{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T07:57:45Z","timestamp":1777190265450,"version":"3.51.4"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,3,17]],"date-time":"2023-03-17T00:00:00Z","timestamp":1679011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,3,17]],"date-time":"2023-03-17T00:00:00Z","timestamp":1679011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>To drive health innovation that meets the needs of all and democratize healthcare, there is a need to assess the generalization performance of deep learning (DL) algorithms across various distribution shifts to ensure that these algorithms are robust. This retrospective study is, to the best of our knowledge, an original attempt to develop and assess the generalization performance of a DL model for AF events detection from long term beat-to-beat intervals across geography, ages and sexes. The new recurrent DL model, denoted ArNet2, is developed on a large retrospective dataset of 2,147 patients totaling 51,386\u2009h obtained from continuous electrocardiogram (ECG). The model\u2019s generalization is evaluated on manually annotated test sets from four centers (USA, Israel, Japan and China) totaling 402 patients. The model is further validated on a retrospective dataset of 1,825 consecutives Holter recordings from Israel. The model outperforms benchmark state-of-the-art models and generalized well across geography, ages and sexes. For the task of event detection ArNet2 performance was higher for female than male, higher for young adults (less than 61 years old) than other age groups and across geography. Finally, ArNet2 shows better performance for the test sets from the USA and China. The main finding explaining these variations is an impairment in performance in groups with a higher prevalence of atrial flutter (AFL). Our findings on the relative performance of ArNet2 across groups may have clinical implications on the choice of the preferred AF examination method to use relative to the group of interest.<\/jats:p>","DOI":"10.1038\/s41746-023-00791-1","type":"journal-article","created":{"date-parts":[[2023,3,26]],"date-time":"2023-03-26T19:57:11Z","timestamp":1679860631000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Generalizable and robust deep learning algorithm for atrial fibrillation diagnosis across geography, ages and sexes"],"prefix":"10.1038","volume":"6","author":[{"given":"Shany","family":"Biton","sequence":"first","affiliation":[]},{"given":"Mohsin","family":"Aldhafeeri","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1004-0826","authenticated-orcid":false,"given":"Erez","family":"Marcusohn","sequence":"additional","affiliation":[]},{"given":"Kenta","family":"Tsutsui","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2903-551X","authenticated-orcid":false,"given":"Tom","family":"Szwagier","sequence":"additional","affiliation":[]},{"given":"Adi","family":"Elias","sequence":"additional","affiliation":[]},{"given":"Julien","family":"Oster","sequence":"additional","affiliation":[]},{"given":"Jean Marc","family":"Sellal","sequence":"additional","affiliation":[]},{"given":"Mahmoud","family":"Suleiman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-7034","authenticated-orcid":false,"given":"Joachim A.","family":"Behar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"791_CR1","doi-asserted-by":"publisher","first-page":"3103","DOI":"10.1161\/STROKEAHA.113.002329","volume":"44","author":"S Bj\u00f6rck","year":"2013","unstructured":"Bj\u00f6rck, S., Palaszewski, B., Friberg, L. & Bergfeldt, L. Atrial fibrillation, stroke risk, and warfarin therapy revisited: A population-based study. Stroke 44, 3103\u20133108 (2013).","journal-title":"Stroke"},{"key":"791_CR2","first-page":"1","volume":"4","author":"M Haim","year":"2015","unstructured":"Haim, M. et al. Prospective national study of the prevalence, incidence, management and outcome of a large contemporary cohort of patients with incident non-valvular atrial fibrillation. J. Am. Hear. Assoc. 4, 1\u201312 (2015).","journal-title":"J. Am. Hear. Assoc."},{"key":"791_CR3","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1161\/01.STR.22.8.983","volume":"22","author":"PA Wolf","year":"1991","unstructured":"Wolf, P. A., Abbott, R. D. & Kannel, W. B. Atrial fibrillation as an independent risk factor for stroke: The framingham study. Stroke 22, 983\u2013988 (1991).","journal-title":"Stroke"},{"key":"791_CR4","first-page":"906","volume":"102","author":"AY-J Shen","year":"2010","unstructured":"Shen, A. Y.-J. et al. Racial\/ethnic differences in the prevalence of atrial fibrillation among older adults\u2014a cross-sectional study. J. Natl. Med. Assoc. 102, 906\u2013914 (2010).","journal-title":"J. Natl. Med. Assoc."},{"key":"791_CR5","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1161\/CIRCULATIONAHA.113.005119","volume":"129","author":"SS Chugh","year":"2014","unstructured":"Chugh, S. S. et al. Worldwide epidemiology of atrial fibrillation: a Global Burden of Disease 2010 Study. Circulation 129, 837\u2013847 (2014).","journal-title":"Circulation"},{"key":"791_CR6","doi-asserted-by":"publisher","first-page":"24","DOI":"10.15420\/usc.2017:39:1","volume":"12","author":"NV Pothineni","year":"2018","unstructured":"Pothineni, N. V. & Vallurupalli, S. Gender and atrial fibrillation: differences and disparities. US Cardiol. Rev. 12, 24\u201333 (2018).","journal-title":"US Cardiol. Rev."},{"key":"791_CR7","doi-asserted-by":"publisher","first-page":"1873","DOI":"10.1088\/0967-3334\/36\/9\/1873","volume":"36","author":"M Carrara","year":"2015","unstructured":"Carrara, M. et al. Heart rate dynamics distinguish among atrial fibrillation, normal sinus rhythm and sinus rhythm with frequent ectopy. Physiol. Meas. 36, 1873\u20131888 (2015).","journal-title":"Physiol. Meas."},{"key":"791_CR8","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1088\/0967-3334\/35\/10\/1929","volume":"35","author":"TJ Moss","year":"2014","unstructured":"Moss, T. J., Lake, D. E. & Moorman, J. R. Local dynamics of heart rate: detection and prognostic implications. Physiol. Meas. 35, 1929\u20131942 (2014).","journal-title":"Physiol. Meas."},{"key":"791_CR9","doi-asserted-by":"publisher","first-page":"2447","DOI":"10.1109\/TBME.2020.3042646","volume":"68","author":"A Chocron","year":"2021","unstructured":"Chocron, A. et al. Remote Atrial Fibrillation Burden Estimation Using Deep Recurrent Neural Network. IEEE Trans. Biomed. Eng. 68, 2447\u20132455 (2021).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"791_CR10","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.ins.2021.06.009","volume":"574","author":"J Wang","year":"2021","unstructured":"Wang, J. An intelligent computer-aided approach for atrial fibrillation and atrial flutter signals classification using modified bidirectional LSTM network. Inf. Sci. (Ny.). 574, 320\u2013332 (2021).","journal-title":"Inf. Sci. (Ny.)."},{"key":"791_CR11","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.3389\/fphys.2018.01390","volume":"9","author":"JA Behar","year":"2018","unstructured":"Behar, J. A. et al. PhysioZoo: A Novel Open Access Platform for Heart Rate Variability Analysis of Mammalian Electrocardiographic Data. Front Physiol. 9, 1390 (2018).","journal-title":"Front Physiol."},{"key":"791_CR12","doi-asserted-by":"crossref","unstructured":"Gendelman, S. et al. PhysioZoo ECG: Digital electrocardiography biomarkers to assess cardiac conduction. in 2021 Computing in Cardiology (CinC) 48 1\u20134 (2021).","DOI":"10.23919\/CinC53138.2021.9662857"},{"key":"791_CR13","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.compbiomed.2015.03.005","volume":"60","author":"S Asgari","year":"2015","unstructured":"Asgari, S., Mehrnia, A. & Moussavi, M. Automatic detection of atrial fibrillation using stationary wavelet transform and support vector machine. Comput. Biol. Med. 60, 132\u2013142 (2015).","journal-title":"Comput. Biol. Med."},{"key":"791_CR14","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.compbiomed.2015.01.019","volume":"65","author":"A Petrenas","year":"2015","unstructured":"Petrenas, A., Marozas, V. & S\u00f6rnmo, L. Low-complexity detection of atrial fibrillation in continuous long-term monitoring. Comput. Biol. Med. 65, 184\u2013191 (2015).","journal-title":"Comput. Biol. Med."},{"key":"791_CR15","doi-asserted-by":"publisher","first-page":"2242","DOI":"10.1016\/S0735-1097(00)00982-7","volume":"36","author":"J Granada","year":"2000","unstructured":"Granada, J. et al. Incidence and predictors of atrial flutter in the general population. J. Am. Coll. Cardiol. 36, 2242\u20132246 (2000).","journal-title":"J. Am. Coll. Cardiol."},{"key":"791_CR16","doi-asserted-by":"publisher","first-page":"H319","DOI":"10.1152\/ajpheart.00561.2010","volume":"300","author":"DE Lake","year":"2011","unstructured":"Lake, D. E. & Moorman, J. R. Accurate estimation of entropy in very short physiological time series: the problem of atrial fibrillation detection in implanted ventricular devices. Am. J. Physiol. Circ. Physiol. 300, H319\u2013H325 (2011).","journal-title":"Am. J. Physiol. Circ. Physiol."},{"key":"791_CR17","doi-asserted-by":"publisher","first-page":"1219","DOI":"10.1109\/TBME.2007.903707","volume":"55","author":"S Sarkar","year":"2008","unstructured":"Sarkar, S., Ritscher, D. & Mehra, R. A detector for a chronic implantable atrial tachyarrhythmia monitor. IEEE Trans. Biomed. Eng. 55, 1219\u20131224 (2008).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"791_CR18","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.1161\/CIRCULATIONAHA.113.001855","volume":"127","author":"S Mohanty","year":"2013","unstructured":"Mohanty, S. et al. Results from a single-blind, randomized study comparing the impact of different ablation approaches on long-term procedure outcome in coexistent atrial fibrillation and flutter (APPROVAL). Circulation 127, 1853\u20131860 (2013).","journal-title":"Circulation"},{"key":"791_CR19","first-page":"1776","volume":"19","author":"U Celikyurt","year":"2017","unstructured":"Celikyurt, U. et al. Incidence of new-onset atrial fibrillation after cavotricuspid isthmus ablation for atrial flutter. Ep Eur. 19, 1776\u20131780 (2017).","journal-title":"Ep Eur."},{"key":"791_CR20","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","volume":"101","author":"AL Goldberger","year":"2000","unstructured":"Goldberger, A. L. et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101, e215\u2013e220 (2000).","journal-title":"Circulation"},{"key":"791_CR21","unstructured":"Wang, X. et al. Paroxysmal atrial fibrillation events detection from dynamic ECG recordings: The 4th China physiological signal challenge 2021. In Proc. PhysioNet 1\u201383 (2021)."},{"key":"791_CR22","first-page":"2893","volume":"37","author":"P Kirchhof","year":"2016","unstructured":"Kirchhof, P. et al. 2016 ESC Guidelines for the management of atrial fibrillation developed in collaboration with EACTS. Kardiol. Pol. 37, 2893\u20132962 (2016).","journal-title":"Kardiol. Pol."},{"key":"791_CR23","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1056\/NEJMcp1111259","volume":"367","author":"MS Link","year":"2012","unstructured":"Link, M. S. Evaluation and initial treatment of supraventricular tachycardia. N. Engl. J. Med. 367, 1438\u20131448 (2012).","journal-title":"N. Engl. J. Med."},{"key":"791_CR24","first-page":"38","volume":"5","author":"MS Link","year":"2007","unstructured":"Link, M. S. Introduction to the arrhythmias: a primer. EP Lab Dig. 5, 38\u201339 (2007).","journal-title":"EP Lab Dig."},{"key":"791_CR25","doi-asserted-by":"publisher","first-page":"1306","DOI":"10.1161\/CIRCULATIONAHA.106.180200","volume":"115","author":"P Kligfield","year":"2007","unstructured":"Kligfield, P. et al. Recommendations for the standardization and interpretation of the electrocardiogram: part I: The electrocardiogram and its technology: a scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Cli. Circulation 115, 1306\u20131324 (2007).","journal-title":"Circulation"},{"key":"791_CR26","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TBME.1985.325532","volume":"32","author":"J Pan","year":"1985","unstructured":"Pan, J. & Tompkins, W. J. A Real-Time QRS Detection Algorithm. IEEE Trans. Biomed. Eng. BME- 32, 230\u2013236 (1985).","journal-title":"IEEE Trans. Biomed. Eng. BME-"},{"key":"791_CR27","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1088\/0967-3334\/33\/9\/1419","volume":"33","author":"GD Clifford","year":"2012","unstructured":"Clifford, G. D., Behar, J., Li, Q. & Rezek, I. Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms. Physiol. Meas. 33, 1419 (2012).","journal-title":"Physiol. Meas."},{"key":"791_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"791_CR29","unstructured":"Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. In Proc. 3rd International Conference on Learning Representations (ICLR) (ICLR, 2015)."},{"key":"791_CR30","unstructured":"Head, T., MechCoder, G. L., Shcherbatyi, I. & others. scikit-optimize\/scikit-optimize: v0. 5.2. Zenodo (2018)."},{"key":"791_CR31","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1001\/jamacardio.2018.1176","volume":"3","author":"AS Go","year":"2018","unstructured":"Go, A. S. et al. Association of burden of atrial fibrillation with risk of ischemic stroke in adults with paroxysmal atrial fibrillation: the KP-RHYTHM study. JAMA Cardiol. 3, 601\u2013608 (2018).","journal-title":"JAMA Cardiol."},{"key":"791_CR32","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1111\/ijcp.12326","volume":"68","author":"G Boriani","year":"2014","unstructured":"Boriani, G. et al. AF burden is important \u2013 fact or fiction? Int. J. Clin. Pract. 68, 444\u2013452 (2014).","journal-title":"Int. J. Clin. Pract."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00791-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00791-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00791-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,26]],"date-time":"2023-03-26T19:59:18Z","timestamp":1679860758000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00791-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,17]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["791"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00791-1","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,17]]},"assertion":[{"value":"5 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"44"}}