.1093\/europace\/euw295","article-title":"2016 ESC guidelines for the management of atrial fibrillation developed in collaboration with EACTS","volume":"18","author":"Kirchhof","year":"2016","journal-title":"Europace"},{"key":"2025111918523577200_ztaf100-B3","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.1016\/j.hrthm.2016.03.003","article-title":"Typical, atypical, and asymptomatic presentations of new-onset atrial fibrillation in the community: characteristics and prognostic implications","volume":"13","author":"Siontis","year":"2016","journal-title":"Hear Rhythm Elsevier"},{"key":"2025111918523577200_ztaf100-B4","doi-asserted-by":"crossref","first-page":"e0195088","DOI":"10.1371\/journal.pone.0195088","article-title":"Estimated prevalence of undiagnosed atrial fibrillation in the United States. Novo G, ed","volume":"13","author":"Turakhia","year":"2018","journal-title":"PLoS One"},{"key":"2025111918523577200_ztaf100-B5","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1161\/01.CIR.98.10.946","article-title":"Impact of atrial fibrillation on the risk of death: the Framingham Heart Study","volume":"98","author":"Benjamin","year":"1998","journal-title":"Circulation"},{"key":"2025111918523577200_ztaf100-B6","doi-asserted-by":"crossref","first-page":"2467","DOI":"10.1056\/NEJMoa1311376","article-title":"Atrial fibrillation in patients with cryptogenic stroke","volume":"370","author":"Gladstone","year":"2014","journal-title":"N Engl J Med"},{"key":"2025111918523577200_ztaf100-B7","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1136\/heartjnl-2019-314898","article-title":"Stroke and thromboembolism prevention in atrial fibrillation","volume":"106","author":"Jame","year":"2020","journal-title":"Heart"},{"key":"2025111918523577200_ztaf100-B8","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1016\/j.hrthm.2023.02.002","article-title":"Very long term outcomes of atrial fibrillation ablation","volume":"20","author":"Winkle","year":"2023","journal-title":"Hear Rhythm"},{"key":"2025111918523577200_ztaf100-B9","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/S0140-6736(19)31721-0","article-title":"An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction","volume":"394","author":"Attia","year":"2019","journal-title":"Lancet"},{"key":"2025111918523577200_ztaf100-B10","doi-asserted-by":"crossref","first-page":"e009355","DOI":"10.1161\/CIRCEP.120.009355","article-title":"Artificial intelligence-electrocardiography to predict incident atrial fibrillation: a population-based study","volume":"13","author":"Christopoulos","year":"2020","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"2025111918523577200_ztaf100-B11","doi-asserted-by":"crossref","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":"2025111918523577200_ztaf100-B12","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1161\/CIRCULATIONAHA.121.057480","article-title":"ECG-based deep learning and clinical risk factors to predict atrial fibrillation","volume":"145","author":"Khurshid","year":"2022","journal-title":"Circulation"},{"key":"2025111918523577200_ztaf100-B13","doi-asserted-by":"crossref","first-page":"e000102","DOI":"10.1161\/JAHA.112.000102","article-title":"Simple risk model predicts incidence of atrial fibrillation in a racially and geographically diverse population: the CHARGE-AF consortium","volume":"2","author":"Alonso","year":"2013","journal-title":"J Am Heart Assoc"},{"key":"2025111918523577200_ztaf100-B14"},{"key":"2025111918523577200_ztaf100-B15","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.jacep.2022.09.021","article-title":"Development of an AI-driven QT correction algorithm for patients in atrial fibrillation","volume":"9","author":"Tarabanis","year":"2022","journal-title":"JACC Clin Electrophysiol"},{"key":"2025111918523577200_ztaf100-B16","doi-asserted-by":"crossref","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":"2025111918523577200_ztaf100-B17","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"2025111918523577200_ztaf100-B18","doi-asserted-by":"crossref","first-page":"1287","DOI":"10.1161\/CIRCULATIONAHA.120.047829","article-title":"Deep neural networks can predict new-onset atrial fibrillation from the 12-lead ECG and help identify those at risk of atrial fibrillation\u2013related stroke","volume":"143","author":"Raghunath","year":"2021","journal-title":"Circulation"},{"key":"2025111918523577200_ztaf100-B19","doi-asserted-by":"crossref","first-page":"e008153","DOI":"10.1161\/CIRCOUTCOMES.121.008153","article-title":"Use of artificial intelligence tools across different clinical settings: a cautionary tale","volume":"14","author":"Siontis","year":"2021","journal-title":"Circ Cardiovasc Qual Outcomes"},{"key":"2025111918523577200_ztaf100-B20","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1001\/jamacardio.2023.3701","article-title":"Deep learning of electrocardiograms in sinus rhythm from US veterans to predict atrial fibrillation","volume":"8","author":"Yuan","year":"2023","journal-title":"JAMA Cardiol"},{"key":"2025111918523577200_ztaf100-B21","volume-title":"2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)","author":"Hancock"},{"key":"2025111918523577200_ztaf100-B22","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1038\/s41569-020-00503-2","article-title":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management","volume":"18","author":"Siontis","year":"2021","journal-title":"Nat Rev Cardiol"},{"key":"2025111918523577200_ztaf100-B23","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1093\/jamia\/ocac020","article-title":"Inaccuracies in electronic health records smoking data and a potential approach to address resulting underestimation in determining lung cancer screening eligibility","volume":"29","author":"Kukhareva","year":"2022","journal-title":"J Am Med Informatics Assoc"},{"key":"2025111918523577200_ztaf100-B24","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1055\/s-0041-1731784","article-title":"Why is the electronic health record so challenging for research and clinical care?","volume":"60","author":"Holmes","year":"2021","journal-title":"Methods Inf Med"},{"key":"2025111918523577200_ztaf100-B25","doi-asserted-by":"crossref","first-page":"956","DOI":"10.1016\/j.jacep.2024.01.022","article-title":"QTNet: predicting drug-induced QT prolongation with artificial intelligence- enabled electrocardiograms","volume":"10","author":"Zhang","year":"2024","journal-title":"JACC Clin Electrophysiol"},{"key":"2025111918523577200_ztaf100-B26","doi-asserted-by":"crossref","first-page":"e010922208402","DOI":"10.2174\/1573403X18666220901102557","article-title":"CHARGE-AF: a useful score for atrial fibrillation prediction?","volume":"19","author":"Goudis","year":"2023","journal-title":"Curr Cardiol Rev"}],"container-title":["European Heart Journal - Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ehjdh\/advance-article-pdf\/doi\/10.1093\/ehjdh\/ztaf100\/64105520\/ztaf100.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/6\/6\/1134\/64105520\/ztaf100.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/6\/6\/1134\/64105520\/ztaf100.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T23:52:49Z","timestamp":1763596369000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/6\/6\/1134\/8239531"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"references-count":26,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,8,22]]},"published-print":{"date-parts":[[2025,11,20]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztaf100","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,11]]},"published":{"date-parts":[[2025,8,22]]}}}