{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T13:21:29Z","timestamp":1770988889058,"version":"3.50.1"},"reference-count":10,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T00:00:00Z","timestamp":1670976000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T00:00:00Z","timestamp":1670976000000},"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":["Crit Care"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Machine learning algorithms have recently been developed to enable the automatic and real-time echocardiographic assessment of left ventricular ejection fraction (LVEF) and have not been evaluated in critically ill patients.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>Real-time LVEF was prospectively measured in 95 ICU patients with a machine learning algorithm installed on a cart-based ultrasound system. Real-time measurements taken by novices (LVEF<jats:sub>Nov<\/jats:sub>) and by experts (LVEF<jats:sub>Exp<\/jats:sub>) were compared with LVEF reference measurements (LVEF<jats:sub>Ref<\/jats:sub>) taken manually by echo experts.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>LVEF<jats:sub>Ref<\/jats:sub> ranged from 26 to 80% (mean 54\u2009\u00b1\u200912%), and the reproducibility of measurements was 9\u2009\u00b1\u20096%. Thirty patients (32%) had a LVEF<jats:sub>Ref<\/jats:sub>\u2009&lt;\u200950% (left ventricular systolic dysfunction). Real-time LVEF<jats:sub>Exp<\/jats:sub> and LVEF<jats:sub>Nov<\/jats:sub> measurements ranged from 31 to 68% (mean 54\u2009\u00b1\u200910%) and from 28 to 70% (mean 54\u2009\u00b1\u20099%), respectively. The reproducibility of measurements was comparable for LVEF<jats:sub>Exp<\/jats:sub> (5\u2009\u00b1\u20094%) and for LVEF<jats:sub>Nov<\/jats:sub> (6\u2009\u00b1\u20095%) and significantly better than for reference measurements (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). We observed a strong relationship between LVEF<jats:sub>Ref<\/jats:sub> and both real-time LVEF<jats:sub>Exp<\/jats:sub> (<jats:italic>r<\/jats:italic>\u2009=\u20090.86, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001) and LVEF<jats:sub>Nov<\/jats:sub> (<jats:italic>r<\/jats:italic>\u2009=\u20090.81, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.001). The average difference (bias) between real time and reference measurements was 0\u2009\u00b1\u20096% for LVEF<jats:sub>Exp<\/jats:sub> and 0\u2009\u00b1\u20097% for LVEF<jats:sub>Nov<\/jats:sub>. The sensitivity to detect systolic dysfunction was 70% for real-time LVEF<jats:sub>Exp<\/jats:sub> and 73% for LVEF<jats:sub>Nov<\/jats:sub>. The specificity to detect systolic dysfunction was 98% both for LVEF<jats:sub>Exp<\/jats:sub> and LVEF<jats:sub>Nov<\/jats:sub>.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>Machine learning-enabled real-time measurements of LVEF were strongly correlated with manual measurements obtained by experts. The accuracy of real-time LVEF measurements was excellent, and the precision was fair. The reproducibility of LVEF measurements was better with the machine learning system. The specificity to detect left ventricular dysfunction was excellent both for experts and for novices, whereas the sensitivity could be improved.<\/jats:p>\n                <jats:p><jats:italic>Trial registration<\/jats:italic>: NCT05336448. Retrospectively registered on April 19, 2022.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s13054-022-04269-6","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T11:03:04Z","timestamp":1671015784000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Machine learning for the real-time assessment of left ventricular ejection fraction in critically ill patients: a bedside evaluation by novices and experts in echocardiography"],"prefix":"10.1186","volume":"26","author":[{"given":"Rita","family":"Varudo","sequence":"first","affiliation":[]},{"given":"Filipe A.","family":"Gonzalez","sequence":"additional","affiliation":[]},{"given":"Jo\u00e3o","family":"Leote","sequence":"additional","affiliation":[]},{"given":"Cristina","family":"Martins","sequence":"additional","affiliation":[]},{"given":"Jacobo","family":"Bacariza","sequence":"additional","affiliation":[]},{"given":"Antero","family":"Fernandes","sequence":"additional","affiliation":[]},{"given":"Frederic","family":"Michard","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,14]]},"reference":[{"key":"4269_CR1","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1186\/s13054-017-1866-z","volume":"21","author":"S Orde","year":"2017","unstructured":"Orde S, Slama M, Hilton A, et al. Pearls and pitfalls in comprehensive critical care echocardiography. Crit Care. 2017;21:279.","journal-title":"Crit Care"},{"key":"4269_CR2","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1007\/s00134-019-05604-2","volume":"45","author":"A Vieillard-Baron","year":"2019","unstructured":"Vieillard-Baron A, Millington SJ, Sanfilippo F, et al. A decade of progress in critical care echocardiography: a narrative review. Intensive Care Med. 2019;45:770\u201388.","journal-title":"Intensive Care Med"},{"key":"4269_CR3","doi-asserted-by":"publisher","first-page":"2107","DOI":"10.1016\/j.chest.2020.07.021","volume":"158","author":"JA Marbach","year":"2020","unstructured":"Marbach JA, Almufleh A, Di Santo P, et al. A shifting paradigm: the role of focused cardiac ultrasound in bedside patient assessment. Chest. 2020;158:2107\u201318.","journal-title":"Chest"},{"key":"4269_CR4","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1016\/j.jacc.2018.12.054","volume":"73","author":"D Dey","year":"2019","unstructured":"Dey D, Slomka PJ, Leeson P, et al. Artificial intelligence in cardiovascular imaging. J Am Coll Cardiol. 2019;73:1317\u201335.","journal-title":"J Am Coll Cardiol"},{"key":"4269_CR5","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1001\/jamacardio.2021.0185","volume":"6","author":"A Narang","year":"2021","unstructured":"Narang A, Bae R, Hong H, et al. Using a deep-learning algorithm to guide novice to acquire echocardiograms for limited diagnostic use. JAMA Cardiol. 2021;6:624\u201332.","journal-title":"JAMA Cardiol"},{"key":"4269_CR6","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1111\/echo.15048","volume":"38","author":"W Nabi","year":"2021","unstructured":"Nabi W, Bansal A, Xu B. Applications of artificial intelligence and machine learning approaches in echocardiography. Echocardiography. 2021;38:982\u201392.","journal-title":"Echocardiography"},{"key":"4269_CR7","doi-asserted-by":"publisher","first-page":"e116","DOI":"10.1016\/j.bja.2022.07.037","volume":"129","author":"FA Gonzalez","year":"2022","unstructured":"Gonzalez FA, Varudo R, Leote J, et al. The automation of sub-aortic velocity time integral measurements by transthoracic echocardiography: clinical evaluation of an artificial intelligence-enabled tool in critically ill patients. Br J Anaesth. 2022;129:e116\u20139. https:\/\/doi.org\/10.1016\/j.bja.2022.07.037.","journal-title":"Br J Anaesth"},{"key":"4269_CR8","doi-asserted-by":"publisher","first-page":"e009303","DOI":"10.1161\/CIRCIMAGING.119.009303","volume":"12","author":"FM Asch","year":"2019","unstructured":"Asch FM, Poilvert N, Abraham T, et al. Automated echocardiographic quantification of left ventricular ejection fraction without volume measurements using a machine learning algorithm mimicking a human expert. Circ Cardiovasc Imaging. 2019;12:e009303.","journal-title":"Circ Cardiovasc Imaging"},{"key":"4269_CR9","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/s10554-020-02046-6","volume":"37","author":"M Schneider","year":"2021","unstructured":"Schneider M, Bartko P, Geller W, et al. A machine-learning algorithm supports ultrasound-na\u00efve novices in the acquisition of diagnostic echocardiography loops and provides accurate estimation of LVEF. Int J Cardiovasc Imaging. 2021;37:577\u201386.","journal-title":"Int J Cardiovasc Imaging"},{"key":"4269_CR10","doi-asserted-by":"publisher","first-page":"e012293","DOI":"10.1161\/CIRCIMAGING.120.012293","volume":"14","author":"FM Asch","year":"2021","unstructured":"Asch FM, Mor-Avi V, Rubenson D, et al. Deep-learning based automated echocardiographic quantification of left ventricular ejection fraction: a point-of-care solution. Circ Cardiovasc Imaging. 2021;14:e012293.","journal-title":"Circ Cardiovasc Imaging"}],"container-title":["Critical Care"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13054-022-04269-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13054-022-04269-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13054-022-04269-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T11:08:11Z","timestamp":1671016091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ccforum.biomedcentral.com\/articles\/10.1186\/s13054-022-04269-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,14]]},"references-count":10,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["4269"],"URL":"https:\/\/doi.org\/10.1186\/s13054-022-04269-6","relation":{},"ISSN":["1364-8535"],"issn-type":[{"value":"1364-8535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,14]]},"assertion":[{"value":"28 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study has been conducted in accordance with the Declaration of Helsinki principles and was approved by the ethical committee of hospital Garcia de Orta, Almada (# TI 71\/2021) on July 27, 2021, and written informed consent was obtained for all patients.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"386"}}