{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T13:31:30Z","timestamp":1768570290284,"version":"3.49.0"},"posted":{"date-parts":[[2024,12,1]]},"group-title":"Cardiovascular Medicine","reference-count":22,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2024,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Timely and accurate detection of pericardial effusion and assessment cardiac tamponade remain challenging and highly operator dependent.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>Artificial intelligence has advanced many echocardiographic assessments, and we aimed to develop and validate a deep learning model to automate the assessment of pericardial effusion severity and cardiac tamponade from echocardiogram videos.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We developed a deep learning model (EchoNet-Pericardium) using temporal-spatial convolutional neural networks to automate pericardial effusion severity grading and tamponade detection from echocardiography videos. The model was trained using a retrospective dataset of 1,427,660 videos from 85,380 echocardiograms at Cedars-Sinai Medical Center (CSMC) to predict PE severity and cardiac tamponade across individual echocardiographic views and an ensemble approach combining predictions from five standard views. External validation was performed on 33,310 videos from 1,806 echocardiograms from Stanford Healthcare (SHC).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In the held out CSMC test set, EchoNet-Pericardium achieved an AUC of 0.900 (95% CI: 0.884\u2013 0.916) for detecting moderate or larger pericardial effusion, 0.942 (95% CI: 0.917\u20130.964) for large pericardial effusion, and 0.955 (95% CI: 0.939\u20130.968) for cardiac tamponade. In the SHC external validation cohort, the model achieved AUCs of 0.869 (95% CI: 0.794\u20130.933) for moderate or larger pericardial effusion, 0.959 (95% CI: 0.945\u20130.972) for large pericardial effusion, and 0.966 (95% CI: 0.906\u20130.995) for cardiac tamponade. Subgroup analysis demonstrated consistent performance across ages, sexes, left ventricular ejection fraction, and atrial fibrillation statuses.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Our deep learning-based framework accurately grades pericardial effusion severity and detects cardiac tamponade from echocardiograms, demonstrating consistent performance and generalizability across different cohorts. This automated tool has the potential to enhance clinical decision-making by reducing operator dependence and expediting diagnosis.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2024.11.27.24318110","type":"posted-content","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T10:25:12Z","timestamp":1733048712000},"source":"Crossref","is-referenced-by-count":1,"title":["Automated Evaluation for Pericardial Effusion and Cardiac Tamponade with Echocardiographic Artificial Intelligence"],"prefix":"10.64898","author":[{"given":"I-Min","family":"Chiu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milos","family":"Vukadinovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Sahashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul P.","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Yung","family":"Cheng","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"}]}],"member":"54368","reference":[{"key":"2024120308300471000_2024.11.27.24318110v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/0002-9149(70)90705-8"},{"key":"2024120308300471000_2024.11.27.24318110v1.2","doi-asserted-by":"publisher","DOI":"10.1002\/clc.4960220703"},{"key":"2024120308300471000_2024.11.27.24318110v1.3","doi-asserted-by":"crossref","first-page":"533","DOI":"10.2459\/01.JCM.0000234772.73454.57","article-title":"Echocardiography in the diagnosis and management of pericardial disease","volume":"7","year":"2006","journal-title":"J. Cardiovasc. Med. (Hagerstown)"},{"key":"2024120308300471000_2024.11.27.24318110v1.4","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1002\/clc.4960091105","article-title":"Pseudopericardial effusion: echocardiographic and computed tomographic correlations","volume":"9","year":"1986","journal-title":"Clin. Cardiol"},{"key":"2024120308300471000_2024.11.27.24318110v1.5","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1016\/j.echo.2019.04.001","article-title":"Machine learning-based three-dimensional echocardiographic quantification of right ventricular size and function: Validation against cardiac magnetic resonance","volume":"32","year":"2019","journal-title":"J. Am. Soc. Echocardiogr"},{"key":"2024120308300471000_2024.11.27.24318110v1.6","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":"2024120308300471000_2024.11.27.24318110v1.7","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.120.047530"},{"key":"2024120308300471000_2024.11.27.24318110v1.8","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":"2024120308300471000_2024.11.27.24318110v1.9","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1161\/CIRCULATIONAHA.124.069047","article-title":"High-throughput deep learning detection of mitral regurgitation","volume":"150","year":"2024","journal-title":"Circulation"},{"key":"2024120308300471000_2024.11.27.24318110v1.10","doi-asserted-by":"crossref","first-page":"1195235","DOI":"10.3389\/fcvm.2023.1195235","article-title":"Development and validation of a deep learning pipeline to measure pericardial effusion in echocardiography","volume":"10","year":"2023","journal-title":"Front Cardiovasc Med"},{"key":"2024120308300471000_2024.11.27.24318110v1.11","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1007\/s11517-023-02855-6","article-title":"Automated detection and localization of pericardial effusion from point-of-care cardiac ultrasound examination","volume":"61","year":"2023","journal-title":"Med. Biol. Eng. Comput"},{"key":"2024120308300471000_2024.11.27.24318110v1.12","unstructured":"Scripts\/ConvertDICOMToAVI.Ipynb at Master \u00b7 Echonet\/Dynamic. (Github)."},{"key":"2024120308300471000_2024.11.27.24318110v1.13","unstructured":"Vukadinovic, M. et al. EchoPrime: A multi-video view-informed vision-language model for comprehensive echocardiography interpretation. arXiv [cs.CV] (2024)."},{"key":"2024120308300471000_2024.11.27.24318110v1.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.echo.2013.06.023"},{"key":"2024120308300471000_2024.11.27.24318110v1.15","unstructured":"r2plus1d_18 \u2014 Torchvision main documentation. https:\/\/pytorch.org\/vision\/main\/models\/generated\/torchvision.models.video.r2plus1d_18.html."},{"key":"2024120308300471000_2024.11.27.24318110v1.16","doi-asserted-by":"crossref","unstructured":"Madani, A. , Arnaout, R. , Mofrad, M. & Arnaout, R . Fast and accurate view classification of echocardiograms using deep learning. NPJ Digit. Med. 1, (2018).","DOI":"10.1038\/s41746-017-0013-1"},{"key":"2024120308300471000_2024.11.27.24318110v1.17","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/s41598-023-50735-8","article-title":"Deep learning for transesophageal echocardiography view classification","volume":"14","year":"2024","journal-title":"Sci. Rep"},{"key":"2024120308300471000_2024.11.27.24318110v1.18","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01342-5"},{"key":"2024120308300471000_2024.11.27.24318110v1.19","doi-asserted-by":"crossref","first-page":"534","DOI":"10.1001\/jamacardio.2024.0595","article-title":"A multimodal video-based AI biomarker for aortic stenosis development and progression","volume":"9","year":"2024","journal-title":"JAMA Cardiol"},{"key":"2024120308300471000_2024.11.27.24318110v1.20","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1038\/s41746-024-01269-4","article-title":"Prospective clinical evaluation of deep learning for ultrasonographic screening of abdominal aortic aneurysms","volume":"7","year":"2024","journal-title":"NPJ Digit. Med"},{"key":"2024120308300471000_2024.11.27.24318110v1.21","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1016\/j.echo.2023.03.001","article-title":"The use of artificial intelligence guidance for rheumatic heart disease screening by novices","volume":"36","year":"2023","journal-title":"J. Am. Soc. Echocardiogr"},{"key":"2024120308300471000_2024.11.27.24318110v1.22","first-page":"e235102","article-title":"Use of a deep-learning algorithm to guide novices in performing focused assessment with sonography in trauma. JAMA Netw","volume":"6","year":"2023","journal-title":"Open"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.11.27.24318110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:21:33Z","timestamp":1768508493000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2024.11.27.24318110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1101\/2024.11.27.24318110","relation":{},"subject":[],"published":{"date-parts":[[2024,12,1]]},"subtype":"preprint"}}