{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T01:55:35Z","timestamp":1791251735869,"version":"4.1.0"},"reference-count":36,"publisher":"European Respiratory Society (ERS)","issue":"1","license":[{"start":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T00:00:00Z","timestamp":1719446400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"nference, Inc"},{"DOI":"10.13039\/100005205","name":"Janssen Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005205","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["publications.ersnet.org"],"crossmark-restriction":true},"short-container-title":["Eur Respir J"],"accepted":{"date-parts":[[2024,5,19]]},"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Early diagnosis of pulmonary hypertension (PH) is critical for effective treatment and management. We aimed to develop and externally validate an artificial intelligence algorithm that could serve as a PH screening tool, based on analysis of a standard 12-lead ECG.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The PH Early Detection Algorithm (PH-EDA) is a convolutional neural network developed using retrospective ECG voltage\u2013time data, with patients classified as \u201cPH-likely\u201d or \u201cPH-unlikely\u201d (controls) based on right heart catheterisation or echocardiography. In total, 39\u2009823 PH-likely patients and 219\u2009404 control patients from Mayo Clinic were randomly split into training (48%), validation (12%) and test (40%) sets. ECGs taken within 1\u2005month of PH diagnosis (diagnostic dataset) were used to train the PH-EDA at Mayo Clinic. Performance was tested on diagnostic ECGs within the test sets from Mayo Clinic (n=16\u2009175\/87\u2009998 PH-likely\/controls) and Vanderbilt University Medical Center (VUMC; n=6045\/24\u2009256 PH-likely\/controls). In addition, performance was tested on ECGs taken 6\u201318\u2005months (pre-emptive dataset), and up to 5\u2005years prior to a PH diagnosis at both sites.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Performance testing yielded an area under the receiver operating characteristic curve (AUC) of 0.92 and 0.88 in the diagnostic test sets at Mayo Clinic and VUMC, respectively, and 0.86 and 0.81, respectively, in the pre-emptive test sets. The AUC remained a minimum of 0.79 at Mayo Clinic and 0.73 at VUMC up to 5\u2005years before diagnosis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The PH-EDA can detect PH at diagnosis and 6\u201318\u2005months prior, demonstrating the potential to accelerate diagnosis and management of this debilitating disease.<\/jats:p><\/jats:sec>","DOI":"10.1183\/13993003.00192-2024","type":"journal-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T15:29:20Z","timestamp":1719502160000},"page":"2400192","update-policy":"https:\/\/doi.org\/10.1183\/ers-crossmark-policy","source":"Crossref","is-referenced-by-count":38,"title":["An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension"],"prefix":"10.1183","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8410-4429","authenticated-orcid":false,"given":"Hilary M.","family":"DuBrock","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7347-8708","authenticated-orcid":false,"given":"Tyler E.","family":"Wagner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2083-944X","authenticated-orcid":false,"given":"Katherine","family":"Carlson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Corinne L.","family":"Carpenter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8392-0205","authenticated-orcid":false,"given":"Samir","family":"Awasthi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9706-7900","authenticated-orcid":false,"given":"Zachi I.","family":"Attia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4128-3978","authenticated-orcid":false,"given":"Robert P.","family":"Frantz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul A.","family":"Friedman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suraj","family":"Kapa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3097-4186","authenticated-orcid":false,"given":"Jeffrey","family":"Annis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evan L.","family":"Brittain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2755-5845","authenticated-orcid":false,"given":"Anna R.","family":"Hemnes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel J.","family":"Asirvatham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melwin","family":"Babu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashim","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Unice","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rakesh","family":"Barve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mona","family":"Selej","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Agron","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Kogan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deborah","family":"Quinn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Preston","family":"Dunnmon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Najat","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7434-9211","authenticated-orcid":false,"given":"Venky","family":"Soundararajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"81","published-online":{"date-parts":[[2024,6,27]]},"reference":[{"key":"2024102103272358000_64.1.2400192.1","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/S2213-2600(15)00543-3","article-title":"A global view of pulmonary hypertension","volume":"4","author":"Hoeper","year":"2016","journal-title":"Lancet Respir Med"},{"key":"2024102103272358000_64.1.2400192.2","doi-asserted-by":"crossref","first-page":"73","DOI":"10.2174\/1573403X09666131117164122","article-title":"Pulmonary hypertension: types and treatments","volume":"11","author":"Rose-Jones","year":"2015","journal-title":"Curr Cardiol Rev"},{"key":"2024102103272358000_64.1.2400192.3","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01900-2018"},{"key":"2024102103272358000_64.1.2400192.4","doi-asserted-by":"crossref","first-page":"3618","DOI":"10.1093\/eurheartj\/ehac237","article-title":"2022 ESC\/ERS guidelines for the diagnosis and treatment of pulmonary hypertension","volume":"43","author":"Humbert","year":"2022","journal-title":"Eur Heart J"},{"key":"2024102103272358000_64.1.2400192.5","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.00879-2022"},{"key":"2024102103272358000_64.1.2400192.6","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehv317"},{"key":"2024102103272358000_64.1.2400192.7","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01032-2015"},{"key":"2024102103272358000_64.1.2400192.8","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1016\/j.chest.2019.01.035","article-title":"A prospective evaluation of the diagnostic accuracy of the physical examination for pulmonary hypertension","volume":"155","author":"Braganza","year":"2019","journal-title":"Chest"},{"key":"2024102103272358000_64.1.2400192.9","doi-asserted-by":"publisher","DOI":"10.1378\/chest.10-1166"},{"key":"2024102103272358000_64.1.2400192.10","doi-asserted-by":"crossref","first-page":"e12188","DOI":"10.1002\/pul2.12188","article-title":"Time to diagnosis of pulmonary hypertension and diagnostic burden: a retrospective analysis of nationwide US healthcare data","volume":"13","author":"Didden","year":"2023","journal-title":"Pulm Circ"},{"key":"2024102103272358000_64.1.2400192.11","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1186\/s12890-019-0827-5","article-title":"The patient experience of pulmonary hypertension: a large cross-sectional study of UK patients","volume":"19","author":"Armstrong","year":"2019","journal-title":"BMC Pulm Med"},{"key":"2024102103272358000_64.1.2400192.12","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1001\/jamacardio.2022.0011","article-title":"Finding pulmonary arterial hypertension \u2013 switching to offense to mitigate disease burden","volume":"7","author":"Maron","year":"2022","journal-title":"JAMA Cardiol"},{"key":"2024102103272358000_64.1.2400192.13","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1111\/resp.13768","article-title":"Diagnostic delay in pulmonary arterial hypertension: insights from the Australian and New Zealand pulmonary hypertension registry","volume":"25","author":"Khou","year":"2020","journal-title":"Respirology"},{"key":"2024102103272358000_64.1.2400192.14","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01687-2018"},{"key":"2024102103272358000_64.1.2400192.15","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1164\/rccm.201604-0882PP","article-title":"Translational advances in the field of pulmonary hypertension. Focusing on developmental origins and disease inception for the prevention of pulmonary hypertension","volume":"195","author":"Maron","year":"2017","journal-title":"Am J Respir Crit Care Med"},{"key":"2024102103272358000_64.1.2400192.16","doi-asserted-by":"crossref","first-page":"e026413","DOI":"10.1161\/JAHA.122.026413","article-title":"Gaps in the care of pulmonary hypertension: a cross-sectional patient simulation study among practicing cardiologists and pulmonologists","volume":"12","author":"de Belen","year":"2023","journal-title":"J Am Heart Assoc"},{"key":"2024102103272358000_64.1.2400192.17","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.jelectrocard.2023.02.007","article-title":"Electrocardiogram in patients with pulmonary hypertension","volume":"79","author":"Ley","year":"2023","journal-title":"J Electrocardiol"},{"key":"2024102103272358000_64.1.2400192.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2019.12.030"},{"key":"2024102103272358000_64.1.2400192.19","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0240-2"},{"key":"2024102103272358000_64.1.2400192.20","doi-asserted-by":"crossref","first-page":"8445","DOI":"10.1038\/s41598-020-65105-x","article-title":"Performance of a convolutional neural network derived from an ECG database in recognizing myocardial infarction","volume":"10","author":"Makimoto","year":"2020","journal-title":"Sci Rep"},{"key":"2024102103272358000_64.1.2400192.21","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/j.eclinm.2019.02.005","article-title":"Multi-centre randomised controlled trial of a smartphone-based event recorder alongside standard care versus standard care for patients presenting to the emergency department with palpitations and pre-syncope: the IPED (Investigation of Palpitations in the ED) study","volume":"8","author":"Reed","year":"2019","journal-title":"EClinicalMedicine"},{"key":"2024102103272358000_64.1.2400192.22","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1016\/j.cardfail.2022.12.016","article-title":"Electrocardiogram detection of pulmonary hypertension using deep learning","volume":"29","author":"Aras","year":"2023","journal-title":"J Card Fail"},{"key":"2024102103272358000_64.1.2400192.23","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528162"},{"key":"2024102103272358000_64.1.2400192.24","doi-asserted-by":"crossref","first-page":"e007952","DOI":"10.1161\/CIRCEP.119.007952","article-title":"Artificial intelligence and machine learning in arrhythmias and cardiac electrophysiology","volume":"13","author":"Feeny","year":"2020","journal-title":"Circ Arrhythm Electrophysiol"},{"key":"2024102103272358000_64.1.2400192.25","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(19)31721-0"},{"key":"2024102103272358000_64.1.2400192.26","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"},{"key":"2024102103272358000_64.1.2400192.27","doi-asserted-by":"publisher","DOI":"10.1183\/13993003.01904-2018"},{"key":"2024102103272358000_64.1.2400192.28","doi-asserted-by":"crossref","first-page":"e0168706","DOI":"10.1371\/journal.pone.0168706","article-title":"Use of ECG and other simple non-invasive tools to assess pulmonary hypertension","volume":"11","author":"Kovacs","year":"2016","journal-title":"PLoS One"},{"key":"2024102103272358000_64.1.2400192.29","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1093\/ehjci\/jeaa001","article-title":"A machine learning cardiac magnetic resonance approach to extract disease features and automate pulmonary arterial hypertension diagnosis","volume":"22","author":"Swift","year":"2021","journal-title":"Eur Heart J Cardiovasc Imaging"},{"key":"2024102103272358000_64.1.2400192.30","doi-asserted-by":"crossref","first-page":"e0224453","DOI":"10.1371\/journal.pone.0224453","article-title":"A machine learning approach for the prediction of pulmonary hypertension","volume":"14","author":"Leha","year":"2019","journal-title":"PLoS One"},{"key":"2024102103272358000_64.1.2400192.31","doi-asserted-by":"crossref","first-page":"2045894019890549","DOI":"10.1177\/2045894019890549","article-title":"Utilising artificial intelligence to determine patients at risk of a rare disease: idiopathic pulmonary arterial hypertension","volume":"9","author":"Kiely","year":"2019","journal-title":"Pulm Circ"},{"key":"2024102103272358000_64.1.2400192.32","doi-asserted-by":"crossref","first-page":"19311","DOI":"10.1038\/s41598-020-76359-w","article-title":"Deep learning to predict elevated pulmonary artery pressure in patients with suspected pulmonary hypertension using standard chest X ray","volume":"10","author":"Kusunose","year":"2020","journal-title":"Sci Rep"},{"key":"2024102103272358000_64.1.2400192.33","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1016\/j.healun.2020.04.009","article-title":"Artificial intelligence for early prediction of pulmonary hypertension using electrocardiography","volume":"39","author":"Kwon","year":"2020","journal-title":"J Heart Lung Transplant"},{"key":"2024102103272358000_64.1.2400192.34","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCEP.119.007988"},{"key":"2024102103272358000_64.1.2400192.35","doi-asserted-by":"publisher","DOI":"10.1183\/09059180.00008211"},{"key":"2024102103272358000_64.1.2400192.36","doi-asserted-by":"publisher","DOI":"10.4103\/2045-8932.109919"}],"container-title":["European Respiratory Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1183\/13993003.00192-2024","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T07:21:11Z","timestamp":1740381671000},"score":1,"resource":{"primary":{"URL":"https:\/\/publications.ersnet.org\/lookup\/doi\/10.1183\/13993003.00192-2024"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,27]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,7,25]]},"published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10.1183\/13993003.00192-2024"],"URL":"https:\/\/doi.org\/10.1183\/13993003.00192-2024","relation":{},"ISSN":["0903-1936","1399-3003"],"issn-type":[{"value":"0903-1936","type":"print"},{"value":"1399-3003","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,27]]}}}