{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T13:07:26Z","timestamp":1769605646810,"version":"3.49.0"},"reference-count":25,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Cardio"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Atrial fibrillation (AF) is a prevalent arrhythmia associated with significant morbidity and mortality. Despite advancements in ablation techniques, predicting recurrence of AF remains a challenge, necessitating reliable models to identify patients at risk of relapse. Traditional scoring systems often lack applicability in diverse clinical settings and may not incorporate the latest evidence-based factors influencing AF outcomes. This study aims to develop an explainable artificial intelligence model using Bayesian networks to predict AF relapse postablation, leveraging on easily obtainable clinical variables.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to investigate the effectiveness of Bayesian networks as a predictive tool for AF relapse following a percutaneous pulmonary vein isolation (PVI) procedure. The objectives include evaluating the model\u2019s performance using various clinical predictors, assessing its adaptability to incorporate new risk factors, and determining its potential to enhance clinical decision-making in the management of AF.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study analyzed data from 480 patients with symptomatic drug-refractory AF who underwent percutaneous PVI. To predict AF relapse following the procedure, an explainable artificial intelligence model based on Bayesian networks was developed. The model used a variable number of clinical predictors, including age, sex, smoking status, preablation AF type, left atrial volume, epicardial fat, obstructive sleep apnea, and BMI. The predictive performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC-ROC) metrics across different configurations of predictors (5, 6, and 7 variables). Validation was conducted through four distinct sampling techniques to ensure robustness and reliability of the predictions.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The Bayesian network model demonstrated promising predictive performance for AF relapse. Using 5 predictors (age, sex, smoking, preablation AF type, and obstructive sleep apnea), the model achieved an AUC-ROC of 0.661 (95% CI 0.603\u20100.718). Incorporating additional predictors improved performance, with a 6-predictor model (adding BMI) achieving an AUC-ROC of 0.703 (95% CI 0.652\u20100.753) and a 7-predictor model (adding left atrial volume and epicardial fat) achieving an AUC-ROC of 0.752 (95% CI 0.701\u20100.800). These results indicate that the model can effectively estimate the risk of AF relapse using readily available clinical variables. Notably, the model maintained acceptable diagnostic accuracy even in scenarios where some predictive features were missing, highlighting its adaptability and potential use in real-world clinical settings.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The developed Bayesian network model provides a reliable and interpretable tool for predicting AF relapse in patients undergoing percutaneous PVI. By using easily accessible clinical variables, presenting acceptable diagnostic accuracy, and showing adaptability to incorporate new medical knowledge over time, the model demonstrates a flexibility and robustness that makes it suitable for real-world clinical scenarios.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/59380","type":"journal-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T05:20:51Z","timestamp":1739337651000},"page":"e59380-e59380","source":"Crossref","is-referenced-by-count":1,"title":["Predicting Atrial Fibrillation Relapse Using Bayesian Networks: Explainable AI Approach"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1248-4631","authenticated-orcid":false,"given":"Jo\u00e3o Miguel","family":"Alves","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1554-6116","authenticated-orcid":false,"given":"Daniel","family":"Matos","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2718-7093","authenticated-orcid":false,"given":"Tiago","family":"Martins","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2771-345X","authenticated-orcid":false,"given":"Diogo","family":"Cavaco","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8532-7090","authenticated-orcid":false,"given":"Pedro","family":"Carmo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1134-5808","authenticated-orcid":false,"given":"Pedro","family":"Galv\u00e3o","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4019-5618","authenticated-orcid":false,"given":"Francisco Moscoso","family":"Costa","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7487-7978","authenticated-orcid":false,"given":"Francisco","family":"Morgado","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1623-7382","authenticated-orcid":false,"given":"Ant\u00f3nio Miguel","family":"Ferreira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9968-477X","authenticated-orcid":false,"given":"Pedro","family":"Freitas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9356-3272","authenticated-orcid":false,"given":"Cl\u00e1udia Camila","family":"Dias","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7867-6682","authenticated-orcid":false,"given":"Pedro Pereira","family":"Rodrigues","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3729-3137","authenticated-orcid":false,"given":"Pedro","family":"Adrag\u00e3o","sequence":"additional","affiliation":[]}],"member":"1010","published-online":{"date-parts":[[2025,2,11]]},"reference":[{"issue":"21","key":"R1","doi-asserted-by":"publisher","first-page":"2709","DOI":"10.1093\/eurheartj\/ehs301","article-title":"The impact of height on the risk of atrial fibrillation: the Cardiovascular Health Study","volume":"33","author":"Rosenberg","journal-title":"Eur Heart J"},{"issue":"FI_3","key":"R2","doi-asserted-by":"publisher","first-page":"f428","DOI":"10.1093\/europace\/eux265","article-title":"Development and validation of a risk score for predicting atrial fibrillation recurrence after a first catheter ablation procedure - ATLAS score","volume":"20","author":"Mesquita","journal-title":"Europace"},{"issue":"9","key":"R3","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1093\/eurheartj\/ehac758","article-title":"Artificial intelligence to enhance clinical value across the spectrum of cardiovascular healthcare","volume":"44","author":"Gill","journal-title":"Eur Heart J"},{"issue":"11","key":"R4","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1161\/CIRCEP.120.007953","article-title":"Digital health and the care of the patient with arrhythmia","volume":"13","author":"Tarakji","journal-title":"Circ Arrhythm Electrophysiol"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1093\/europace\/euac145","article-title":"AFA-Recur: an ESC EORP AFA-LT registry machine-learning web calculator predicting atrial fibrillation recurrence after ablation","volume":"25","author":"Saglietto","journal-title":"EP Europace"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-42542-y","article-title":"Machine learning model for predicting late recurrence of atrial fibrillation after catheter ablation","volume":"13","author":"Budzianowski","journal-title":"Sci Rep"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2022.1042573","article-title":"Development and validation of a novel risk model for predicting atrial fibrillation recurrence risk among paroxysmal atrial fibrillation patients after the first catheter ablation","volume":"9","author":"Li","journal-title":"Front Cardiovasc Med"},{"issue":"Supplement_2","key":"R8","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehac544.2775","article-title":"Can artificial intelligence prediction of successful atrial fibrillation catheter ablation therapy be interpretable?","volume":"43","author":"Ogbomo-Harmitt","journal-title":"Eur Heart J"},{"issue":"6","key":"R9","doi-asserted-by":"publisher","first-page":"1225","DOI":"10.1093\/ejcts\/ezab022","article-title":"Can we predict the risk for atrial fibrillation recurrence after concomitant surgical atrial fibrillation ablation and should this influence our treatment strategy?","volume":"59","author":"Pecha","journal-title":"Eur J Cardiothorac Surg"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102079","article-title":"Bayesian networks in healthcare: what is preventing their adoption?","volume":"116","author":"Kyrimi","journal-title":"Artif Intell Med"},{"issue":"Supplement_2","key":"R11","doi-asserted-by":"publisher","DOI":"10.1093\/ehjci\/ehaa946.0587","article-title":"Epicardial fat volume outperforms classic clinical scores for predicting atrial fibrillation relapse after pulmonary vein isolation","volume":"41","author":"Nascimento Matos","journal-title":"Eur Heart J"},{"issue":"12","key":"R12","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1161\/CIRCEP.116.004378","article-title":"Associations of epicardial, abdominal, and overall adiposity with atrial fibrillation","volume":"9","author":"Wong","journal-title":"Circ Arrhythm Electrophysiol"},{"issue":"23","key":"R13","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.121.022560","article-title":"Causal effect of obstructive sleep apnea on atrial fibrillation: a Mendelian randomization study","volume":"10","author":"Chen","journal-title":"J Am Heart Assoc"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.ccep.2020.10.003","article-title":"Sleep apnea and atrial fibrillation","volume":"13","author":"Linz","journal-title":"Card Electrophysiol Clin"},{"issue":"2","key":"R15","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"Schwarz","journal-title":"Ann Statist"},{"key":"R16","unstructured":"Russell SJ Norvig P Davis E . Artificial Intelligence: A Modern Approach. 3rded. Prentice Hall; 2010."},{"key":"R17","unstructured":"R: a language and environment for statistical computing. R Foundation for Statistical Computing. 2022. URL: https:\/\/cran.r-project.org\/bin\/windows\/base\/old\/4.2.2\/ [Accessed 27-01-2025]"},{"issue":"3","key":"R18","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v035.i03","article-title":"Learning Bayesian networks with the bnlearn R package","volume":"35","author":"Scutari","journal-title":"J Stat Softw"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-12-77","article-title":"pROC: an open-source package for R and S+ to analyze and compare ROC curves","volume":"12","author":"Robin","journal-title":"BMC Bioinformatics"},{"issue":"5","key":"R20","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.tcm.2022.01.010","article-title":"Successfully implemented artificial intelligence and machine learning applications in cardiology: state-of-the-art review","volume":"33","author":"Van den Eynde","journal-title":"Trends Cardiovasc Med"},{"issue":"38","key":"R21","doi-asserted-by":"publisher","first-page":"3904","DOI":"10.1093\/eurheartj\/ehab544","article-title":"Artificial intelligence in the diagnosis and management of arrhythmias","volume":"42","author":"Nagarajan","journal-title":"Eur Heart J"},{"issue":"8","key":"R22","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.119.007952","article-title":"Artificial intelligence and machine learning in arrhythmias and cardiac electrophysiology","volume":"13","author":"Feeny","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1177\/20552076221074488","article-title":"Re-focusing explainability in medicine","volume":"8","author":"Arbelaez Ossa","journal-title":"Dig Health"},{"issue":"4","key":"R24","doi-asserted-by":"publisher","first-page":"89","DOI":"10.4103\/2231-0770.110739","article-title":"Correlation of epicardial fat and anthropometric measurements in Asian-Indians: a community based study","volume":"2","author":"Shetty","journal-title":"Avicenna J Med"},{"issue":"9","key":"R25","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1097\/JTO.0b013e3181ec173d","article-title":"Receiver operating characteristic curve in diagnostic test assessment","volume":"5","author":"Mandrekar","journal-title":"J Thorac Oncol"}],"container-title":["JMIR Cardio"],"original-title":[],"language":"en","deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T05:20:56Z","timestamp":1739337656000},"score":1,"resource":{"primary":{"URL":"https:\/\/cardio.jmir.org\/2025\/1\/e59380"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.2196\/59380","relation":{},"ISSN":["2561-1011"],"issn-type":[{"value":"2561-1011","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,11]]},"article-number":"v9i21e59380"}}