{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T04:09:51Z","timestamp":1774066191671,"version":"3.50.1"},"posted":{"date-parts":[[2024,6,14]]},"group-title":"Cardiovascular Medicine","reference-count":30,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2024,6,14]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                <jats:sec>\n                  <jats:title>Importance<\/jats:title>\n                  <jats:p>Chronic liver disease affects more than 1.5 billion adults worldwide, however the majority of cases are asymptomatic and undiagnosed. Echocardiography is broadly performed and visualizes the liver; but this information is not leveraged.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To develop and evaluate a deep learning algorithm on echocardiography videos to enable opportunistic screening for chronic liver disease.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Design<\/jats:title>\n                  <jats:p>Retrospective observational cohorts<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Setting<\/jats:title>\n                  <jats:p>Two large urban academic medical centers<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Participants<\/jats:title>\n                  <jats:p>Adult patients who received echocardiography and abdominal imaging (either abdominal ultrasound or abdominal magnetic resonance imaging) with \u226430 days between tests, between July 4, 2012, to June 4, 2022.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Exposure<\/jats:title>\n                  <jats:p>Deep learning model predictions from a deep-learning computer vision pipeline that identifies subcostal view echocardiogram videos and detects the presence of cirrhosis or steatotic liver disease (SLD).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Main Outcome and Measures<\/jats:title>\n                  <jats:p>Clinical diagnosis by paired abdominal ultrasound or magnetic resonance imaging (MRI).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>A total of 1,596,640 echocardiogram videos (66,922 studies from 24,276 patients) from Cedars-Sinai Medical Center (CSMC) were used to develop EchoNet-Liver, an automated pipeline that identifies high quality subcostal images from echocardiogram studies and detects the presence of cirrhosis or SLD. In the held-out CSMC test cohort, EchoNet-Liver was able to detect the presence of cirrhosis with an AUC of 0.837 (0.789 - 0.880) and SLD with an AUC of 0.799 (0.758 - 0.837). In a separate test cohort with paired abdominal MRIs, cirrhosis was detected with an AUC of 0.704 (0.689-0.718) and SLD was detected with an AUC of 0.726 (0.659-0.790). In an external test cohort of 106 patients (n = 5,280 videos), the model detected cirrhosis with an AUC of 0.830 (0.738 - 0.909) and SLD with an AUC of 0.768 (0.652 \u2013 0.875).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions and Relevance<\/jats:title>\n                  <jats:p>Deep learning assessment of clinical echocardiography enables opportunistic screening of SLD and cirrhosis. Application of this algorithm may identify patients who may benefit from further diagnostic testing and treatment for chronic liver disease.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>KEY POINTS<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Question<\/jats:title>\n                    <jats:p>Can a deep learning algorithm applied to echocardiography videos effectively identify chronic liver diseases including cirrhosis and steatotic liver disease (SLD)?<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Findings<\/jats:title>\n                    <jats:p>This retrospective observational cohort study utilized 1,596,640 echocardiography videos from 66,922 studies of 24,276 patients. The deep learning model with a computer vision pipeline (EchoNet-Liver) demonstrated strong performance to detect cirrhosis and SLD. External validation at a geographically distinct site demonstrated similar discriminative ability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Meaning<\/jats:title>\n                    <jats:p>The application of EchoNet-Liver to echocardiography could aid opportunistic screening of chronic liver diseases, providing a unique cost-effective angle to improve patient management.<\/jats:p>\n                  <\/jats:sec>\n                <\/jats:sec>","DOI":"10.1101\/2024.06.13.24308898","type":"posted-content","created":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T12:55:29Z","timestamp":1718369729000},"source":"Crossref","is-referenced-by-count":5,"title":["Opportunistic Screening of Chronic Liver Disease with Deep Learning Enhanced Echocardiography"],"prefix":"10.64898","author":[{"given":"Yuki","family":"Sahashi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milos","family":"Vukadinovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatemeh","family":"Amrollahi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirsh","family":"Trivedi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Rhee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4977-036X","authenticated-orcid":false,"given":"Susan","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3813-7518","authenticated-orcid":false,"given":"David","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan C.","family":"Kwan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2024061804500735000_2024.06.13.24308898v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cgh.2019.07.060"},{"issue":"1","key":"2024061804500735000_2024.06.13.24308898v1.2","doi-asserted-by":"crossref","first-page":"102068","DOI":"10.1016\/j.clinre.2022.102068","article-title":"Global burden of non-alcoholic fatty liver disease in 204 countries and territories from 1990 to 2019","volume":"47","year":"2023","journal-title":"Clin Res Hepatol Gastroenterol"},{"issue":"3","key":"2024061804500735000_2024.06.13.24308898v1.3","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/S2468-1253(19)30349-8","article-title":"The global, regional, and national burden of cirrhosis by cause in 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017","volume":"5","author":"GBD 2017 Cirrhosis Collaborators","year":"2020","journal-title":"Lancet Gastroenterol Hepatol"},{"issue":"1","key":"2024061804500735000_2024.06.13.24308898v1.4","doi-asserted-by":"crossref","first-page":"e2353965","DOI":"10.1001\/jamanetworkopen.2023.53965","article-title":"Undiagnosed Cirrhosis and Hepatic Encephalopathy in a National Cohort of Veterans With Dementia","volume":"7","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2024061804500735000_2024.06.13.24308898v1.5","doi-asserted-by":"publisher","DOI":"10.2337\/dc22-2048"},{"key":"2024061804500735000_2024.06.13.24308898v1.6","doi-asserted-by":"publisher","DOI":"10.1097\/HEP.0000000000000845"},{"issue":"5","key":"2024061804500735000_2024.06.13.24308898v1.7","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1097\/HEP.0000000000000323","article-title":"AASLD Practice Guidance on the clinical assessment and management of nonalcoholic fatty liver disease","volume":"77","year":"2023","journal-title":"Hepatology"},{"key":"2024061804500735000_2024.06.13.24308898v1.8","unstructured":"Virnig BA , Shippee ND , O\u2019Donnell B , Zeglin J , Parashuram S. Trends in the Use of Echocardiography, 2007 to 2011. Agency for Healthcare Research and Quality (US); 2014."},{"key":"2024061804500735000_2024.06.13.24308898v1.9","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2023.3701"},{"key":"2024061804500735000_2024.06.13.24308898v1.10","doi-asserted-by":"crossref","first-page":"103613","DOI":"10.1016\/j.ebiom.2021.103613","article-title":"Deep learning evaluation of biomarkers from echocardiogram videos","volume":"73","year":"2021","journal-title":"EBioMedicine"},{"issue":"4","key":"2024061804500735000_2024.06.13.24308898v1.11","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1001\/jamacardio.2021.6059","article-title":"High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy With Cardiovascular Deep Learning","volume":"7","year":"2022","journal-title":"JAMA Cardiol"},{"key":"2024061804500735000_2024.06.13.24308898v1.12","doi-asserted-by":"publisher","DOI":"10.1101\/2024.02.08.24302547"},{"issue":"1","key":"2024061804500735000_2024.06.13.24308898v1.13","doi-asserted-by":"crossref","first-page":"2726","DOI":"10.1038\/s41467-021-22877-8","article-title":"Artificial intelligence-enabled fully automated detection of cardiac amyloidosis using electrocardiograms and echocardiograms","volume":"12","year":"2021","journal-title":"Nat Commun"},{"key":"2024061804500735000_2024.06.13.24308898v1.14","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2024.0595"},{"issue":"20","key":"2024061804500735000_2024.06.13.24308898v1.15","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1016\/j.jacc.2023.09.800","article-title":"Deep Learning\u2013Enabled Assessment of Left Heart Structure and Function Predicts Cardiovascular Outcomes","volume":"82","year":"2023","journal-title":"J Am Coll Cardiol"},{"issue":"7802","key":"2024061804500735000_2024.06.13.24308898v1.16","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1038\/s41586-020-2145-8","article-title":"Video-based AI for beat-to-beat assessment of cardiac function","volume":"580","year":"2020","journal-title":"Nature"},{"key":"2024061804500735000_2024.06.13.24308898v1.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2024.01.011"},{"issue":"1","key":"2024061804500735000_2024.06.13.24308898v1.18","doi-asserted-by":"crossref","first-page":"e46","DOI":"10.1016\/S2589-7500(21)00235-1","article-title":"Automated interpretation of systolic and diastolic function on the echocardiogram: a multicohort study","volume":"4","year":"2022","journal-title":"The Lancet Digital Health"},{"issue":"7957","key":"2024061804500735000_2024.06.13.24308898v1.19","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1038\/s41586-023-05947-3","article-title":"Blinded, randomized trial of sonographer versus AI cardiac function assessment","volume":"616","year":"2023","journal-title":"Nature"},{"key":"2024061804500735000_2024.06.13.24308898v1.20","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2309000"},{"issue":"12","key":"2024061804500735000_2024.06.13.24308898v1.21","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1056\/NEJMoa2028395","article-title":"A Placebo-Controlled Trial of Subcutaneous Semaglutide in Nonalcoholic Steatohepatitis","volume":"384","year":"2021","journal-title":"N Engl J Med"},{"key":"2024061804500735000_2024.06.13.24308898v1.22","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa2401755"},{"issue":"17","key":"2024061804500735000_2024.06.13.24308898v1.23","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1001\/jama.2023.17935","article-title":"Diagnosis and Management of Nonalcoholic Fatty Liver Disease","volume":"330","year":"2023","journal-title":"JAMA"},{"issue":"18","key":"2024061804500735000_2024.06.13.24308898v1.24","doi-asserted-by":"crossref","first-page":"1589","DOI":"10.1001\/jama.2023.5997","article-title":"Diagnosis and Management of Cirrhosis and Its Complications: A Review","volume":"329","year":"2023","journal-title":"JAMA"},{"issue":"4","key":"2024061804500735000_2024.06.13.24308898v1.25","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1002\/hep.29639","article-title":"Optimal threshold of controlled attenuation parameter with MRI-PDFF as the gold standard for the detection of hepatic steatosis","volume":"67","year":"2018","journal-title":"Hepatology"},{"key":"2024061804500735000_2024.06.13.24308898v1.26","first-page":"2261","article-title":"Densely connected convolutional networks","volume":"25","year":"2016","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. Published online August"},{"key":"2024061804500735000_2024.06.13.24308898v1.27","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"2024061804500735000_2024.06.13.24308898v1.28","doi-asserted-by":"crossref","unstructured":"Selvaraju RR , Cogswell M , Das A , Vedantam R , Parikh D , Batra D. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In: 2017 IEEE International Conference on Computer Vision (ICCV). IEEE; 2017:618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"issue":"3","key":"2024061804500735000_2024.06.13.24308898v1.29","doi-asserted-by":"crossref","first-page":"E41","DOI":"10.1148\/radiol.229010","article-title":"Value-added Opportunistic CT Screening: State of the Art","volume":"303","year":"2022","journal-title":"Radiology"},{"issue":"9","key":"2024061804500735000_2024.06.13.24308898v1.30","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1161\/CIRCULATIONAHA.122.062746","article-title":"Incidental Coronary Artery Calcium: Opportunistic Screening of Previous Nongated Chest Computed Tomography Scans to Improve Statin Rates (NOTIFY-1 Project)","volume":"147","year":"2023","journal-title":"Circulation"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.06.13.24308898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:03:13Z","timestamp":1768507393000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2024.06.13.24308898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1101\/2024.06.13.24308898","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1056\/AIoa2400948","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2024,6,14]]},"subtype":"preprint"}}