{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T04:08:20Z","timestamp":1793333300475,"version":"4.5.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002910","name":"French Community of Belgium","doi-asserted-by":"publisher","award":["038733"],"award-info":[{"award-number":["038733"]}],"id":[{"id":"10.13039\/501100002910","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"European Union\u2019s Horizon 2020 research and innovation programme","doi-asserted-by":"publisher","award":["101034383"],"award-info":[{"award-number":["101034383"]}],"id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]}],"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>Introduction<\/jats:title>\n                    <jats:p>Integrating machine learning (ML) models into wearable or connected devices to deliver early warning alerts prior to atrial fibrillation (AF) onset may represent an effective preventive strategy. Machine learning algorithms applied to two-lead Holter electrocardiogram (ECG) recordings can support the development of predictive models capable of detecting imminent paroxysmal AF episodes within short-term windows. This approach could facilitate a more targeted \u2018pill-in-the-pocket\u2019 (PITP)-like intervention strategy, potentially enhancing timely therapeutic actions and improving patient outcomes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>This study aimed to identify patients currently in sinus rhythm who will experience an AF episode within the subsequent hours by analysing 24-h Holter ECG recordings with ML.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We established a novel database comprising 95 871 manually analysed Holter ECG recordings, identifying 1319 episodes of paroxysmal AF from 872 patients. Among these, 835 AF episodes from 506 recordings had more than 60\u2005min of normal sinus rhythm prior to AF onset and more than 10\u2005min of sustained AF following onset. Patients were stratified into five age groups: all patients combined, under 60 years, 60\u201370 years, 70\u201380 years, and over 80 years. Additionally, 365 recordings from 347 patients without rhythm abnormalities were identified and classified, from which two ECG segments were selected. Two deep learning (DL) models were trained on raw ECG data to predict AF onset. To compare DL models with traditional ML approaches using heart rate variability (HRV) parameters, we employed a random forest classifier and a gradient-boosted decision tree model (XGBoost, XGB).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The decision trees models trained on HRV parameters delivered the best predictive performance. The most significant results were observed for episodes lasting more than 5\u2005min of AF, achieving an area under the receiver operating characteristic curve of 0.919 (95% CI: 0.879\u20130.958) and an area under the precision\u2013recall curve of 0.919 (95% CI: 0.879\u20130.958) for XGB. At a decision threshold of 0.5, accuracy was 84.5% (81.2\u201387.8), sensitivity was 83.0% (79.5\u201386.4), specificity was 86.6% (79.3\u201393.9), positive predictive value was 90.2% (85.5\u201394.9), negative predictive value was 78.4% (74.7\u201382.1), and the F1 score was 86.2% (83.5\u201389.0).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These findings indicate that HRV parameters contain crucial information for the short-term prediction of AF onset, supporting preventive strategies. Integration of such predictive models into wearable mHealth technologies could facilitate a PITP-like preventive approach, potentially reducing AF-related morbidity. Prospective studies are warranted to validate these promising results further.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ehjdh\/ztaf104","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T12:00:46Z","timestamp":1757592046000},"page":"1159-1168","source":"Crossref","is-referenced-by-count":9,"title":["Short-term atrial fibrillation onset prediction using machine learning"],"prefix":"10.1093","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4636-848X","authenticated-orcid":false,"given":"Jean-Marie","family":"Gr\u00e9goire","sequence":"first","affiliation":[{"name":"Cardiology Department, Universit\u00e9 de Mons , Avenue Maistriau , 25, Mons 7000 ,","place":["Belgium"]},{"name":"IRIDIA, Universit\u00e9 Libre de Bruxelles , Av. Adolphe Buyl, Bruxelles 1000 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0705-3514","authenticated-orcid":false,"given":"C\u00e9dric","family":"Gilon","sequence":"additional","affiliation":[{"name":"IRIDIA, Universit\u00e9 Libre de Bruxelles , Av. Adolphe Buyl, Bruxelles 1000 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8261-238X","authenticated-orcid":false,"given":"Fran\u00e7ois","family":"Marelli","sequence":"additional","affiliation":[{"name":"ISIA Lab, Universit\u00e9 de Mons , Boulevard Dolez , 31, Mons 7000 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5820-7360","authenticated-orcid":false,"given":"Hugues","family":"Bersini","sequence":"additional","affiliation":[{"name":"IRIDIA, Universit\u00e9 Libre de Bruxelles , Av. Adolphe Buyl, Bruxelles 1000 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurent","family":"Groben","sequence":"additional","affiliation":[{"name":"Cardiology Department, Centre Hospitalier de Luxembourg , Rue Nicolas Ernest Barbl\u00e9, 4, Luxembourg 1210, G-D de Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3014-872X","authenticated-orcid":false,"given":"Thomas","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Cardiology Department, CHU Brugmann , Place A Van Gehuchten, 4, Bruxelles 1020 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernard","family":"Deruyter","sequence":"additional","affiliation":[{"name":"Cardiology Department, Europe Hospitals , Av. De Fr\u00e9 206, Bruxelles 1180 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal","family":"Godart","sequence":"additional","affiliation":[{"name":"Cardiology Department, CHU Helora , Bd John Fitzgerald Kennedy 2, Mons 7000 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7787-1937","authenticated-orcid":false,"given":"St\u00e9phane","family":"Carlier","sequence":"additional","affiliation":[{"name":"Cardiology Department, Universit\u00e9 de Mons , Avenue Maistriau , 25, Mons 7000 ,","place":["Belgium"]},{"name":"Cardiology Department, CHU Helora , Bd John Fitzgerald Kennedy 2, Mons 7000 ,","place":["Belgium"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"2025111918512649100_ztaf104-B1","doi-asserted-by":"crossref","first-page":"3314","DOI":"10.1093\/eurheartj\/ehae176","article-title":"2024 ESC guidelines for the management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS): developed by the task force for the management of atrial fibrillation of the European Society of Cardiology (ESC), with the special contribution of the European Heart Rhythm Association (EHRA) of the ESC. Endorsed by the European Stroke Organisation (ESO)","volume":"45","author":"Van Gelder","year":"2024","journal-title":"Eur Heart J"},{"key":"2025111918512649100_ztaf104-B2","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-related stroke","volume":"143","author":"Raghunath","year":"2021","journal-title":"Circulation"},{"key":"2025111918512649100_ztaf104-B3","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":"2025111918512649100_ztaf104-B4","doi-asserted-by":"publisher","first-page":"12818","DOI":"10.1038\/s41598-021-92172-5","article-title":"A new deep learning algorithm of 12-lead electrocardiogram for identifying atrial fibrillation during sinus rhythm","volume":"11 (1)","author":"Baek","year":"2021","journal-title":"Sci Rep"},{"key":"2025111918512649100_ztaf104-B5","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":"2025111918512649100_ztaf104-B6","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1016\/j.jacep.2023.04.008","article-title":"Detecting paroxysmal atrial fibrillation from an electrocardiogram in sinus rhythm: external validation of the AI approach","volume":"9","author":"Gruwez","year":"2023","journal-title":"JACC Clin Electrophysiol"},{"key":"2025111918512649100_ztaf104-B7","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":"2025111918512649100_ztaf104-B8","doi-asserted-by":"crossref","first-page":"4935","DOI":"10.1093\/eurheartj\/ehae691","article-title":"Another piece in the puzzle of atrial fibrillation risk: clinical, genetic, and electrocardiogram-based artificial intelligence","volume":"45","author":"Kany","year":"2024","journal-title":"Eur Heart J"},{"key":"2025111918512649100_ztaf104-B9","doi-asserted-by":"crossref","first-page":"4994","DOI":"10.1093\/eurheartj\/ehad738","article-title":"Prevention of atrial fibrillation: a call to action","volume":"44","author":"Elliott","year":"2023","journal-title":"Eur Heart J"},{"key":"2025111918512649100_ztaf104-B10","first-page":"1","article-title":"IRIDIA-AF, a large paroxysmal atrial fibrillation long-term electrocardiogram monitoring database","volume":"10","author":"Gilon","year":"2023","journal-title":"Sci Data"},{"key":"2025111918512649100_ztaf104-B11","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1093\/ehjdh\/ztab071","article-title":"Atrial fibrillation risk prediction from the 12-lead electrocardiogram using digital biomarkers and deep representation learning","volume":"2","author":"Biton","year":"2021","journal-title":"Eur Heart J Digit Health"},{"key":"2025111918512649100_ztaf104-B12","doi-asserted-by":"crossref","first-page":"922","DOI":"10.3389\/fphys.2018.00922","article-title":"Quantitative analysis of the effect of an ectopic beat on the heart rate variability in the resting condition","volume":"9","author":"Choi","year":"2018","journal-title":"Front Physiol"},{"key":"2025111918512649100_ztaf104-B13","doi-asserted-by":"crossref","first-page":"64873","DOI":"10.1109\/ACCESS.2020.2984412","article-title":"Explainability of a machine learning granting scoring model in peer-to-peer lending","volume":"8","author":"Ariza-Garzon","year":"2020","journal-title":"IEEE Access"},{"key":"2025111918512649100_ztaf104-B14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1161\/CIRCEP.119.007284","article-title":"Age and sex estimation using artificial intelligence from standard 12-lead ECGs","volume":"12","author":"Attia","year":"2019","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"2025111918512649100_ztaf104-B15","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1093\/ehjdh\/ztab043","article-title":"The 12-lead electrocardiogram as a biomarker of biological age","volume":"2","author":"Ladejobi","year":"2021","journal-title":"Eur Heart J Digit Health"},{"key":"2025111918512649100_ztaf104-B16","doi-asserted-by":"crossref","first-page":"258","DOI":"10.3389\/fpubh.2017.00258","article-title":"An overview of heart rate variability metrics and norms","volume":"5","author":"Shaffer","year":"2017","journal-title":"Front Public Health"},{"key":"2025111918512649100_ztaf104-B17","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1016\/S0735-1097(97)00554-8","article-title":"Twenty-four hour time domain heart rate variability and heart rate: relations to age and gender over nine decades","volume":"31","author":"Umetani","year":"1998","journal-title":"J Am Coll Cardiol"},{"key":"2025111918512649100_ztaf104-B18","doi-asserted-by":"crossref","first-page":"8697","DOI":"10.3390\/s23218697","article-title":"Age and gender impact on heart rate variability towards noninvasive glucose measurement","volume":"23","author":"Stojmenski","year":"2023","journal-title":"Sensors"},{"key":"2025111918512649100_ztaf104-B19","doi-asserted-by":"crossref","first-page":"71","DOI":"10.5334\/gh.873","article-title":"Age and sex differences in heart rate variability and vagal specific patterns\u2014baependi heart study","volume":"15","author":"Geovanini","year":"2020","journal-title":"Glob Heart"},{"key":"2025111918512649100_ztaf104-B20","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.acvd.2022.04.006","article-title":"Role of the autonomic nervous system and premature atrial contractions in short-term paroxysmal atrial fibrillation forecasting: insights from machine learning models","volume":"115","author":"Gr\u00e9goire","year":"2022","journal-title":"Arch Cardiovasc Dis"},{"key":"2025111918512649100_ztaf104-B21","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1093\/oxfordjournals.eurheartj.a014868","article-title":"Heart rate variability. Standards of measurement, physiological interpretation, and clinical use","volume":"17","author":"Malik","year":"1996","journal-title":"Eur Heart J"},{"key":"2025111918512649100_ztaf104-B22","doi-asserted-by":"crossref","first-page":"213","DOI":"10.3389\/fpsyg.2017.00213","article-title":"Heart rate variability and cardiac vagal tone in psychophysiological research\u2014recommendations for experiment planning, data analysis, and data reporting","volume":"8","author":"Laborde","year":"2017","journal-title":"Front Psychol"},{"key":"2025111918512649100_ztaf104-B23","first-page":"1","article-title":"Heart rate fragmentation: a new approach to the analysis of cardiac interbeat interval dynamics","volume":"8","author":"Costa","year":"2017","journal-title":"Front Physiol"},{"key":"2025111918512649100_ztaf104-B24","doi-asserted-by":"crossref","first-page":"H 256","DOI":"10.1152\/ajpheart.00421.2020","article-title":"Fragmented sinoatrial dynamics in the prediction of atrial fibrillation: the multi-ethnic study of atherosclerosis","author":"Costa","year":"2021","journal-title":"Am J Physiol Heart Circ Physiol"},{"key":"2025111918512649100_ztaf104-B25","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s10840-018-0463-7","article-title":"Prevalence and predictors of atrial arrhythmias in patients with sinus node dysfunction and atrial pacing","volume":"53","author":"Bukari","year":"2018","journal-title":"J Interv Card Electrophysiol"},{"key":"2025111918512649100_ztaf104-B26","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1080\/00015385.2023.2177371","article-title":"Autonomic nervous system assessment using heart rate variability","volume":"78","author":"Gr\u00e9goire","year":"2023","journal-title":"Acta Cardiol"},{"key":"2025111918512649100_ztaf104-B27","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1109\/10.959330","article-title":"Do existing measures of Poincar\u00e9 plot geometry reflect nonlinear features of heart rate variability?","volume":"48","author":"Brennan","year":"2001","journal-title":"IEEE Trans Biomed Eng"},{"key":"2025111918512649100_ztaf104-B28","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.jacc.2016.10.059","article-title":"Cardiac autonomic dysfunction and incidence of atrial fibrillation","volume":"69","author":"Agarwal","year":"2017","journal-title":"J Am Coll Cardiol"},{"key":"2025111918512649100_ztaf104-B29","doi-asserted-by":"crossref","first-page":"2753","DOI":"10.1161\/01.CIR.0000018443.44005.D8","article-title":"Autonomic tone variations before the onset of paroxysmal atrial fibrillation","volume":"105","author":"Bettoni","year":"2002","journal-title":"Circulation"},{"key":"2025111918512649100_ztaf104-B30","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1093\/ehjdh\/ztad039","article-title":"Determine atrial fibrillation burden with a photoplethysmographic mobile sensor: the atrial fibrillation burden trial: detection and quantification of episodes of atrial fibrillation using a cloud analytics service connected to a wearable with photoplethysmographic sensor","volume":"4","author":"Reissenberger","year":"2023","journal-title":"Eur Heart J Digit Health"},{"key":"2025111918512649100_ztaf104-B31","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1093\/europace\/euac144","article-title":"Searching for atrial fibrillation: looking harder, looking longer, and in increasingly sophisticated ways. An EHRA position paper","volume":"25","author":"Kalarus","year":"2023","journal-title":"Europace"},{"key":"2025111918512649100_ztaf104-B32","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1093\/ehjdh\/ztad054","article-title":"Smartphone-based atrial fibrillation screening in the general population: feasibility and impact on medical treatment","volume":"4","author":"Gruwez","year":"2023","journal-title":"Eur Heart J Digit Health"},{"key":"2025111918512649100_ztaf104-B33","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/j.jacasi.2021.09.004","article-title":"Photoplethysmography-based machine learning approaches for atrial fibrillation prediction: a report from the Huawei heart study","volume":"1","author":"Guo","year":"2021","journal-title":"JACC Asia"},{"key":"2025111918512649100_ztaf104-B34","doi-asserted-by":"crossref","first-page":"E010204","DOI":"10.1161\/CIRCEP.121.010204","article-title":"Open-label, multicenter study of flecainide acetate oral inhalation solution for acute conversion of recent-onset, symptomatic atrial fibrillation to Sinus rhythm","volume":"15","author":"Crijns","year":"2022","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"2025111918512649100_ztaf104-B35","doi-asserted-by":"crossref","first-page":"1515","DOI":"10.1016\/j.jacep.2022.07.010","article-title":"Safety of pill-in-the-pocket class 1C antiarrhythmic drugs for atrial fibrillation","volume":"8","author":"Markman","year":"2022","journal-title":"JACC Clin Electrophysiol"},{"key":"2025111918512649100_ztaf104-B36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/europace\/euad162","article-title":"Real-world utilization of the pill-in-the-pocket method for terminating episodes of atrial fibrillation: data from the multinational antiarrhythmic interventions for managing atrial fibrillation (AIM-AF) survey","volume":"25","author":"Reiffel","year":"2023","journal-title":"EP Europace"}],"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\/ztaf104\/64247499\/ztaf104.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/6\/6\/1159\/64247499\/ztaf104.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/6\/6\/1159\/64247499\/ztaf104.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T23:51:39Z","timestamp":1763596299000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/6\/6\/1159\/8251747"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,9,11]]},"published-print":{"date-parts":[[2025,11,20]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztaf104","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,11]]},"published":{"date-parts":[[2025,9,11]]}}}