{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T01:27:22Z","timestamp":1792114042940,"version":"4.4.0"},"reference-count":6,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T00:00:00Z","timestamp":1667347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"One Brave Idea"},{"name":"American Heart Association and Verily"},{"name":"AstraZeneca and pillar"},{"DOI":"10.13039\/100015627","name":"Quest Diagnostics","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100015627","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,22]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Aim<\/jats:title><jats:p>Left ventricular systolic dysfunction (LVSD) carries an increased risk for overt heart failure and mortality, yet treatable to mitigate disease progression. An artificial intelligence (AI)-enabled 12-lead electrocardiogram (ECG) model demonstrated promise in LVSD screening, but the performance dropped unexpectedly in external validation. We thus sought to train de novo models for LVSD detection and investigated their performance across multiple institutions and across a broader set of patient strata.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods and results<\/jats:title><jats:p>ECGs taken within 14 days of an echocardiogram were obtained from four academic hospitals (three in the United States and one in Japan). Four AI models were trained to detect patients with ejection fraction (EF) &amp;lt;40% using ECGs from each of the four institutions. All the models were then evaluated on the held-out test data set from the same institution and data from the three external institutions. Subgroup analyses stratified by patient characteristics and common ECG abnormalities were performed. A total of 221 846 ECGs were identified from the 4 institutions. While the Brigham and Women\u2019s Hospital (BWH)-trained and Keio-trained models yielded similar accuracy on their internal test data [area under the receiver operating curve (AUROC) 0.913 and 0.914, respectively], external validity was worse for the Keio-trained model (AUROC: 0.905\u20130.915 for BWH trained and 0.849\u20130.877 for Keio-trained model). Although ECG abnormalities including atrial fibrillation, left bundle branch block, and paced rhythm-reduced detection, the models performed robustly across patient characteristics and other ECG features.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>While using the same model architecture, different data sets produced models with different performances for detecting low-EF highlighting the importance of external validation and extensive stratification analysis.<\/jats:p><\/jats:sec>","DOI":"10.1093\/ehjdh\/ztac065","type":"journal-article","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T06:18:37Z","timestamp":1667369917000},"page":"654-657","source":"Crossref","is-referenced-by-count":43,"title":["Importance of external validation and subgroup analysis of artificial intelligence in the detection of low ejection fraction from electrocardiograms"],"prefix":"10.1093","volume":"3","author":[{"given":"Ryuichiro","family":"Yagi","sequence":"first","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital , Boston, MA , USA"},{"name":"Harvard Medical School , Boston, MA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0450-0331","authenticated-orcid":false,"given":"Shinichi","family":"Goto","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital , Boston, MA , USA"},{"name":"Harvard Medical School , Boston, MA , USA"},{"name":"Department of Cardiology, Keio University School of Medicine, Shinjuku , Tokyo , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshinori","family":"Katsumata","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Keio University School of Medicine, Shinjuku , Tokyo , Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5181-2664","authenticated-orcid":false,"given":"Calum A","family":"MacRae","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital , Boston, MA , USA"},{"name":"Harvard Medical School , Boston, MA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2791-9434","authenticated-orcid":false,"given":"Rahul C","family":"Deo","sequence":"additional","affiliation":[{"name":"One Brave Idea and Division of Cardiovascular Medicine, Department of Medicine, Brigham and Women\u2019s Hospital , Boston, MA , USA"},{"name":"Harvard Medical School , Boston, MA , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,11,2]]},"reference":[{"key":"2023021909300351100_","first-page":"237","article-title":"Assessing the risk of progression from asymptomatic left ventricular dysfunction to overt heart failure a systematic overview and meta-analysis","volume":"4","author":"Echouffo-Tcheugui","year":"2016","journal-title":"J Am Coll Cardiol HF"},{"key":"2023021909300351100_","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1038\/s41591-018-0240-2","article-title":"Screening for cardiac contractile dysfunction using an artificial intelligence\u2013enabled electrocardiogram","volume":"25","author":"Attia","year":"2019","journal-title":"Nat Med"},{"key":"2023021909300351100_","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.ijcard.2020.12.065","article-title":"External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction","volume":"329","author":"Attia","year":"2021","journal-title":"Int J Cardiol"},{"key":"2023021909300351100_","doi-asserted-by":"crossref","first-page":"2176","DOI":"10.1038\/s41591-021-01595-0","article-title":"Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations","volume":"27","author":"Seyyed-Kalantari","year":"2021","journal-title":"Nat Med"},{"key":"2023021909300351100_","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1038\/s41591-021-01335-4","article-title":"Artificial intelligence\u2013enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial","volume":"27","author":"Yao","year":"2021","journal-title":"Nat Med"},{"key":"2023021909300351100_","doi-asserted-by":"crossref","DOI":"10.1161\/CIRCEP.119.007988","article-title":"Assessing and mitigating bias in medical artificial intelligence: the effects of race and ethnicity on a deep learning model for ECG analysis","volume":"13","author":"Noseworthy","year":"2020","journal-title":"Circulation Arrhythmia Electrophysiol"}],"container-title":["European Heart Journal - Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ehjdh\/advance-article-pdf\/doi\/10.1093\/ehjdh\/ztac065\/47051879\/ztac065.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/3\/4\/654\/49255155\/ztac065.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ehjdh\/article-pdf\/3\/4\/654\/49255155\/ztac065.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,10]],"date-time":"2023-03-10T23:25:46Z","timestamp":1678490746000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ehjdh\/article\/3\/4\/654\/6793726"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,2]]},"references-count":6,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,11,2]]},"published-print":{"date-parts":[[2022,12,22]]}},"URL":"https:\/\/doi.org\/10.1093\/ehjdh\/ztac065","relation":{},"ISSN":["2634-3916"],"issn-type":[{"value":"2634-3916","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,12,22]]},"published":{"date-parts":[[2022,11,2]]}}}