{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:51:03Z","timestamp":1787010663490,"version":"build-2736575974"},"posted":{"date-parts":[[2024,8,14]]},"group-title":"Cardiovascular Medicine","reference-count":34,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T00:00:00Z","timestamp":1723593600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2024,8,14]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>AF risk estimation is feasible using clinical factors, inherited predisposition, and artificial intelligence (AI)-enabled electrocardiogram (ECG) analysis.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To test whether integrating these distinct risk signals improves AF risk estimation.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>In the UK Biobank prospective cohort study, we estimated AF risk using three models derived from external populations: the well-validated Cohorts for Aging in Heart and Aging Research in Genomic Epidemiology AF (CHARGE-AF) clinical score, a 1,113,667-variant AF polygenic risk score (PRS), and a published AI-enabled ECG-based AF risk model (ECG-AI). We estimated discrimination of 5-year incident AF using time-dependent area under the receiver operating characteristic (AUROC) and average precision (AP).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Among 49,293 individuals (mean age 65\u00b18 years, 52% women), 825 (2.4%) developed AF within 5 years. Using single models, discrimination of 5-year incident AF was higher using ECG-AI (AUROC 0.705 [95%CI 0.686-0.724]; AP 0.085 [0.071-0.11]) and CHARGE-AF (AUROC 0.785 [0.769-0.801]; AP 0.053 [0.048-0.061]) versus the PRS (AUROC 0.618, [0.598-0.639]; AP 0.038 [0.028-0.045]). The inclusion of all components (\u201cPredict-AF3\u201d) was the best performing model (AUROC 0.817 [0.802-0.832]; AP 0.11 [0.091-0.15], p&lt;0.01 vs CHARGE-AF+ECG-AI), followed by the two component model of CHARGE-AF+ECG-AI (AUROC 0.802 [0.786-0.818]; AP 0.098 [0.081-0.13]). Using Predict-AF3, individuals at high AF risk (i.e., 5-year predicted AF risk &gt;2.5%) had a 5-year cumulative incidence of AF of 5.83% (5.33-6.32). At the same threshold, the 5-year cumulative incidence of AF was progressively higher according to the number of models predicting high risk (zero: 0.67% [0.51-0.84], one: 1.48% [1.28-1.69], two: 4.48% [3.99-4.98]; three: 11.06% [9.48-12.61]), and Predict-AF3 achieved favorable net reclassification improvement compared to both CHARGE-AF+ECG-AI (0.039 [0.015-0.066]) and CHARGE-AF+PRS (0.033 [0.0082-0.059]).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Integration of clinical, genetic, and AI-derived risk signals improves discrimination of 5-year AF risk over individual components. Models such as Predict-AF3 have substantial potential to improve prioritization of individuals for AF screening and preventive interventions.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2024.08.13.24311944","type":"posted-content","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T15:25:14Z","timestamp":1723649114000},"source":"Crossref","is-referenced-by-count":4,"title":["Integrating Clinical, Genetic, and Electrocardiogram-Based Artificial Intelligence to Estimate Risk of Incident Atrial Fibrillation"],"prefix":"10.64898","author":[{"given":"Shinwan","family":"Kany","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joel T.","family":"R\u00e4m\u00f6","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel F.","family":"Friedman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu-Chen","family":"Weng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carolina","family":"Roselli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min Seo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akl C.","family":"Fahed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9599-4866","authenticated-orcid":false,"given":"Steven A.","family":"Lubitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahnaz","family":"Maddah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2067-0533","authenticated-orcid":false,"given":"Patrick T.","family":"Ellinor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaan","family":"Khurshid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2024081613100708000_2024.08.13.24311944v1.1","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.0000121736.16643.11"},{"key":"2024081613100708000_2024.08.13.24311944v1.2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.120.316341"},{"key":"2024081613100708000_2024.08.13.24311944v1.3","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.121.057014"},{"key":"2024081613100708000_2024.08.13.24311944v1.4","doi-asserted-by":"crossref","unstructured":"Uittenbogaart SB , Verbiest-van Gurp N , Lucassen WAM , et al. Opportunistic screening versus usual care for detection of atrial fibrillation in primary care: cluster randomised controlled trial. BMJ. 2020;370:m3208.","DOI":"10.1136\/bmj.m3208"},{"key":"2024081613100708000_2024.08.13.24311944v1.5","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.114.014343"},{"key":"2024081613100708000_2024.08.13.24311944v1.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtcvs.2012.05.060"},{"key":"2024081613100708000_2024.08.13.24311944v1.7","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-007-0543-5"},{"key":"2024081613100708000_2024.08.13.24311944v1.8","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.112.000102"},{"key":"2024081613100708000_2024.08.13.24311944v1.9","doi-asserted-by":"crossref","first-page":"e003355","DOI":"10.1161\/CIRCGEN.121.003355","article-title":"Predictive Accuracy of a Clinical and Genetic Risk Model for Atrial Fibrillation","volume":"14","year":"2021","journal-title":"Circ Genom Precis Med"},{"key":"2024081613100708000_2024.08.13.24311944v1.10","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1038\/s41591-020-0800-0","article-title":"Polygenic and clinical risk scores and their impact on age at onset and prediction of cardiometabolic diseases and common cancers","volume":"26","year":"2020","journal-title":"Nat Med"},{"key":"2024081613100708000_2024.08.13.24311944v1.11","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","year":"2022","journal-title":"Circulation"},{"key":"2024081613100708000_2024.08.13.24311944v1.12","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.120.047829"},{"key":"2024081613100708000_2024.08.13.24311944v1.13","unstructured":"Roselli C , Surakka I , Olesen MS , Sveinbjornsson G , Marston NA , Choi SH , Holm H , Chaffin M , Gudbjartsson D , Hill MC , Aegisdottir H , Albert CM , Alonso A , Anderson CD , Arking DE , Arnar DO , Barnard J , Benjamin EJ , Braunwald E , Brumpton B , Campbell A , Chami N , Chasman DI , Cho K , Choi EK , Christophersen IE , Chung MK , Conen D , Crijns HJ , Cutler MJ , Czuba T , Damrauer SM , Martin D , Dorr M , Dudink E , Duong T , Eriskstrup C , Esko T , Fatkin D , Faul JD , Ferreira M , Freitag DF , Ganesh SK , Gaziano M , Geelhoed B , Ghouse J , Gieger C , Giulianini F , Graham SE , Gudnason V , Guo X , Haggerty C , Jukema JW , Jurgens SJ , Kaab S , Kane JP , Kany S , Kardia SLR , Kavousi M , Khurshid S , Kamanu FK , Kirchhof P , Kleber ME , Knight S , Komuro I , Krieger JE , Launer LJ , Li D , Lin H , Lin HJ , Loos RJF , Lotta L , Lubitz SA , Lunetta KL , Macfarlane PW , Magnusson PKE , Malik R , Mantineo H , Marcus GM , Marz W , McManus DD , Melander O , Melloni GEM , Meyre P , Miyazawa K , Mohanty S , Monfort LM , Muller-Nurasyid M , Nafissi NA , Natale A , Nazarian S , Ostrowski SR , Pak HN , Pang S , Pedersen OB , Pedersen NL , Pereira AC , Pirruccello JP , Preuss M , Psaty BM , Pullinger CR , Rader DJ , Ramo JT , Ridker PM , Rienstra M , Risch L , Roden DM , Rotter JI , Sabatine MS , Schunkert H , Shah SH , Shim J , Shoemaker MB , Simonson B , Sinner MF , Smit RAJ , Smith JA , Smith NL , Smith JG , Soliman EZ , Sorensen E , Sotoodehnia N , Strbian D , Stricker BH , Teder-Laving M , Sun YV , Theriault S , Thorolfsdottir RB , Thorsteinsdottir U , Tveit A , Van der Harst P , van Meurs J , Wang B , Weiss S , Wells QS , Weng LC , Wilson PW , Xiao L , Yang PS , Yao J , Yoneda ZT , Zeller T , Zeng L , Zhao W , Zhou W , Zollner S , The Biobank Japan Project, Regeneron Genetics Center, DBDS Genomic Consortium, Ruff CT , Bundgaard H , Willer C , Stefansson K , Ellinor PT . Meta-analysis of Genome-wide associations and polygenic risk prediction for atrial fibrillation in more than 180,000 cases. Nat Genet. 2024. Published online2024."},{"key":"2024081613100708000_2024.08.13.24311944v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0579-z"},{"key":"2024081613100708000_2024.08.13.24311944v1.15","doi-asserted-by":"crossref","first-page":"1225","DOI":"10.1038\/s41588-018-0133-9","article-title":"Multi-ethnic genome-wide association study for atrial fibrillation","volume":"50","year":"2018","journal-title":"Nat Genet"},{"key":"2024081613100708000_2024.08.13.24311944v1.16","doi-asserted-by":"crossref","first-page":"1776","DOI":"10.1038\/s41467-019-09718-5","article-title":"Polygenic prediction via Bayesian regression and continuous shrinkage priors","volume":"10","year":"2019","journal-title":"Nat Commun"},{"issue":"7","key":"2024081613100708000_2024.08.13.24311944v1.17","first-page":"2015","article-title":"Second-generation PLINK: rising to the challenge of larger and richer datasets","volume":"4","year":"2015","journal-title":"Gigascience"},{"key":"2024081613100708000_2024.08.13.24311944v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ahj.2016.05.004"},{"key":"2024081613100708000_2024.08.13.24311944v1.19","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.118.006273"},{"key":"2024081613100708000_2024.08.13.24311944v1.20","doi-asserted-by":"publisher","DOI":"10.1002\/sim.5647"},{"key":"2024081613100708000_2024.08.13.24311944v1.21","doi-asserted-by":"crossref","first-page":"1671","DOI":"10.1002\/sim.7606","article-title":"A threshold-free summary index of prediction accuracy for censored time to event data","volume":"37","year":"2018","journal-title":"Stat Med"},{"key":"2024081613100708000_2024.08.13.24311944v1.22","doi-asserted-by":"publisher","DOI":"10.1111\/j.0006-341X.2000.00779.x"},{"key":"2024081613100708000_2024.08.13.24311944v1.23","doi-asserted-by":"crossref","first-page":"e009355","DOI":"10.1161\/CIRCEP.120.009355","article-title":"Artificial Intelligence\u2013Electrocardiography to Predict Incident Atrial Fibrillation","volume":"13","year":"2020","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"2024081613100708000_2024.08.13.24311944v1.24","doi-asserted-by":"publisher","DOI":"10.1002\/sim.8570"},{"key":"2024081613100708000_2024.08.13.24311944v1.25","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4085"},{"key":"2024081613100708000_2024.08.13.24311944v1.26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ahj.2024.03.001","article-title":"Risk calculator for incident atrial fibrillation across a range of prediction horizons","volume":"272","year":"2024","journal-title":"Am Heart J"},{"key":"2024081613100708000_2024.08.13.24311944v1.27","doi-asserted-by":"crossref","first-page":"e008997","DOI":"10.1161\/CIRCEP.120.008997","article-title":"Performance of Atrial Fibrillation Risk Prediction Models in Over 4 Million Individuals","volume":"14","year":"2021","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"2024081613100708000_2024.08.13.24311944v1.28","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1161\/CIRCGEN.122.003808","article-title":"Genetic Susceptibility to Atrial Fibrillation Identified via Deep Learning of 12-Lead Electrocardiograms","volume":"16","year":"2023","journal-title":"Circ Genom Precis Med"},{"key":"2024081613100708000_2024.08.13.24311944v1.29","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1093\/eurheartj\/ehac460","article-title":"A polygenic risk score predicts atrial fibrillation in cardiovascular disease","volume":"44","year":"2023","journal-title":"Eur Heart J"},{"key":"2024081613100708000_2024.08.13.24311944v1.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2024.04.085"},{"key":"2024081613100708000_2024.08.13.24311944v1.31","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehaa612"},{"key":"2024081613100708000_2024.08.13.24311944v1.32","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.119.007607"},{"key":"2024081613100708000_2024.08.13.24311944v1.33","doi-asserted-by":"crossref","first-page":"e015218","DOI":"10.1161\/JAHA.119.015218","article-title":"Comparison of Cardiovascular Risk Factors in European Population Cohorts for Predicting Atrial Fibrillation and Heart Failure, Their Subsequent Onset, and Death","volume":"9","year":"2020","journal-title":"J Am Heart Assoc"},{"key":"2024081613100708000_2024.08.13.24311944v1.34","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwx246"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.08.13.24311944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:09:19Z","timestamp":1768507759000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2024.08.13.24311944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,14]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1101\/2024.08.13.24311944","relation":{},"subject":[],"published":{"date-parts":[[2024,8,14]]},"subtype":"preprint"}}