{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T20:22:37Z","timestamp":1776198157804,"version":"3.50.1"},"reference-count":45,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100009619","name":"Japan Agency for Medical Research and Development","doi-asserted-by":"publisher","award":["JP17ek0210082"],"award-info":[{"award-number":["JP17ek0210082"]}],"id":[{"id":"10.13039\/100009619","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Noninvasive Electrocardiol"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Artificial intelligence (AI)\u2010enhanced electrocardiography (ECG) has been developed to detect paroxysmal atrial fibrillation (AF) from sinus rhythm ECGs (SR\u2010ECGs). For broader applicability, model development across institutions and ECG systems is essential.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We developed an AI\u2010enhanced ECG model using SR\u2010ECGs from Tokai University (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009172,613; Nihon Kohden [NK] system) and The Cardiovascular Institute (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200919,170; GE MUSE system). AF\u2010labeled SR\u2010ECGs were defined as recordings within 31\u2009days of an AF episode, while SR\u2010labeled SR\u2010ECGs were those with \u2265\u20091095\u2009days of AF\u2010free follow\u2010up. Three datasets were constructed: Dataset 1 (Tokai University, all departments, NK), Dataset 2 (Tokai University, Cardiology Department, NK), and Dataset 3 (The Cardiovascular Institute, Cardiology Department, MUSE). We developed five models: scratch models (S1\u2013S3) trained on Datasets 1\u20133, and fine\u2010tuned models (F1, F2) trained on Datasets 1 and 2 after pretraining on Dataset 3. Models were evaluated using A1\u2013A3 (same as Datasets 1\u20133) and B1\u2013B3, which differed in ECG resolution and compression (B1: original MUSE, B2: MUSE\u2010NK intermediate, B3: NK\u2010converted).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Model F2, fine\u2010tuned on homogeneous datasets from cardiology departments, showed consistently high performance (AUC: A1\u2009=\u20090.885, A2\u2009=\u20090.829, A3\u2009=\u20090.845). Model F1, fine\u2010tuned on heterogeneous datasets, demonstrated lower performance (AUC: A1\u2009=\u20090.837, A2\u2009=\u20090.726, A3\u2009=\u20090.660). Model performance was consistent across different ECG format variants (B1\u2013B3).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Fine\u2010tuning on homogeneous data improved performance and generalizability, whereas heterogeneous data led to reduced performance. ECG system format differences had minimal impact on model accuracy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/anec.70159","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T08:19:37Z","timestamp":1770625177000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Artificial Intelligence\u2010Enhanced Electrocardiography for Predicting Paroxysmal Atrial Fibrillation From Sinus Rhythm: Impact of Data Integration Across Institutions and Devices"],"prefix":"10.1111","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4769-5925","authenticated-orcid":false,"given":"Shinya","family":"Suzuki","sequence":"first","affiliation":[{"name":"Department of Cardiovascular Medicine The Cardiovascular Institute  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3128-6421","authenticated-orcid":false,"given":"Mari","family":"Amino","sequence":"additional","affiliation":[{"name":"Department of Cardiology Tokai University School of Medicine  Kanagawa Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobumoto","family":"Moriai","sequence":"additional","affiliation":[{"name":"Nihon Kohden Corporation  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshifumi","family":"Sumioka","sequence":"additional","affiliation":[{"name":"Nihon Kohden Corporation  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akira","family":"Hyodo","sequence":"additional","affiliation":[{"name":"Nihon Kohden Corporation  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiichi","family":"Satoh","sequence":"additional","affiliation":[{"name":"Nihon Kohden Corporation  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsuneo","family":"Takayanagi","sequence":"additional","affiliation":[{"name":"Nihon Kohden Corporation  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Umemoto","sequence":"additional","affiliation":[{"name":"Nihon Kohden Corporation  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yota","family":"Sekiguchi","sequence":"additional","affiliation":[{"name":"Nihon Kohden Corporation  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1184-4228","authenticated-orcid":false,"given":"Naomi","family":"Hirota","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine The Cardiovascular Institute  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7774-7477","authenticated-orcid":false,"given":"Atsuhiko","family":"Yagishita","sequence":"additional","affiliation":[{"name":"Department of Cardiology Tokai University School of Medicine  Kanagawa Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5686-4324","authenticated-orcid":false,"given":"Yuji","family":"Ikari","sequence":"additional","affiliation":[{"name":"Department of Cardiology Tokai University School of Medicine  Kanagawa Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taira","family":"Nakayama","sequence":"additional","affiliation":[{"name":"Department of Neurology Tokai University School of Medicine  Kanagawa Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoichi","family":"Ohnuki","sequence":"additional","affiliation":[{"name":"Department of Neurology Tokai University School of Medicine  Kanagawa Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eiichiro","family":"Nagata","sequence":"additional","affiliation":[{"name":"Department of Neurology Tokai University School of Medicine  Kanagawa Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Motogi","sequence":"additional","affiliation":[{"name":"Nihon Kohden Corporation  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2544-8464","authenticated-orcid":false,"given":"Takeshi","family":"Yamashita","sequence":"additional","affiliation":[{"name":"Department of Cardiovascular Medicine The Cardiovascular Institute  Tokyo Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichiro","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Department of Cardiology Tokai University School of Medicine  Kanagawa Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,2,9]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.120.008437"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcha.2024.101389"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2020.12.065"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0240-2"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(19)31721-0"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-92172-5"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102632"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2024.03.029"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.120.009355"},{"key":"e_1_2_12_11_1","first-page":"29","article-title":"Performance of Handheld Electrocardiogram Devices to Detect Atrial Fibrillation in a Cardiology and Geriatric Ward Setting","volume":"19","author":"Desteghe L.","year":"2017","journal-title":"Europace"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2021.0038"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.121.058696"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacep.2023.04.008"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2022.865852"},{"key":"e_1_2_12_16_1","unstructured":"He K. X.Zhang S.Ren andJ.Sun.2015.\u201cDeep Residual Learning for Image Recognition.\u201darXiv pre\u2010print server[Internet].https:\/\/arxiv.org\/abs\/1512.03385."},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2020.11.012"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-021-02391-8"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00380-024-02367-9"},{"key":"e_1_2_12_20_1","doi-asserted-by":"crossref","unstructured":"Howard J. andS.Ruder.2018.\u201cUniversal Language Model Fine\u2010Tuning for Text Classification [Internet].\u201dhttps:\/\/doi.org\/10.18653\/v1\/P18\u20101031.","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2016160816"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.117.006624"},{"key":"e_1_2_12_23_1","unstructured":"Iwana B. K. andS.Uchida.2020. \u201cTime Series Data Augmentation for Neural Networks by Time Warping With a Discriminative Teacher [Internet].\u201d arXiv [Cs.LG].http:\/\/arxiv.org\/abs\/2004.08780."},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10103359"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehw210"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.12.030"},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cjca.2021.09.028"},{"key":"e_1_2_12_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cvdhj.2022.10.002"},{"key":"e_1_2_12_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-02179-1"},{"key":"e_1_2_12_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118948"},{"key":"e_1_2_12_33_1","doi-asserted-by":"crossref","unstructured":"Nagi J. F.Ducatelle A. G.Di Caro et\u00a0al.2011.\u201cMax\u2010Pooling Convolutional Neural Networks for Vision\u2010Based Hand Gesture Recognition.\u201dIEEE International Conference on Signal and Image Processing Applicationss; Kuala Lumpur; Nov 16\u201318 2011;342\u201347.","DOI":"10.1109\/ICSIPA.2011.6144164"},{"key":"e_1_2_12_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_12_35_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.120.047829"},{"key":"e_1_2_12_36_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.108.191096"},{"key":"e_1_2_12_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_12_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2021.08.026"},{"key":"e_1_2_12_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcha.2022.100954"},{"key":"e_1_2_12_40_1","doi-asserted-by":"publisher","DOI":"10.1253\/circrep.CR-23-0068"},{"key":"e_1_2_12_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jjcc.2011.06.006"},{"key":"e_1_2_12_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"e_1_2_12_43_1","doi-asserted-by":"publisher","DOI":"10.4065\/76.5.467"},{"key":"e_1_2_12_44_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0195088"},{"key":"e_1_2_12_45_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13082218"},{"key":"e_1_2_12_46_1","doi-asserted-by":"publisher","DOI":"10.1093\/ehjdh\/ztac065"}],"container-title":["Annals of Noninvasive Electrocardiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/anec.70159","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/anec.70159","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/anec.70159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:12:43Z","timestamp":1774451563000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/anec.70159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,9]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1111\/anec.70159"],"URL":"https:\/\/doi.org\/10.1111\/anec.70159","archive":["Portico"],"relation":{},"ISSN":["1082-720X","1542-474X"],"issn-type":[{"value":"1082-720X","type":"print"},{"value":"1542-474X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,9]]},"assertion":[{"value":"2025-06-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-28","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70159"}}