{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T01:49:13Z","timestamp":1782092953693,"version":"3.54.5"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":53,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Cardiovasc Disord"],"DOI":"10.1186\/s12872-026-05936-0","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:36:51Z","timestamp":1777531011000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Empowering atrial fibrillation detection with TabPFN and SHAP interpretation based on ECG-derived features: a dual-center temporal validation study"],"prefix":"10.1186","volume":"26","author":[{"given":"Mingming","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tenglong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojue","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoming","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yafeng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"issue":"1","key":"5936_CR1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1161\/CIRCRESAHA.120.316340","volume":"127","author":"J Kornej","year":"2020","unstructured":"Kornej J, B\u00f6rschel CS, Benjamin EJ, Schnabel RB. Epidemiology of atrial fibrillation in the 21st century: novel methods and new insights. Circul Res. 2020;127(1):4\u201320.","journal-title":"Circul Res"},{"key":"5936_CR2","doi-asserted-by":"crossref","unstructured":"Linz D, Gawalko M, Betz K, Hendriks JM, Lip GY, Vinter N, Johnsen S. Atrial fibrillation: epidemiology, screening and digital health. The Lancet Regional Health\u2013Europe. 2024;(37).","DOI":"10.1016\/j.lanepe.2023.100786"},{"issue":"4","key":"5936_CR3","doi-asserted-by":"publisher","first-page":"1211","DOI":"10.1007\/s10741-021-10142-5","volume":"27","author":"K Xiang","year":"2022","unstructured":"Xiang K, Akram M, Elbossaty WF, Yang J, Fan C. Exosomes in atrial fibrillation: therapeutic potential and role as clinical biomarkers. Heart Fail Rev. 2022;27(4):1211\u201321.","journal-title":"Heart Fail Rev"},{"issue":"8","key":"5936_CR4","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1136\/heart.89.8.939","volume":"89","author":"V Markides","year":"2003","unstructured":"Markides V, Schilling RJ. Atrial fibrillation: classification, pathophysiology, mechanisms and drug treatment. Heart. 2003;89(8):939\u201343.","journal-title":"Heart"},{"issue":"2","key":"5936_CR5","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1056\/NEJMoa1105575","volume":"366","author":"JS Healey","year":"2012","unstructured":"Healey JS, Connolly SJ, Gold MR, Israel CW, Van Gelder IC, Capucci A, Hohnloser SH. Subclinical atrial fibrillation and the risk of stroke. N Engl J Med. 2012;366(2):120\u20139.","journal-title":"N Engl J Med"},{"issue":"26","key":"5936_CR6","doi-asserted-by":"publisher","first-page":"2478","DOI":"10.1056\/NEJMoa1313600","volume":"370","author":"T Sanna","year":"2014","unstructured":"Sanna T, Diener HC, Passman RS, Di Lazzaro V, Bernstein RA, Morillo CA, Brachmann J. Cryptogenic stroke and underlying atrial fibrillation. N Engl J Med. 2014;370(26):2478\u201386.","journal-title":"N Engl J Med"},{"issue":"11","key":"5936_CR7","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1046\/j.1460-9592.2002.01587.x","volume":"25","author":"F Roche","year":"2002","unstructured":"Roche F, Costa GASPOZJMD, Isaaz A, Duverney K, Pichot D, BARTH\u00c9L\u00c9MY V, J. C. Frequent and prolonged asymptomatic episodes of paroxysmal atrial fibrillation revealed by automatic long-term event recorders in patients with a negative 24\u2010hour Holter. Pacing Clin Electrophysiol. 2002;25(11):1587\u201393.","journal-title":"Pacing Clin Electrophysiol"},{"issue":"10310","key":"5936_CR8","doi-asserted-by":"publisher","first-page":"1465","DOI":"10.1016\/S0140-6736(21)01785-2","volume":"398","author":"B Freedman","year":"2021","unstructured":"Freedman B, Lowres N. High-intensity atrial fibrillation screening to prevent stroke. Lancet. 2021;398(10310):1465\u20137.","journal-title":"Lancet"},{"issue":"13","key":"5936_CR9","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1161\/CIRCULATIONAHA.120.047829","volume":"143","author":"S Raghunath","year":"2021","unstructured":"Raghunath S, Pfeifer JM, Ulloa-Cerna AE, Nemani A, Carbonati T, Jing L, Haggerty CM. 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. Circulation. 2021;143(13):1287\u201398.","journal-title":"Circulation"},{"issue":"46","key":"5936_CR10","doi-asserted-by":"publisher","first-page":"4920","DOI":"10.1093\/eurheartj\/ehae595","volume":"45","author":"G Jabbour","year":"2024","unstructured":"Jabbour G, Nolin-Lapalme A, Tastet O, Corbin D, Jord\u00e0 P, Sowa A, Tadros R. Prediction of incident atrial fibrillation using deep learning, clinical models, and polygenic scores. Eur Heart J. 2024;45(46):4920\u201334.","journal-title":"Eur Heart J"},{"issue":"Suppl1","key":"5936_CR11","first-page":"A12922","volume":"144","author":"S Khurshid","year":"2021","unstructured":"Khurshid S, Friedman S, Reeder C, Di Achille P, Diamant N, Singh P, Lubitz SA. Electrocardiogram-based deep learning and clinical risk factors to predict incident atrial fibrillation. Circulation. 2021;144(Suppl1):A12922\u201312922.","journal-title":"Circulation"},{"issue":"1","key":"5936_CR12","doi-asserted-by":"publisher","first-page":"77","DOI":"10.4103\/njc.njc_8_18","volume":"16","author":"CA Alikor","year":"2019","unstructured":"Alikor CA, Nwafor CE. Availability and utilization of electrocardiogram as cardiac diagnostic tool in private hospitals in Port Harcourt. Nigerian J Cardiol. 2019;16(1):77\u201380.","journal-title":"Nigerian J Cardiol"},{"key":"5936_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12875-020-01325-4","volume":"21","author":"I Mappangara","year":"2020","unstructured":"Mappangara I, Qanitha A, Uiterwaal CS, Henriques JP, de Mol BA. Tele-ECG consulting and outcomes on primary care patients in a low-to-middle income population: the first experience from Makassar telemedicine program, Indonesia. BMC Fam Pract. 2020;21:1\u201311.","journal-title":"BMC Fam Pract"},{"key":"5936_CR14","doi-asserted-by":"crossref","unstructured":"Canakci B, Liu J, Wu X, Cheriere N, Costa P, Legtchenko S, Rowstron A. Good things come in small packages: Should we adopt Lite-GPUs in AI infrastructure?. arXiv e-prints, arXiv-2501. 2025.","DOI":"10.1145\/3713082.3730390"},{"key":"5936_CR15","doi-asserted-by":"crossref","unstructured":"Harmon DM, Sehrawat O, Maanja M, Wight J, Noseworthy PA. Artificial intelligence for the detection and treatment of atrial fibrillation. Arrhythmia & Electrophysiology Review. 2023;12:e12.","DOI":"10.15420\/aer.2022.31"},{"key":"5936_CR16","doi-asserted-by":"crossref","unstructured":"Casassus B. Doctors express enthusiasm for AI but have a \u201ctroubling\u201d reluctance to use it, says report. 2024.","DOI":"10.1136\/bmj.q2586"},{"key":"5936_CR17","unstructured":"Olaoye G, Luz A. Hybrid Models for Medical Data Analysis. Available at SSRN: https:\/\/ssrn.com\/abstract=4742530."},{"issue":"6","key":"5936_CR18","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1038\/s42256-023-00657-x","volume":"5","author":"H Chen","year":"2023","unstructured":"Chen H, Covert IC, Lundberg SM, Lee SI. Algorithms to estimate Shapley value feature attributions. Nat Mach Intell. 2023;5(6):590\u2013601.","journal-title":"Nat Mach Intell"},{"key":"5936_CR19","doi-asserted-by":"crossref","unstructured":"Rozemberczki B, Watson L, Bayer P, Yang HT, Kiss O, Nilsson S, Sarkar R. The shapley value in machine learning. In The 31st International Joint Conference on Artificial Intelligence and the 25th European Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization. 2022:5572\u20139.","DOI":"10.24963\/ijcai.2022\/778"},{"key":"5936_CR20","doi-asserted-by":"crossref","unstructured":"Ashcroft RE. The declaration of Helsinki. The Oxford textbook of clinical research ethics. 2008;21:141\u20138.","DOI":"10.1093\/oso\/9780195168655.003.0014"},{"key":"5936_CR21","doi-asserted-by":"crossref","unstructured":"Dan GA, Martinez-Rubio A. The 2024 European Society of Cardiology Atrial Fibrillation Guidelines: A Moving Goalpost. European Cardiology Review. 2025;20:e01.","DOI":"10.15420\/ecr.2024.55"},{"issue":"6","key":"5936_CR22","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1016\/j.hrthm.2024.11.012","volume":"22","author":"NM de Groot","year":"2025","unstructured":"de Groot NM, Kleber A, Narayan SM, Ciaccio EJ, Doessel O, Bernus O, Anter E. Atrial fibrillation nomenclature, definitions, and mechanisms: Position paper from the international Working Group of the Signal Summit. Heart rhythm. 2025;22(6):1480\u201391.","journal-title":"Heart rhythm"},{"issue":"12","key":"5936_CR23","doi-asserted-by":"publisher","first-page":"euae298","DOI":"10.1093\/europace\/euae298","volume":"26","author":"M Rienstra","year":"2024","unstructured":"Rienstra M, Tzeis S, Bunting KV, Caso V, Crijns HJ, De Potter TJ, Van Gelder IC. Spotlight on the 2024 ESC\/EACTS management of atrial fibrillation guidelines: 10 novel key aspects. Europace. 2024;26(12):euae298.","journal-title":"Europace"},{"key":"5936_CR24","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321\u201357.","journal-title":"J Artif Intell Res"},{"issue":"1","key":"5936_CR25","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1186\/1471-2105-14-106","volume":"14","author":"R Blagus","year":"2013","unstructured":"Blagus R, Lusa L. SMOTE for high-dimensional class-imbalanced data. BMC Bioinformatics. 2013;14(1):106.","journal-title":"BMC Bioinformatics"},{"issue":"5","key":"5936_CR26","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/s11135-006-9018-6","volume":"41","author":"RM O\u2019brien","year":"2007","unstructured":"O\u2019brien RM. A caution regarding rules of thumb for variance inflation factors. Qual Quant. 2007;41(5):673\u201390.","journal-title":"Qual Quant"},{"issue":"3","key":"5936_CR27","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1081\/QEN-120001878","volume":"14","author":"TA Craney","year":"2002","unstructured":"Craney TA, Surles JG. Model-dependent variance inflation factor cutoff values. Qual Eng. 2002;14(3):391\u2013403.","journal-title":"Qual Eng"},{"issue":"3","key":"5936_CR28","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1177\/0163278703255230","volume":"26","author":"FY Hsieh","year":"2003","unstructured":"Hsieh FY, Lavori PW, Cohen HJ, Feussner JR. An overview of variance inflation factors for sample-size calculation. Eval Health Prof. 2003;26(3):239\u201357.","journal-title":"Eval Health Prof"},{"issue":"1","key":"5936_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0169-7439(00)00122-2","volume":"56","author":"QS Xu","year":"2001","unstructured":"Xu QS, Liang YZ. Monte Carlo cross validation. Chemometr Intell Lab Syst. 2001;56(1):1\u201311.","journal-title":"Chemometr Intell Lab Syst"},{"issue":"1","key":"5936_CR30","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1186\/s12911-022-02016-z","volume":"22","author":"G Shan","year":"2022","unstructured":"Shan G. Monte Carlo cross-validation for a study with binary outcome and limited sample size. BMC Med Inf Decis Mak. 2022;22(1):270.","journal-title":"BMC Med Inf Decis Mak"},{"issue":"2","key":"5936_CR31","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1002\/cem.858","volume":"18","author":"QS Xu","year":"2004","unstructured":"Xu QS, Liang YZ, Du YP. Monte Carlo cross-validation for selecting a model and estimating the prediction error in multivariate calibration. J Chemometrics: J Chemometrics Soc. 2004;18(2):112\u201320.","journal-title":"J Chemometrics: J Chemometrics Soc"},{"issue":"1","key":"5936_CR32","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","volume":"3","author":"WJ Youden","year":"1950","unstructured":"Youden WJ. Index for rating diagnostic tests. Cancer. 1950;3(1):32\u20135.","journal-title":"Cancer"},{"issue":"4","key":"5936_CR33","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1002\/bimj.200410135","volume":"47","author":"R Fluss","year":"2005","unstructured":"Fluss R, Faraggi D, Reiser B. Estimation of the Youden Index and its associated cutoff point. Biometrical Journal: J Math Methods Biosci. 2005;47(4):458\u201372.","journal-title":"Biometrical Journal: J Math Methods Biosci"},{"issue":"3","key":"5936_CR34","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44(3):837\u201345.","journal-title":"Biometrics"},{"key":"5936_CR35","doi-asserted-by":"crossref","unstructured":"Demler OV, Pencina MJ, Sr DA, R. B. Misuse of DeLong test to compare AUCs for nested models. Stat Med. 2012;31(23):2577\u201387.","DOI":"10.1002\/sim.5328"},{"key":"5936_CR36","first-page":"507","volume":"498","author":"M Khorasani","year":"2022","unstructured":"Khorasani M, Abdou M, Fern\u00e1ndez JH. Web application development with streamlit. Softw Dev. 2022;498:507.","journal-title":"Softw Dev"},{"key":"5936_CR37","doi-asserted-by":"crossref","unstructured":"Shukla S, Maheshwari A, Johri P. (2021, December). Comparative analysis of ml algorithms & stream lit web application. In 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) (pp. 175\u2013180). IEEE.","DOI":"10.1109\/ICAC3N53548.2021.9725496"},{"issue":"2","key":"5936_CR38","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1177\/2396987319896674","volume":"5","author":"A Mentel","year":"2020","unstructured":"Mentel A, Quinn TJ, Cameron AC, Lees KR, Abdul-Rahim AH. The impact of atrial fibrillation type on the risks of thromboembolic recurrence, mortality and major haemorrhage in patients with previous stroke: A systematic review and meta-analysis of observational studies. Eur Stroke J. 2020;5(2):155\u201368.","journal-title":"Eur Stroke J"},{"issue":"1","key":"5936_CR39","doi-asserted-by":"publisher","first-page":"102181","DOI":"10.1016\/j.cpcardiol.2023.102181","volume":"49","author":"S Elsheikh","year":"2024","unstructured":"Elsheikh S, Hill A, Irving G, Lip GY, Abdul-Rahim AH. Atrial fibrillation and stroke: State-of-the-art and future directions. Curr Probl Cardiol. 2024;49(1):102181.","journal-title":"Curr Probl Cardiol"},{"issue":"21","key":"5936_CR40","doi-asserted-by":"publisher","first-page":"2154","DOI":"10.1016\/j.jacc.2024.08.017","volume":"84","author":"GD Barnes","year":"2024","unstructured":"Barnes GD, Lip GY. Applying Clinical Risk Scores in Real-World Practice: The CHA2DS2-VASc Score in Atrial Fibrillation. J Am Coll Cardiol. 2024;84(21):2154\u20136.","journal-title":"J Am Coll Cardiol"},{"key":"5936_CR41","doi-asserted-by":"crossref","unstructured":"Ibdah R, Obeidat O, Khader Y, Al-Nusair J, Abusurrah O, Obeidat A, Hammoudeh A. Validation of CHA2DS2 VASc score predictability of stroke and systemic embolization in a Middle Eastern Population with AF: the Jordan Atrial Fibrillation (JoFib) Study. Vascular health and risk management; 2023. pp. 255\u201364.","DOI":"10.2147\/VHRM.S404575"},{"issue":"3","key":"5936_CR42","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.hroo.2022.12.009","volume":"O2","author":"H Yarmohammadi","year":"2023","unstructured":"Yarmohammadi H, Wan EY, Biviano A, Garan H, Koehler JL, Stadler RW. Prolonged PR interval and incidence of atrial fibrillation, heart failure admissions, and mortality in patients with implanted cardiac devices: a real-world survey. Heart Rhythm. 2023;O2(3):171\u20139.","journal-title":"Heart Rhythm"},{"issue":"1","key":"5936_CR43","doi-asserted-by":"publisher","first-page":"57","DOI":"10.4330\/wjc.v8.i1.57","volume":"8","author":"F Monitillo","year":"2016","unstructured":"Monitillo F, Leone M, Rizzo C, Passantino A, Iacoviello M. Ventricular repolarization measures for arrhythmic risk stratification. World J Cardiol. 2016;8(1):57.","journal-title":"World J Cardiol"},{"key":"5936_CR44","unstructured":"Ramachandram D, Joshi H, Zhu J, Gandhi D, Hartman L, Raval A. (2025). Transparent AI: the case for interpretability and explainability. arXiv preprint arXiv:2507.23535."},{"key":"5936_CR45","doi-asserted-by":"crossref","unstructured":"Mohammed S, Malhotra N. Ethical and Regulatory Challenges in Machine Learning-Based Healthcare Systems: A Review of Implementation Barriers and Future Directions. BenchCouncil Transactions on Benchmarks, Standards and Evaluations; 2025. p. 100215.","DOI":"10.1016\/j.tbench.2025.100215"},{"key":"5936_CR46","unstructured":"Gao W, Hu Q, Ye Z, Sun P, Wang X, Luo Y, Wen Y. (2022). Deep learning workload scheduling in GPU datacenters: Taxonomy, challenges and vision. arXiv preprint arXiv:2205.11913."}],"container-title":["BMC Cardiovascular Disorders"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12872-026-05936-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12872-026-05936-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12872-026-05936-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T01:41:25Z","timestamp":1782092485000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12872-026-05936-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["5936"],"URL":"https:\/\/doi.org\/10.1186\/s12872-026-05936-0","relation":{},"ISSN":["1471-2261"],"issn-type":[{"value":"1471-2261","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]},"assertion":[{"value":"8 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study was conducted in accordance with the Declaration of Helsinki. The protocol was approved by the Institutional Review Board of The Fourth Affiliated Hospital of Soochow University and Suzhou Traditional Chinese and Western Medicine Hospital. As this study utilized de-identified retrospective ECG data and did not involve any intervention or risk to the participants, the requirement for informed consent was waived by the ethics committee. All patient identifiers were removed prior to analysis to ensure privacy and confidentiality.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"536"}}