{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T15:44:13Z","timestamp":1792165453140,"version":"4.4.0"},"reference-count":43,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"7","content-domain":{"domain":["www.ahajournals.org"],"crossmark-restriction":true},"short-container-title":["Circ: Arrhythmia and Electrophysiology"],"published-print":{"date-parts":[[2020,7]]},"abstract":"<jats:sec>\n            <jats:title>Background:<\/jats:title>\n            <jats:p>Pulmonary vein isolation (PVI) is an effective treatment strategy for patients with atrial fibrillation (AF), but many experience AF recurrence and require repeat ablation procedures. The goal of this study was to develop and evaluate a methodology that combines machine learning (ML) and personalized computational modeling to predict, before PVI, which patients are most likely to experience AF recurrence after PVI.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods:<\/jats:title>\n            <jats:p>This single-center retrospective proof-of-concept study included 32 patients with documented paroxysmal AF who underwent PVI and had preprocedural late gadolinium enhanced magnetic resonance imaging. For each patient, a personalized computational model of the left atrium simulated AF induction via rapid pacing. Features were derived from pre-PVI late gadolinium enhanced magnetic resonance images and from results of simulations of AF induction. The most predictive features were used as input to a quadratic discriminant analysis ML classifier, which was trained, optimized, and evaluated with 10-fold nested cross-validation to predict the probability of AF recurrence post-PVI.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results:<\/jats:title>\n            <jats:p>In our cohort, the ML classifier predicted probability of AF recurrence with an average validation sensitivity and specificity of 82% and 89%, respectively, and a validation area under the curve of 0.82. Dissecting the relative contributions of simulations of AF induction and raw images to the predictive capability of the ML classifier, we found that when only features from simulations of AF induction were used to train the ML classifier, its performance remained similar (validation area under the curve, 0.81). However, when only features extracted from raw images were used for training, the validation area under the curve significantly decreased (0.47).<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusions:<\/jats:title>\n            <jats:p>ML and personalized computational modeling can be used together to accurately predict, using only pre-PVI late gadolinium enhanced magnetic resonance imaging scans as input, whether a patient is likely to experience AF recurrence following PVI, even when the patient cohort is small.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1161\/circep.119.008213","type":"journal-article","created":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T00:31:52Z","timestamp":1592181112000},"update-policy":"https:\/\/doi.org\/10.1161\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":103,"title":["Preprocedure Application of Machine Learning and Mechanistic Simulations Predicts Likelihood of Paroxysmal Atrial Fibrillation Recurrence Following Pulmonary Vein Isolation"],"prefix":"10.1161","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4510-2516","authenticated-orcid":true,"given":"Julie K.","family":"Shade","sequence":"first","affiliation":[{"name":"Alliance for Cardiovascular Diagnostic and Treatment Innovation (J.K.S., R.L.A., D.B., D.P., H.C., N.A.T.), Johns Hopkins University, Baltimore, MD."},{"name":"Department of Biomedical Engineering (J.K.S., D.B., N.A.T.), Johns Hopkins University, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5853-8258","authenticated-orcid":true,"given":"Rheeda L.","family":"Ali","sequence":"additional","affiliation":[{"name":"Alliance for Cardiovascular Diagnostic and Treatment Innovation (J.K.S., R.L.A., D.B., D.P., H.C., N.A.T.), Johns Hopkins University, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dante","family":"Basile","sequence":"additional","affiliation":[{"name":"Alliance for Cardiovascular Diagnostic and Treatment Innovation (J.K.S., R.L.A., D.B., D.P., H.C., N.A.T.), Johns Hopkins University, Baltimore, MD."},{"name":"Department of Biomedical Engineering (J.K.S., D.B., N.A.T.), Johns Hopkins University, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Popescu","sequence":"additional","affiliation":[{"name":"Alliance for Cardiovascular Diagnostic and Treatment Innovation (J.K.S., R.L.A., D.B., D.P., H.C., N.A.T.), Johns Hopkins University, Baltimore, MD."},{"name":"Department of Applied Math and Statistics (D.P.), Johns Hopkins University, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tauseef","family":"Akhtar","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Medicine (T.A., J.E.M., D.D.S., H.C.), Johns Hopkins University School of Medicine, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph E.","family":"Marine","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Medicine (T.A., J.E.M., D.D.S., H.C.), Johns Hopkins University School of Medicine, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David D.","family":"Spragg","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Medicine (T.A., J.E.M., D.D.S., H.C.), Johns Hopkins University School of Medicine, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9262-9433","authenticated-orcid":true,"given":"Hugh","family":"Calkins","sequence":"additional","affiliation":[{"name":"Alliance for Cardiovascular Diagnostic and Treatment Innovation (J.K.S., R.L.A., D.B., D.P., H.C., N.A.T.), Johns Hopkins University, Baltimore, MD."},{"name":"Division of Cardiology, Department of Medicine (T.A., J.E.M., D.D.S., H.C.), Johns Hopkins University School of Medicine, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8661-063X","authenticated-orcid":true,"given":"Natalia A.","family":"Trayanova","sequence":"additional","affiliation":[{"name":"Alliance for Cardiovascular Diagnostic and Treatment Innovation (J.K.S., R.L.A., D.B., D.P., H.C., N.A.T.), Johns Hopkins University, Baltimore, MD."},{"name":"Department of Biomedical Engineering (J.K.S., D.B., N.A.T.), Johns Hopkins University, Baltimore, MD."},{"name":"Department of Medicine (N.A.T.), Johns Hopkins University School of Medicine, Baltimore, MD."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.285.18.2370"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2017.05.012"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.2174\/1573403X13666170117125124"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2004.03.071"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1093\/cvr\/cvz083"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.08.1036"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2018.10.015"},{"key":"e_1_3_4_9_2","volume-title":"Presented in the 2018 Computing in Cardiology Conference (CinC)","author":"Bhalodia R","unstructured":"Bhalodia, R, Goparaju, A, Sodergren, T, Whitaker, R, Morris, A, Kholmovski, E, Marrouche, N, Cates, J, Elhabian, S. Deep learning for end-to-end atrial fibrillation recurrence estimation. Presented in the 2018 Computing in Cardiology Conference (CinC), Maastricht, the Netherlands, September 23\u201326, 2018."},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00380-018-1244-z"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.113.000689"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hlc.2017.05.119"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2018.01207"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.11909\/j.issn.1671-5411.2017.04.008"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2018.00414"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijcard.2019.01.096"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-019-0437-9"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1093\/cvr\/cvw073"},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2006.01.015"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2013.10.007"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jelectrocard.2008.12.003"},{"key":"e_1_3_4_22_2","first-page":"223","article-title":"Modeling atrial fiber orientation in patient-specific geometries: a semi-automatic rule-based approach.","volume":"6666","author":"Krueger MW","year":"2011","unstructured":"Krueger, MW, Schmidt, V, Tob\u00f3n, C, Weber, FM, Lorenz, C, Keller, DUJ, Barschdorf, H, Burdumy, M, Neher, P, Plank, G, et al. Modeling atrial fiber orientation in patient-specific geometries: a semi-automatic rule-based approach. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics). 2011;6666 LNCS:223\u2013232.","journal-title":"Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics)"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jelectrocard.2012.08.005"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2018.01151"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2016.04.009"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1152\/ajpheart.1998.275.1.H301"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.111.969022"},{"key":"e_1_3_4_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncpcardio1370"},{"key":"e_1_3_4_29_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.107.754564"},{"key":"e_1_3_4_30_2","doi-asserted-by":"publisher","DOI":"10.1152\/ajpheart.00781.2006"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2008.0112"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.pbiomolbio.2007.07.012"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1063\/1.5003340"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1046\/j.1540-8167.2002.00672.x"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacep.2016.05.004"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-013-9654-z"},{"key":"e_1_3_4_37_2","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation.","volume":"11","author":"Cawley GC","year":"2010","unstructured":"Cawley, GC, Talbot, NLC. On over-fitting in model selection and subsequent selection bias in performance evaluation. J Mach Learn Res. 2010;11:2079\u20132107.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.5351\/KJAS.2004.17.3.459"},{"key":"e_1_3_4_39_2","first-page":"1277","article-title":"Bayesian quadratic discriminant analysis.","volume":"8","author":"Srivastava S","year":"2007","unstructured":"Srivastava, S, Gupta, MR, Frigyik, BA. Bayesian quadratic discriminant analysis. J Mach Learn Res. 2007;8:1277\u20131305.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxj035"},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICECA.2018.8474912"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1186\/1532-429X-18-S1-Q28"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1093\/europace\/eux265"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.hrthm.2016.07.018"}],"container-title":["Circulation: Arrhythmia and Electrophysiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ahajournals.org\/doi\/full\/10.1161\/CIRCEP.119.008213","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T01:30:26Z","timestamp":1715563826000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ahajournals.org\/doi\/10.1161\/CIRCEP.119.008213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":43,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,7]]}},"alternative-id":["10.1161\/CIRCEP.119.008213"],"URL":"https:\/\/doi.org\/10.1161\/circep.119.008213","relation":{},"ISSN":["1941-3149","1941-3084"],"issn-type":[{"value":"1941-3149","type":"print"},{"value":"1941-3084","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7]]},"assertion":[{"value":"2019-12-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-05-05","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-06-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e008213"}}