{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T11:43:50Z","timestamp":1793965430896,"version":"4.8.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000050","name":"U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["K23HL135274"],"award-info":[{"award-number":["K23HL135274"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["DP2HL174046"],"award-info":[{"award-number":["DP2HL174046"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","award":["R56HL161475"],"award-info":[{"award-number":["R56HL161475"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Cardiovasc Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Medical imaging often captures multiple two-dimensional views of three-dimensional anatomic structures, but most artificial intelligence (AI) models analyze two-dimensional data. Here we show that integrating multiple imaging views using a single AI model can improve diagnostic performance. We developed a deep neural network (DNN) architecture that combines information from multiple video views simultaneously. Using echocardiogram data from the University of California, San Francisco, and the Montreal Heart Institute, we applied our multiview DNN approach for three primary demonstration tasks: detecting any left or right ventricular abnormality, diastolic dysfunction, and substantial valvular regurgitation. Across various tasks, our multiview DNNs improved discrimination as measured by the area under the receiver operating characteristic curve by 0.06\u20130.09 compared to DNNs trained on any single view. This demonstrates that AI models that can combine information from multiple imaging views simultaneously can better capture complex anatomy and physiology for certain tasks, underscoring the value of a multiview paradigm for AI in medical imaging.<\/jats:p>","DOI":"10.1038\/s44161-026-00786-7","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:07:47Z","timestamp":1773770867000},"page":"234-245","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multiview deep learning improves detection of major cardiac conditions from echocardiography"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1618-6244","authenticated-orcid":false,"given":"Joshua P.","family":"Barrios","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minhaj U.","family":"Ansari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey E.","family":"Olgin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean","family":"Abreau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0466-1354","authenticated-orcid":false,"given":"Jacques","family":"Delfrate","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3019-4829","authenticated-orcid":false,"given":"Elodie L.","family":"Langlais","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8490-0270","authenticated-orcid":false,"given":"Robert","family":"Avram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-3326","authenticated-orcid":false,"given":"Geoffrey H.","family":"Tison","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"786_CR1","unstructured":"Bahdanau, D., Cho, K. H. & Bengio, Y. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, ICLR 2015\u2014Conference Track Proceedings 1\u201315 (ICLR, 2015)."},{"key":"786_CR2","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 770\u2013778 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"786_CR3","doi-asserted-by":"publisher","unstructured":"Karpathy, A. et al. Large-scale video classification with convolutional neural networks. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1725\u20131732 (IEEE, 2014); https:\/\/doi.org\/10.1109\/CVPR.2014.223","DOI":"10.1109\/CVPR.2014.223"},{"key":"786_CR4","doi-asserted-by":"publisher","unstructured":"Tran, D. et al. A closer look at spatiotemporal convolutions for action recognition. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition 6450\u20136459 (IEEE, 2018); https:\/\/doi.org\/10.1109\/CVPR.2018.00675","DOI":"10.1109\/CVPR.2018.00675"},{"key":"786_CR5","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M. & Yu, K. 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35, 221\u2013231 (2013).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"786_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J. & Zisserman, A. Quo vadis, action recognition? A new model and the kinetics dataset. In Proc. 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 4724\u20134733 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.502"},{"key":"786_CR7","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41586-020-2145-8","volume":"580","author":"D Ouyang","year":"2020","unstructured":"Ouyang, D. et al. Video-based AI for beat-to-beat assessment of cardiac function. Nature 580, 252\u2013256 (2020).","journal-title":"Nature"},{"key":"786_CR8","doi-asserted-by":"publisher","unstructured":"Hughes, J. W. et al. Deep learning evaluation of biomarkers from echocardiogram videos-NC-ND license (http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/) (2021); https:\/\/doi.org\/10.1016\/j.ebiom.2021.103613","DOI":"10.1016\/j.ebiom.2021.103613"},{"key":"786_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-22877-8","volume":"12","author":"S Goto","year":"2021","unstructured":"Goto, S. et al. Artificial intelligence-enabled fully automated detection of cardiac amyloidosis using electrocardiograms and echocardiograms. Nat. Commun. 12, 2726 (2021).","journal-title":"Nat. Commun."},{"key":"786_CR10","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1038\/s41588-022-01090-3","volume":"54","author":"JP Pirruccello","year":"2022","unstructured":"Pirruccello, J. P. et al. Genetic analysis of right heart structure and function in 40,000 people. Nat. Genet. 54, 792\u2013803 (2022).","journal-title":"Nat. Genet."},{"key":"786_CR11","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1038\/s41551-020-00667-9","volume":"5","author":"AE Ulloa Cerna","year":"2021","unstructured":"Ulloa Cerna, A. E. et al. Deep-learning-assisted analysis of echocardiographic videos improves predictions of all-cause mortality. Nat. Biomed. Eng. 5, 546\u2013554 (2021).","journal-title":"Nat. Biomed. Eng."},{"key":"786_CR12","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1001\/jamacardio.2021.6059","volume":"7","author":"G Duffy","year":"2022","unstructured":"Duffy, G. et al. High-throughput precision phenotyping of left ventricular hypertrophy with cardiovascular deep learning. JAMA Cardiol. 7, 386\u2013395 (2022).","journal-title":"JAMA Cardiol."},{"key":"786_CR13","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.jcmg.2019.02.024","volume":"13","author":"K Kusunose","year":"2020","unstructured":"Kusunose, K. et al. A deep learning approach for assessment of regional wall motion abnormality from echocardiographic images. JACC Cardiovasc. Imaging 13, 374\u2013381 (2020).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"786_CR14","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/j.jcmg.2023.09.011","volume":"17","author":"CJ Chao","year":"2023","unstructured":"Chao, C. J. et al. Echocardiography-based deep learning model to differentiate constrictive pericarditis and restrictive cardiomyopathy. JACC Cardiovasc. Imaging 17, 349\u2013360 (2023).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"786_CR15","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C. X3D: expanding architectures for efficient video recognition. Preprint at https:\/\/arxiv.org\/abs\/2004.04730 (2020).","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"786_CR16","doi-asserted-by":"publisher","first-page":"1623","DOI":"10.1161\/CIRCULATIONAHA.118.034338","volume":"138","author":"J Zhang","year":"2018","unstructured":"Zhang, J. et al. Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy. Circulation 138, 1623\u20131635 (2018).","journal-title":"Circulation"},{"key":"786_CR17","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1038\/s41591-021-01342-5","volume":"27","author":"R Arnaout","year":"2021","unstructured":"Arnaout, R. et al. An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart disease. Nat. Med. 27, 882\u2013891 (2021).","journal-title":"Nat. Med."},{"key":"786_CR18","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/s41746-018-0065-x","volume":"1","author":"X Gao","year":"2018","unstructured":"Gao, X. et al. Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease. NPJ Digit. Med. 1, 59 (2018).","journal-title":"NPJ Digit. Med."},{"key":"786_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.echo.2014.10.003","volume":"28","author":"RM Lang","year":"2015","unstructured":"Lang, R. M. et al. Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J. Am. Soc. Echocardiogr. 28, 1\u201339.e14 (2015).","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"786_CR20","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.echo.2008.11.023","volume":"22","author":"SF Nagueh","year":"2009","unstructured":"Nagueh, S. F. et al. Recommendations for the evaluation of left ventricular diastolic function by echocardiography. J. Am. Soc. Echocardiogr. 22, 107\u2013133 (2009).","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"786_CR21","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.echo.2016.01.011","volume":"29","author":"SF Nagueh","year":"2016","unstructured":"Nagueh, S. F. et al. Recommendations for the evaluation of left ventricular diastolic function by echocardiography: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J. Am. Soc. Echocardiogr. 29, 277\u2013314 (2016).","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"786_CR22","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.echo.2017.01.007","volume":"30","author":"WA Zoghbi","year":"2017","unstructured":"Zoghbi, W. A. et al. Recommendations for noninvasive evaluation of native valvular regurgitation: a report from the American Society of Echocardiography developed in collaboration with the Society for Cardiovascular Magnetic Resonance. J. Am. Soc. Echocardiogr. 30, 303\u2013371 (2017).","journal-title":"J. Am. Soc. Echocardiogr."},{"key":"786_CR23","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128, 336\u2013359 (2020).","journal-title":"Int. J. Comput. Vis."},{"key":"786_CR24","doi-asserted-by":"publisher","first-page":"2053","DOI":"10.1016\/j.jacc.2006.07.047","volume":"48","author":"RM Lang","year":"2006","unstructured":"Lang, R. M., Mor-Avi, V., Sugeng, L., Nieman, P. S. & Sahn, D. J. Three-dimensional echocardiography. The benefits of the additional dimension. J. Am. Coll. Cardiol. 48, 2053\u20132069 (2006).","journal-title":"J. Am. Coll. Cardiol."},{"key":"786_CR25","doi-asserted-by":"publisher","first-page":"105901","DOI":"10.1016\/j.bspc.2023.105901","volume":"91","author":"R Mittal","year":"2024","unstructured":"Mittal, R. et al. 3D reconstruction of brain tumors from 2D MRI scans: an improved marching cube algorithm. Biomed. Signal Process. Control 91, 105901 (2024).","journal-title":"Biomed. Signal Process. Control"},{"key":"786_CR26","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1016\/S0735-1097(86)80143-7","volume":"7","author":"D Wohlgelernter","year":"1986","unstructured":"Wohlgelernter, D. et al. Regional myocardial dysfunction during coronary angioplasty: evaluation by two-dimensional echocardiography and 12 lead electrocardiography. J. Am. Coll. Cardiol. 7, 1245\u20131254 (1986).","journal-title":"J. Am. Coll. Cardiol."},{"key":"786_CR27","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1001\/jamacardio.2023.0968","volume":"8","author":"R Avram","year":"2023","unstructured":"Avram, R. et al. Automated assessment of cardiac systolic function from coronary angiograms with video-based artificial intelligence algorithms. JAMA Cardiol. 8, 586\u2013594 (2023).","journal-title":"JAMA Cardiol."},{"key":"786_CR28","doi-asserted-by":"publisher","first-page":"bbab569","DOI":"10.1093\/bib\/bbab569","volume":"23","author":"SR Stahlschmidt","year":"2022","unstructured":"Stahlschmidt, S. R., Ulfenborg, B. & Synnergren, J. Multimodal deep learning for biomedical data fusion: a review. Brief. Bioinform. 23, bbab569 (2022).","journal-title":"Brief. Bioinform."},{"key":"786_CR29","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2025.8731","author":"G Holste","year":"2025","unstructured":"Holste, G. et al. Complete AI-enabled echocardiography interpretation with multitask deep learning. JAMA https:\/\/doi.org\/10.1001\/jama.2025.8731 (2025).","journal-title":"JAMA"},{"key":"786_CR30","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1016\/j.jacc.2023.09.800","volume":"82","author":"ES Lau","year":"2023","unstructured":"Lau, E. S. et al. Deep learning\u2013enabled assessment of left heart structure and function predicts cardiovascular outcomes. J. Am. Coll. Cardiol. 82, 1936\u20131948 (2023).","journal-title":"J. Am. Coll. Cardiol."},{"key":"786_CR31","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/5.554205","volume":"85","author":"DL Hall","year":"1997","unstructured":"Hall, D. L. & Llinas, J. An introduction to multi-sensor data fusion. Proc. IEEE 85, 6\u201323 (1997).","journal-title":"Proc. IEEE"},{"key":"786_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2024.01.011","author":"AC Kwan","year":"2024","unstructured":"Kwan, A. C. et al. Deep learning-derived myocardial strain. JACC Cardiovasc. Imaging https:\/\/doi.org\/10.1016\/j.jcmg.2024.01.011 (2024).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"786_CR33","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.1016\/j.jcmg.2023.02.017","volume":"16","author":"M Tokodi","year":"2023","unstructured":"Tokodi, M. et al. Deep learning-based prediction of right ventricular ejection fraction using 2D echocardiograms. JACC Cardiovasc. Imaging 16, 1005\u20131018 (2023).","journal-title":"JACC Cardiovasc. Imaging"},{"key":"786_CR34","doi-asserted-by":"publisher","first-page":"985657","DOI":"10.3389\/fcvm.2023.985657","volume":"10","author":"X Lin","year":"2023","unstructured":"Lin, X. et al. Echocardiography-based AI for detection and quantification of atrial septal defect. Front. Cardiovasc. Med. 10, 985657 (2023).","journal-title":"Front. Cardiovasc. Med."},{"key":"786_CR35","first-page":"8024","volume":"32","author":"A Paszke","year":"2019","unstructured":"Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, 8024\u20138035 (2019).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"786_CR36","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.patrec.2008.08.010","volume":"30","author":"C Ferri","year":"2009","unstructured":"Ferri, C., Hern\u00e1ndez-Orallo, J. & Modroiu, R. An experimental comparison of performance measures for classification. Pattern Recognit. Lett. 30, 27\u201338 (2009).","journal-title":"Pattern Recognit. Lett."},{"key":"786_CR37","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44, 837\u2013845 (1988).","journal-title":"Biometrics"},{"key":"786_CR38","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1136\/bmj.310.6973.170","volume":"310","author":"JM Bland","year":"1995","unstructured":"Bland, J. M. & Altman, D. G. Multiple significance tests: the Bonferroni method. Brit. Med. J. 310, 170 (1995).","journal-title":"Brit. Med. J."}],"container-title":["Nature Cardiovascular Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s44161-026-00786-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44161-026-00786-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44161-026-00786-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:07:49Z","timestamp":1773770869000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s44161-026-00786-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["786"],"URL":"https:\/\/doi.org\/10.1038\/s44161-026-00786-7","relation":{},"ISSN":["2731-0590"],"issn-type":[{"value":"2731-0590","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"25 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"G.H.T. has previously received research grants from Janssen Pharmaceuticals and MyoKardia, Inc., a wholly owned subsidiary of Bristol Myers Squibb, and is an advisor to Prolaio Inc. and Viz.ai. S.A. was at UCSF during his contribution to this work; the information and views herein are solely S.A.\u2019s and do not represent his current employer (Point72). The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}