{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:43:59Z","timestamp":1785908639951,"version":"3.56.0"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cardiovasc. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Postoperative atrial fibrillation is a common complication after cardiac surgery, associated with both short- and long-term adverse effects. Persistent forms of postoperative atrial fibrillation lasting until hospital discharge are less frequent but clinically significant. Despite its impact, reliable prediction remains challenging. This study aimed to develop and evaluate machine learning models that integrate electrocardiographic and clinical variables to predict atrial fibrillation at discharge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this retrospective single-center study, 1,905 patients undergoing cardiac surgery were analyzed. Perioperative 12-lead electrocardiographic parameters and clinical variables were preselected using univariable logistic regression (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&amp;lt;\u20090.1). Various machine learning models, including neural networks, support vector machines, k-nearest neighbors' random forests, and Bayesian classifiers were trained, using 10-fold cross-validation and subsequently evaluated on an independent test set. A genetic algorithm was applied for variable selection, and a reject option was implemented to withhold uncertain predictions.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Of 1,905 patients 2.2% were discharged in atrial fibrillation. The final neural network model yielded a 69.9% coverage rate, with 99.2% of all predictions being correct (95% CI: 98.6\u201399.6). Key predictors included age, CHADS\n                      <jats:sub>2<\/jats:sub>\n                      -VASc score, left ventricular ejection fraction, EuroSCORE II, cardiopulmonary bypass time, prior cardiogenic shock, perioperative atrioventricular block, and mitral valve surgery.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A machine learning model integrating perioperative electrocardiographic and clinical variables demonstrated robust performance in predicting the absence of atrial fibrillation at discharge, accurately identifying more than two thirds of patients. For the remaining patients, management continued to rely on clinical judgment. This approach offers a valuable tool for improved risk stratification and may facilitate the implementation of more targeted prophylactic strategies following cardiac surgery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcvm.2026.1886483","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T04:46:39Z","timestamp":1785905199000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Neural network-based prediction of atrial fibrillation at discharge following cardiac surgery"],"prefix":"10.3389","volume":"13","author":[{"given":"Spela","family":"Leiler","sequence":"first","affiliation":[{"name":"Department of Cardiac Surgery, Klinikum Nuernberg, Paracelsus Medical University","place":["Nuremberg, Germany"]},{"name":"Paracelsus Medical University","place":["Nuremberg, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wolfgang","family":"Hitzl","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology and Optometry, Paracelsus Medical University","place":["Salzburg, Austria"]},{"name":"Research Program Experimental Ophthalmology and Glaucoma Research, Paracelsus Medical University","place":["Salzburg, Austria"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andre","family":"Bauer","sequence":"additional","affiliation":[{"name":"College of Computing, Illinois Institute of Technology","place":["Chicago, IL, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentin","family":"Guenzler","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine II \u2013 Cardiology, Pneumology and Intensive Care, University Hospital Regensburg","place":["Regensburg, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Theodor","family":"Fischlein","sequence":"additional","affiliation":[{"name":"Department of Cardiac Surgery, Klinikum Nuernberg, Paracelsus Medical University","place":["Nuremberg, Germany"]},{"name":"Paracelsus Medical University","place":["Nuremberg, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomas","family":"Holubec","sequence":"additional","affiliation":[{"name":"Department of Cardiac Surgery, Klinikum Nuernberg, Paracelsus Medical University","place":["Nuremberg, Germany"]},{"name":"Paracelsus Medical University","place":["Nuremberg, Germany"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jurij Matija","family":"Kalisnik","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, University of Ljubljana","place":["Ljubljana, Slovenia"]},{"name":"Department of Cardiothoracic and Vascular Surgery, University of Graz, Innsbruck and Vienna Affiliated Tertiary Care Centre Klinikum KABEG","place":["Klagenfurt, Austria"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1020","DOI":"10.1093\/eurheartj\/ehad019","article-title":"Postoperative atrial fibrillation: from mechanisms to treatment","volume":"44","author":"Gaudino","year":"2023","journal-title":"Eur Heart J"},{"key":"B2","doi-asserted-by":"publisher","first-page":"329","DOI":"10.31083\/j.rcm2202040","article-title":"Determinants of atrial fibrillation after cardiac surgery","volume":"22","author":"Qureshi","year":"2021","journal-title":"Rev Cardiovasc Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1156626","DOI":"10.3389\/fcvm.2023.1156626","article-title":"Post-operative atrial fibrillation after cardiac surgery: challenges throughout the patient journey","volume":"10","author":"McIntyre","year":"2023","journal-title":"Front Cardiovasc Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"103131","DOI":"10.1016\/j.eclinm.2025.103131","article-title":"Performance of an AI prediction tool for new-onset atrial fibrillation after coronary artery bypass grafting","volume":"81","author":"Ma","year":"2025","journal-title":"eClinicalMedicine"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e2121867","DOI":"10.1001\/jamanetworkopen.2021.21867","article-title":"Effect of continuous electrocardiogram monitoring on detection of undiagnosed atrial fibrillation after hospitalization for cardiac surgery: a randomized clinical trial","volume":"4","author":"Ha","year":"2021","journal-title":"JAMA Netw Open"},{"key":"B6","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1016\/j.jtcvs.2023.03.026","article-title":"Anticoagulation for atrial fibrillation after cardiac surgery: do guidelines reflect the evidence?","volume":"167","author":"Chatterjee","year":"2024","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B7","doi-asserted-by":"publisher","first-page":"ivad153","DOI":"10.1093\/icvts\/ivad153","article-title":"Cardiopulmonary bypass management and risk of new-onset atrial fibrillation after cardiac surgery","volume":"37","author":"Taha","year":"2023","journal-title":"Interdiscip Cardiovasc Thorac Surg"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2018","DOI":"10.1016\/j.athoracsur.2016.05.016","article-title":"Duration of postoperative atrial fibrillation after cardiac surgery is associated with worsened long-term survival","volume":"102","author":"Sigurdsson","year":"2016","journal-title":"Ann Thorac Surg"},{"key":"B9","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.xjon.2021.01.014","article-title":"Novel insights in pathophysiology of postoperative atrial fibrillation","volume":"6","author":"Kharbanda","year":"2021","journal-title":"JTCVS Open"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1016\/j.jtcvs.2021.06.059","article-title":"Commentary: the importance of being predictable: postoperative atrial fibrillation","volume":"165","author":"Dimagli","year":"2023","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B11","doi-asserted-by":"publisher","first-page":"2209","DOI":"10.1016\/j.athoracsur.2022.03.062","article-title":"Clinical course of postoperative atrial fibrillation after cardiac surgery and long-term outcome","volume":"114","author":"Rezk","year":"2022","journal-title":"Ann Thorac Surg"},{"key":"B12","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":"B13","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.xjon.2024.10.003","article-title":"Interatrial block is an independent risk factor new-onset atrial fibrillation after cardiac surgery","volume":"22","author":"Leiler","year":"2024","journal-title":"JTCVS Open"},{"key":"B14","doi-asserted-by":"publisher","first-page":"ivae178","DOI":"10.1093\/icvts\/ivae178","article-title":"Preoperative interatrial block is associated with postoperative atrial fibrillation after cardiac surgery","volume":"40","author":"Leiler","year":"2025","journal-title":"Interdiscip Cardiovasc Thorac Surg"},{"key":"B15","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.ijcard.2019.04.070","article-title":"Cardiac autonomic regulation and PR interval determination for enhanced atrial fibrillation risk prediction after cardiac surgery","volume":"289","author":"Kali\u0161nik","year":"2019","journal-title":"Int J Cardiol"},{"key":"B16","doi-asserted-by":"publisher","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":"B17","doi-asserted-by":"publisher","first-page":"161","DOI":"10.11909\/j.issn.1671-5411.2017.03.007","article-title":"Diagnosis of interatrial block","volume":"14","author":"de Luna","year":"2017","journal-title":"J Geriatr Cardiol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1183\/13993003.01032-2015","article-title":"2015 ESC\/ERS guidelines for the diagnosis and treatment of pulmonary hypertension: the joint task force for the diagnosis and treatment of pulmonary hypertension of the European Society of Cardiology (ESC) and the European Respiratory Society (ERS)","volume":"46","author":"Gali\u00e8","year":"2015","journal-title":"Eur Respir J"},{"key":"B19","article-title":"Cardiogenic shock","volume-title":"StatPearls","author":"Kosaraju","year":"2025"},{"key":"B20","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1097\/ALN.0000000000004734","article-title":"Acute kidney injury after cardiac surgery: prediction, prevention and management","volume":"139","author":"Cheruku","year":"2023","journal-title":"Anesthesiology"},{"key":"B21","first-page":"ezac289","article-title":"Artificial intelligence-based early detection of acute kidney injury after cardiac surgery","volume-title":"Eur J Cardiothorac Surg","author":"Kalisnik","year":"2022"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-014-0241-z","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"13","author":"Collins","year":"2015","journal-title":"BMC Med"},{"key":"B23","year":""},{"key":"B24","year":""},{"key":"B25","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.amjcard.2023.09.079","article-title":"Machine learning for predicting postoperative atrial fibrillation after cardiac surgery: a scoping review of current literature","volume":"209","author":"El-Sherbini","year":"2023","journal-title":"Am J Cardiol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"179","DOI":"10.11909\/j.issn.1671-5411.2017.03.010","article-title":"Predisposing factors for atrial fibrillation in the elderly","volume":"14","author":"Wasmer","year":"2017","journal-title":"J Geriatr Cardiol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1055\/s-0038-1667065","article-title":"Clinical risk factors for post-operative atrial fibrillation among patients after cardiac surgery","volume":"67","author":"Yamashita","year":"2019","journal-title":"Thorac Cardiovasc Surg"},{"key":"B28","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.amjcard.2023.08.161","article-title":"Risk scores for prediction of postoperative atrial fibrillation after cardiac surgery: a systematic review and meta-analysis","volume":"209","author":"Pandey","year":"2023","journal-title":"Am J Cardiol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1007\/s10840-022-01430-7","article-title":"Role of CHA2DS2-VASc score in predicting atrial fibrillation recurrence in patients undergoing pulmonary vein isolation with cryoballoon ablation","volume":"66","author":"Rordorf","year":"2023","journal-title":"J Interv Card Electrophysiol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1016\/j.amjmed.2016.02.029","article-title":"Usefulness of CHADS2 and CHA2DS2-VASc scores in the prediction of new-onset atrial fibrillation: a population-based study","volume":"129","author":"Saliba","year":"2016","journal-title":"Am J Med"},{"key":"B31","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1177\/02676591211037025","article-title":"Predicting atrial fibrillation after cardiac surgery: a scoping review of associated factors and systematic review of existing prediction models","volume":"38","author":"Fleet","year":"2023","journal-title":"Perfusion"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1650700","DOI":"10.3389\/fmed.2025.1650700","article-title":"Machine learning prediction of post-CABG atrial fibrillation using clinical and pharmacogenomic biomarkers","volume":"12","author":"Hua","year":"2025","journal-title":"Front Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1002\/clc.23167","article-title":"Atrioventricular block can be used as a risk predictor of clinical atrial fibrillation","volume":"42","author":"Zhao","year":"2019","journal-title":"Clin Cardiol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1016\/S0140-6736(09)60443-8","article-title":"Development of a risk score for atrial fibrillation in the community; the Framingham Heart Study","volume":"373","author":"Schnabel","year":"2009","journal-title":"Lancet"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1225833","DOI":"10.3389\/fcvm.2023.1225833","article-title":"Incidence of atrioventricular block after isolated coronary artery bypass grafting: a systematic review and pooled-analysis","volume":"10","author":"Yaghoobian","year":"2023","journal-title":"Front Cardiovasc Med"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1093\/europace\/euw161","article-title":"EHRA\/HRS\/APHRS\/SOLAECE expert consensus on atrial cardiomyopathies: definition, characterization, and clinical implication","volume":"18","author":"Goette","year":"2016","journal-title":"Europace"},{"key":"B37","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1016\/j.xjon.2023.08.018","article-title":"New-onset postoperative atrial fibrillation after mitral valve surgery: determinants and the effect on survival","volume":"16","author":"Aggarwal","year":"2023","journal-title":"JTCVS Open"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1016\/j.jtcvs.2023.08.057","article-title":"Postoperative atrial fibrillation in mitral valve surgery is not benign","volume":"168","author":"Fu","year":"2024","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B39","doi-asserted-by":"publisher","first-page":"518","DOI":"10.5603\/CJ.a2016.0066","article-title":"Atrial fibrillation following off-pump versus on-pump coronary artery bypass grafting: incidence and risk factors","volume":"23","author":"Lewicki","year":"2016","journal-title":"Cardiol J"},{"key":"B40","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.1016\/j.jtcvs.2018.10.091","article-title":"Postoperative atrial fibrillation is associated with higher scores on predictive indices","volume":"157","author":"Burgos","year":"2019","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1210","DOI":"10.1016\/j.athoracsur.2019.07.084","article-title":"CHA2DS2-VASc score for identifying patients at high risk of postoperative atrial fibrillation after cardiac surgery: a meta-analysis","volume":"109","author":"Chen","year":"2020","journal-title":"Ann Thorac Surg"},{"key":"B42","doi-asserted-by":"publisher","first-page":"e034154","DOI":"10.1161\/JAHA.123.034154","article-title":"Machine learning algorithm to predict atrial fibrillation using serial 12-lead ECGs based on left atrial remodeling","volume":"13","author":"Choi","year":"2024","journal-title":"J Am Heart Assoc"},{"key":"B43","doi-asserted-by":"publisher","first-page":"166","DOI":"10.11909\/j.issn.1671-5411.2017.03.004","article-title":"Anticoagulation in elderly patients at high risk of atrial fibrillation without documented arrhythmias","volume":"14","author":"Mart\u00ednez-Sell\u00e9s","year":"2017","journal-title":"J Geriatr Cardiol"},{"key":"B44","doi-asserted-by":"publisher","first-page":"2881","DOI":"10.1161\/CIRCULATIONAHA.104.475194","article-title":"Inflammation of atrium after cardiac surgery is associated with inhomogeneity of atrial conduction and atrial fibrillation","volume":"111","author":"Ishii","year":"2005","journal-title":"Circulation"},{"key":"B45","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1097\/HCO.0b013e32835b0956","article-title":"Statin therapy and atrial fibrillation: systematic review and updated meta-analysis of published randomized controlled trials","volume":"28","author":"Fauchier","year":"2013","journal-title":"Curr Opin Cardiol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"839441","DOI":"10.3389\/fcvm.2022.839441","article-title":"Amiodarone-Induced multi-systemic toxicity involving the liver, lungs, thyroid, and eyes: a case report","volume":"9","author":"You","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1032116","DOI":"10.3389\/fcvm.2022.1032116","article-title":"Colchicine for prevention of post-operative atrial fibrillation: meta-analysis of randomized controlled trials","volume":"9","author":"Ge","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1016\/S0140-6736(21)02490-9","article-title":"Posterior left pericardiotomy for the prevention of atrial fibrillation after cardiac surgery: an adaptive, single-centre, single-blind, randomised, controlled trial","volume":"398","author":"Gaudino","year":"2021","journal-title":"Lancet Lond Engl"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1573095","DOI":"10.3389\/fcvm.2025.1573095","article-title":"Advances in iron deficiency and iron-related arrhythmias and cardiovascular diseases","volume":"12","author":"Im","year":"2025","journal-title":"Front Cardiovasc Med"},{"key":"B50","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1016\/j.jtcvs.2015.10.015","article-title":"Active clearance of chest drainage catheters reduces retained blood","volume":"151","author":"Sirch","year":"2016","journal-title":"J Thorac Cardiovasc Surg"},{"key":"B51","doi-asserted-by":"publisher","first-page":"i9","DOI":"10.1093\/ejcts\/ezaf007","article-title":"The impact of a chest drainage system on retained blood-associated complications after cardiac surgery","volume":"67","author":"Kalisnik","year":"2025","journal-title":"Eur J Cardiothorac Surg"}],"container-title":["Frontiers in Cardiovascular Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1886483\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T04:46:48Z","timestamp":1785905208000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1886483\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":51,"alternative-id":["10.3389\/fcvm.2026.1886483"],"URL":"https:\/\/doi.org\/10.3389\/fcvm.2026.1886483","relation":{},"ISSN":["2297-055X"],"issn-type":[{"value":"2297-055X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"article-number":"1886483"}}