{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T10:05:11Z","timestamp":1772705111151,"version":"3.50.1"},"posted":{"date-parts":[[2026,3,2]]},"group-title":"Cardiovascular Medicine","reference-count":25,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,3,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Aims<\/jats:title>\n                  <jats:p>We aimed to develop and evaluate fully automated artificial intelligence (AI) system. for detection of mitral valve prolapse (MVP) and mitral regurgitation (MR) from echocardiographic studies.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods and Results<\/jats:title>\n                  <jats:p>We used a dataset of 24,869 echocardiographic studies from the University of California San Francisco (UCSF) to train a multi-view deep neural network (DNN) to detect MVP using apical 4-chamber, 2-chamber, and parasternal long-axis views. A separate dataset of 27,906 studies from UCSF was used to train a second multi-view DNN model to detect moderate-to-severe or severe MR using color Doppler in the same views. External validation was performed on echocardiographic MVP videos from Houston Methodist Hospital.<\/jats:p>\n                  <jats:p>The DNN model for MVP detection achieved an AUC of 0.917 (95% CI: 0.899-0.934), with stronger performance in those with mitral annular disjunction or bileaflet MVP. External validation for MVP detection in a geographically and demographically distinct population yielded an AUC of 0.835 (95% CI: 0.803-0.869). The DNN for detection of moderate-to-severe or severe MR in patients with concurrent MVP achieved an AUC of 0.877 (95% CI: (0.805-0.939).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>AI algorithms can perform automatic detection of MVP and clinically significant MR from echocardiogram studies with high performance. The MVP DNN performed particularly well for more severe MVP phenotypes such as mitral annular disjunction or bileaflet MVP. These algorithms could provide a novel approach for automated, accurate, and rapid diagnosis of MVP and its common clinical sequelae across institutions.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Graphical Abstract<\/jats:title>\n                  <jats:fig id=\"Ufig1\" position=\"float\" orientation=\"portrait\" fig-type=\"figure\">\n                    <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"26347229v1_ufig1\" position=\"float\" orientation=\"portrait\"\/>\n                  <\/jats:fig>\n                <\/jats:sec>","DOI":"10.64898\/2026.02.26.26347229","type":"posted-content","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T15:45:15Z","timestamp":1772466315000},"source":"Crossref","is-referenced-by-count":0,"title":["Automated Echocardiographic Detection of Mitral Valve Prolapse and Mitral Regurgitation with Video-based Artificial Intelligence Algorithms"],"prefix":"10.64898","author":[{"given":"Minhaj U.","family":"Ansari","sequence":"first","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua P.","family":"Barrios","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"},{"name":"Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lionel","family":"Tastet","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Jhawar","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Cristin","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amy","family":"Rich","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dwight","family":"Bibby","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qizhi","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farzin","family":"Arya","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valentina","family":"Crudo","sequence":"additional","affiliation":[{"name":"Houston Methodist DeBakey Heart & Vascular Center, \u00a9 Houston, TX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thuy","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Houston Methodist DeBakey Heart & Vascular Center, \u00a9 Houston, TX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dipan J.","family":"Shah","sequence":"additional","affiliation":[{"name":"Houston Methodist DeBakey Heart & Vascular Center, \u00a9 Houston, TX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesca N.","family":"Delling","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-3326","authenticated-orcid":false,"given":"Geoffrey H.","family":"Tison","sequence":"additional","affiliation":[{"name":"Department of Medicine, Division of Cardiology, University of California, San Francisco, San Francisco, CA"},{"name":"Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA"},{"name":"Co-Director, Center for Biosignal Research, University of California, San Francisco, San Francisco, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026030501100722000_2026.02.26.26347229v1.1","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.1016\/j.jacc.2022.09.044","article-title":"Research Opportunities in the Treatment of Mitral Valve Prolapse: JACC Expert Panel","volume":"80","year":"2022","journal-title":"Journal of the American College of Cardiology"},{"key":"2026030501100722000_2026.02.26.26347229v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2020.11.010"},{"key":"2026030501100722000_2026.02.26.26347229v1.3","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1038\/s41569-021-00570-z","article-title":"Global epidemiology of valvular heart disease","volume":"18","year":"2021","journal-title":"Nature Reviews Cardiology. Nature Research"},{"key":"2026030501100722000_2026.02.26.26347229v1.4","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2017-312932"},{"issue":"6","key":"2026030501100722000_2026.02.26.26347229v1.5","first-page":"e016319","article-title":"Primary Atriopathy in Mitral Valve Prolapse: Echocardiographic Evidence and Clinical Implications","volume":"17","year":"2024","journal-title":"Circ Cardiovasc Imaging"},{"key":"2026030501100722000_2026.02.26.26347229v1.6","doi-asserted-by":"crossref","unstructured":"Basso C , Iliceto S , Thiene G , Perazzolo Marra M . Mitral Valve Prolapse , Ventricular Arrhythmias , and Sudden Death . Vol. 140, Circulation. NLM (Medline); 2019. p. 952\u201364.","DOI":"10.1161\/CIRCULATIONAHA.118.034075"},{"key":"2026030501100722000_2026.02.26.26347229v1.7","doi-asserted-by":"publisher","DOI":"10.1093\/europace\/euac125"},{"key":"2026030501100722000_2026.02.26.26347229v1.8","doi-asserted-by":"crossref","unstructured":"Tastet L , Ansari MU , Barrios JP , Cristin L , Jhawar R , Rich A , et al. Phenotyping of Mitral Valve Prolapse Without Severe Mitral Regurgitation Using Electrocardiographic and Echocardiographic Data. JACC Clin Electrophysiol. 2025;","DOI":"10.1016\/j.jacep.2025.06.001"},{"key":"2026030501100722000_2026.02.26.26347229v1.9","doi-asserted-by":"crossref","unstructured":"Tison GH , Abreau S , Barrios J , Lim LJ , Yang M , Crudo V , et al. Identifying Mitral Valve Prolapse at Risk for Arrhythmias and Fibrosis From Electrocardiograms Using Deep Learning. JACC: Advances. 2023 Aug 1;2(6).","DOI":"10.1016\/j.jacadv.2023.100446"},{"key":"2026030501100722000_2026.02.26.26347229v1.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2017.01.007"},{"key":"2026030501100722000_2026.02.26.26347229v1.11","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.118.034338"},{"key":"2026030501100722000_2026.02.26.26347229v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0216-8"},{"key":"2026030501100722000_2026.02.26.26347229v1.13","doi-asserted-by":"crossref","unstructured":"Vrudhula A , Duffy G , Vukadinovic M , Liang D , Cheng S , Ouyang D . High-Throughput Deep Learning Detection of Mitral Regurgitation. Circulation. 2024 Sep 17;","DOI":"10.1101\/2024.02.08.24302547"},{"issue":"12","key":"2026030501100722000_2026.02.26.26347229v1.14","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1161\/CIRCULATIONAHA.124.068996","article-title":"Deep Learning for Echo Analysis, Tracking, and Evaluation of Mitral Regurgitation (DELINEATE-MR)","volume":"150","year":"2024","journal-title":"Circulation"},{"issue":"5","key":"2026030501100722000_2026.02.26.26347229v1.15","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1016\/j.ultrasmedbio.2023.12.023","article-title":"Mitral Valve Segmentation and Tracking from Transthoracic Echocardiography Using Deep Learning","volume":"50","year":"2024","journal-title":"Ultrasound Med Biol"},{"issue":"2","key":"2026030501100722000_2026.02.26.26347229v1.16","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1007\/s11548-021-02542-7","article-title":"Automatic morphological classification of mitral valve diseases in echocardiographic images based on explainable deep learning methods","volume":"17","year":"2022","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"2026030501100722000_2026.02.26.26347229v1.17","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.80.3.589"},{"key":"2026030501100722000_2026.02.26.26347229v1.18","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.75.4.756"},{"key":"2026030501100722000_2026.02.26.26347229v1.19","unstructured":"Paszke A , Gross S , Massa F , Lerer A , Bradbury J , Chanan G , et al. PyTorch: An imperative style, high-performance deep learning library. Adv Neural Inf Process Syst. 2019;32(NeurIPS)."},{"key":"2026030501100722000_2026.02.26.26347229v1.20","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C . X3D: Expanding Architectures for Efficient Video Recognition. 2020 Apr 9; Available from: http:\/\/arxiv.org\/abs\/2004.04730","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"2026030501100722000_2026.02.26.26347229v1.21","unstructured":"Smith LN . Cyclical Learning Rates for Training Neural Networks. 2015 Jun 3; Available from: http:\/\/arxiv.org\/abs\/1506.01186"},{"key":"2026030501100722000_2026.02.26.26347229v1.22","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1038\/nrcardio.2015.161","article-title":"Mitral valve disease-morphology and mechanisms","volume":"12","year":"2015","journal-title":"Nature Reviews Cardiology"},{"key":"2026030501100722000_2026.02.26.26347229v1.23","doi-asserted-by":"crossref","unstructured":"Rinaldi M , Kramer-Fox R , Favillij S , Roman MJ , Deverebx RB . Natural History of Mitral Valve Prolapse. Vol. 75, THE AMERICAN JOURNAL OF CARDIOLOGY@. 1995.","DOI":"10.1016\/S0002-9149(99)80718-8"},{"key":"2026030501100722000_2026.02.26.26347229v1.24","doi-asserted-by":"crossref","unstructured":"Macmahon SW , Devereux RB , Kramer-Fox R , Katherine M , Kligfield P , Pini R , et al. Proceedings of a National Heart, Lung, and Blood Institute Symposium CLINICAL AND EPIDEMIOOGICAL lSSUES MITRAL VALVE PROLAPSE Diagnosis and classification of severity of mitral valve prolapse: Methodoldgic, biologic, and prognostic considerations. 1986.","DOI":"10.1016\/0002-8703(87)90955-0"},{"key":"2026030501100722000_2026.02.26.26347229v1.25","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.115.020621"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.02.26.26347229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T09:11:46Z","timestamp":1772701906000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.02.26.26347229"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":25,"URL":"https:\/\/doi.org\/10.64898\/2026.02.26.26347229","relation":{},"subject":[],"published":{"date-parts":[[2026,3,2]]},"subtype":"preprint"}}