{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T16:51:54Z","timestamp":1791219114332,"version":"4.1.0"},"reference-count":44,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n The clinical value of artificial intelligence (AI)\u2013based diagnostic systems depends not only on their accuracy but also on how well their outputs integrate with clinicians\u2019 judgments in practice. Critical knowledge gaps remain regarding diagnostic concordance between AI and clinicians in stress echocardiography interpretation, patient characteristics predicting discordance, and how cardiologists respond when AI recommendations conflict with their clinical diagnoses.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study examined the diagnostic alignment between an AI-driven stress echocardiography system (EchoGo Pro [EGP]) and cardiologists\u2019 diagnoses of coronary artery disease (CAD), identified predictors of concordance and AI scan rejection, and explored cardiologists\u2019 decision-making strategies when disagreements arise.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We conducted mixed methods research. The quantitative study analyzed concordance between EGP and cardiologists using data from 854 participants with suspected CAD in the multicenter PROTEUS randomized controlled trial. Logistic regression identified predictors of agreement, disagreement, and scan rejection, adjusting for age, sex, smoking status, BMI, and cardiovascular risk factors (hypertension, hypercholesterolemia, diabetes, family history of CAD, and prior CAD events). To gain deeper insight into discordance, we conducted a qualitative study analyzing survey responses from 61 UK consultant cardiologists recruited via Qualtrics, exploring their perceptions of AI tools, the risks of following discordant AI recommendations, and their typical responses to AI-clinician disagreement.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n EGP and cardiologists agreed in 60% (512\/854) of the cases, but agreement was significantly lower among patients with hypertension (OR 0.58, 95% CI 0.38\u20100.89;\n P<\/jats:italic>\n =.01), diabetes (OR 0.56, 95% CI 0.35\u20100.90;\n P<\/jats:italic>\n =.02), and pre-existing CAD (OR 0.48, 95% CI 0.30\u20100.77;\n P<\/jats:italic>\n =.002). EGP rejected 26.1% (222\/854) of the scans due to insufficient image quality, with rejection significantly more common in male patients (\n \u03b2<\/jats:italic>\n =0.35;\n P<\/jats:italic>\n =.03) and those with a family history of CAD. If a positive CAD diagnosis was assigned when either cardiologists or EGP identified CAD, the proportion of positive cases increased from 17.9% (153\/854) to 22.1% (189\/854), potentially identifying additional at-risk patients. Survey respondents (50\/60, 85% male; 26\/57, 46% aged 40-49 years; 39\/61, 64% White) required 65% to 69% confidence in their initial diagnosis to justify disregarding contradictory AI recommendations. The survey findings revealed cardiologists treated AI recommendations as advisory rather than definitive. When facing discordance, they retained confidence in their judgment and sought corroboration through additional testing, data review, or second opinions rather than deferring to AI. Paradoxically, cardiologists with higher confidence in AI tools required greater confidence in their own diagnosis to disregard AI recommendations (\n \u03b2<\/jats:italic>\n =7.73;\n P<\/jats:italic>\n =.02). Cardiologists attributed discordance primarily to AI\u2019s inability to incorporate patient history, comorbidities, and broader clinical context.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n EGP shows promise as an adjunctive tool but struggles with multimorbid patients and exhibits high, uneven rejection rates. Cardiologists use AI to prompt scrutiny, not replace judgment. Future systems need to integrate wider patient data with imaging and minimize bias through representative training to avoid exacerbating inequities.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/83541","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T20:35:09Z","timestamp":1774989309000},"page":"e83541-e83541","source":"Crossref","is-referenced-by-count":1,"title":["Alignment Between Cardiologists and AI-Driven Diagnostic Systems: Mixed Methods Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7383-3455","authenticated-orcid":false,"given":"Mahdi","family":"Mahdavi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2468-6193","authenticated-orcid":false,"given":"Sarah","family":"White","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7448-9190","authenticated-orcid":false,"given":"Sandeep S","family":"Hothi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5170-7792","authenticated-orcid":false,"given":"Chris","family":"Flood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5056-5265","authenticated-orcid":false,"given":"Rosica","family":"Panayotova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0183-9516","authenticated-orcid":false,"given":"Daniel","family":"Frings","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1038\/s41746-020-00367-3","article-title":"Second opinion needed: communicating uncertainty in medical machine learning","volume":"4","author":"Kompa","journal-title":"NPJ Digit Med"},{"issue":"21","key":"R2","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2018.17163","article-title":"Clinical decision support in the era of artificial intelligence","volume":"320","author":"Shortliffe","journal-title":"JAMA"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"Topol","journal-title":"Nat Med"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106821","article-title":"Deep learning-based automatic segmentation of images in cardiac radiography: a promising challenge","volume":"220","author":"Song","journal-title":"Comput Methods Programs Biomed"},{"key":"R5","doi-asserted-by":"crossref","unstructured":"Raghu D Tripathy HK . Medical image analysis using deep learning algorithm convolutional neural networks. In: Pandian AP Fernando X Haoxiang W , editors. Computer Networks, Big Data and IoT. Vol 117. 2022:245-256. [doi: 10.1007\/978-981-19-0898-9_19]","DOI":"10.1007\/978-981-19-0898-9_19"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2025.1664183","article-title":"Application of artificial intelligence in non-invasive cardiovascular imaging for coronary artery disease: a systematic review and meta-analysis","volume":"12","author":"Liu","journal-title":"Front Cardiovasc Med"},{"issue":"16","key":"R7","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11162308","article-title":"Clinicians\u2019 perceptions of artificial intelligence: focus on workload, risk, trust, clinical decision making, and clinical integration","volume":"11","author":"Shamszare","journal-title":"Healthcare (Basel)"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1038\/s41746-025-01722-y","article-title":"Systematic review of cost effectiveness and budget impact of artificial intelligence in healthcare","volume":"8","author":"El Arab","journal-title":"NPJ Digit Med"},{"issue":"5","key":"R9","doi-asserted-by":"publisher","DOI":"10.1007\/s12410-017-9412-6","article-title":"The updated NICE guidelines: cardiac CT as the first-line test for coronary artery disease","volume":"10","author":"Moss","journal-title":"Curr Cardiovasc Imaging Rep"},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102165","article-title":"Artificial intelligence applied to support medical decisions for the automatic analysis of echocardiogram images: a systematic review","volume":"120","author":"de Siqueira","journal-title":"Artif Intell Med"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.2147\/VHRM.S431612","article-title":"Interobserver variability of coronary stenosis characterized by coronary angiography: a single-center (Toronto General Hospital) retrospective chart review by staff cardiologists","volume":"20","author":"Shivaie","journal-title":"Vasc Health Risk Manag"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2025.112059","article-title":"Assessment of inter- and intrareader agreement among different stenosis quantification methods in coronary CT angiography","volume":"186","author":"Rovetto","journal-title":"Eur J Radiol"},{"issue":"6","key":"R13","doi-asserted-by":"publisher","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","article-title":"A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis","volume":"1","author":"Liu","journal-title":"Lancet Digit Health"},{"issue":"4","key":"R14","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1001\/jama.2025.8731","article-title":"Complete AI-enabled echocardiography interpretation with multitask deep learning","volume":"334","author":"Holste","journal-title":"JAMA"},{"issue":"4","key":"R15","doi-asserted-by":"publisher","first-page":"R115","DOI":"10.1530\/ERP-18-0056","article-title":"Artificial intelligence and echocardiography","volume":"5","author":"Alsharqi","journal-title":"Echo Res Pract"},{"issue":"7","key":"R16","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1016\/j.cjca.2018.04.032","article-title":"Decision support tools, systems, and artificial intelligence in cardiac imaging","volume":"34","author":"Massalha","journal-title":"Can J Cardiol"},{"issue":"5","key":"R17","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1016\/j.jcmg.2021.10.013","article-title":"Automated echocardiographic detection of severe coronary artery disease using artificial intelligence","volume":"15","author":"Upton","journal-title":"JACC Cardiovasc Imaging"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m689","article-title":"Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies","volume":"368","author":"Nagendran","journal-title":"BMJ"},{"issue":"1","key":"R19","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01332-6","article-title":"Explainability for artificial intelligence in healthcare: a multidisciplinary perspective","volume":"20","author":"Amann","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41746-021-00385-9","article-title":"Do as AI say: susceptibility in deployment of clinical decision-aids","volume":"4","author":"Gaube","journal-title":"NPJ Digit Med"},{"key":"R21","doi-asserted-by":"crossref","unstructured":"Sivaraman V Bukowski LA Levin J Kahn JM Perer A . Ignore, trust, or negotiate: understanding clinician acceptance of AI-based treatment recommendations in health care. Presented at: CHI \u201923: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems; Hamburg Germany. 2023.[doi: 10.1145\/3544548.3581075]","DOI":"10.1145\/3544548.3581075"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1017\/dap.2020.25","article-title":"From satisficing to artificing: the evolution of administrative decision-making in the age of the algorithm","volume":"3","author":"Snow","journal-title":"Data & Policy"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2025.1651324","article-title":"Cognitive alignment in cardiovascular AI: designing predictive models that think with, not just for, clinicians","volume":"12","author":"Joseph","journal-title":"Front Cardiovasc Med"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1038\/s41746-024-01326-y","article-title":"Systematic review to understand users perspectives on AI-enabled decision aids to inform shared decision making","volume":"7","author":"Hassan","journal-title":"NPJ Digit Med"},{"issue":"10","key":"R25","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2023-079617","article-title":"Evaluating artificial intelligence-driven stress echocardiography analysis system (EASE study): a mixed method study","volume":"14","author":"Mahdavi","journal-title":"BMJ Open"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ahj.2023.05.003","article-title":"PROTEUS study: a prospective randomized controlled trial evaluating the use of artificial intelligence in stress echocardiography","volume":"263","author":"Woodward","journal-title":"Am Heart J"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.jclinepi.2010.03.002","article-title":"Guidelines for Reporting Reliability and Agreement Studies (GRRAS) were proposed","volume":"64","author":"Kottner","journal-title":"J Clin Epidemiol"},{"issue":"8","key":"R28","doi-asserted-by":"publisher","first-page":"573","DOI":"10.7326\/0003-4819-147-8-200710160-00010","article-title":"The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies","volume":"147","author":"von Elm","journal-title":"Ann Intern Med"},{"issue":"24","key":"R29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/ijerph16245134","article-title":"Comparison of the JNC7 and 2017 American College of Cardiology\/American Heart Association guidelines for the management of hypertension in Koreans: analysis of two independent nationwide population-based studies","volume":"16","author":"Choi","journal-title":"Int J Environ Res Public Health"},{"issue":"Suppl 1","key":"R30","doi-asserted-by":"publisher","first-page":"S19","DOI":"10.2337\/dc23-S002","article-title":"2. Classification and diagnosis of diabetes: standards of care in diabetes-2023","volume":"46","author":"ElSayed","journal-title":"Diabetes Care"},{"key":"R31","unstructured":"Demography question development for Census 2021. Office for National Statistics. 2024. URL: https:\/\/www.ons.gov.uk\/census\/censustransformationprogramme\/questiondevelopment\/demographyquestiondevelopmentforcensus2021 [Accessed 04-09-2025]"},{"issue":"33","key":"R32","doi-asserted-by":"publisher","first-page":"46","DOI":"10.53841\/bpsqmip.2022.1.33.46","article-title":"Thematic analysis: a practical guide to understanding and doing","volume":"1","author":"Braun","journal-title":"QMiP Bulletin"},{"issue":"13","key":"R33","doi-asserted-by":"publisher","DOI":"10.3390\/jcm14134452","article-title":"Comparing AI-driven and heart team decision-making in multivessel coronary artery disease","volume":"14","author":"Migliaro","journal-title":"J Clin Med"},{"issue":"34","key":"R34","doi-asserted-by":"publisher","first-page":"3227","DOI":"10.1093\/eurheartj\/ehab484","article-title":"2021 ESC Guidelines on cardiovascular disease prevention in clinical practice","volume":"42","author":"Visseren","journal-title":"Eur Heart J"},{"issue":"4","key":"R35","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1016\/j.mcpdig.2023.08.002","article-title":"Diagnostic accuracy of artificial intelligence in virtual primary care","volume":"1","author":"Zeltzer","journal-title":"Mayo Clin Proc Digit Health"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/s11739-021-02773-1","article-title":"Does chest shape influence exercise stress echocardiographic results in patients with suspected coronary artery disease?","volume":"17","author":"Sonaglioni","journal-title":"Intern Emerg Med"},{"issue":"17","key":"R37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/ijerph17176110","article-title":"A perspective from a case conference on comparing the diagnostic process: human diagnostic thinking vs. artificial intelligence (AI) decision support tools","volume":"17","author":"Harada","journal-title":"Int J Environ Res Public Health"},{"issue":"1","key":"R38","doi-asserted-by":"publisher","DOI":"10.1186\/s44156-023-00020-1","article-title":"Real world hospital costs following stress echocardiography in the UK: a costing study from the EVAREST\/BSE-NSTEP multi-entre study","volume":"10","author":"Johnson","journal-title":"Echo Res Pract"},{"issue":"25","key":"R39","doi-asserted-by":"publisher","first-page":"2690","DOI":"10.1016\/j.jacc.2024.04.028","article-title":"Addressing the global burden of cardiovascular disease in women: JACC state-of-the-art review","volume":"83","author":"Vervoort","journal-title":"J Am Coll Cardiol"},{"issue":"4","key":"R40","doi-asserted-by":"publisher","first-page":"e260","DOI":"10.1016\/S2589-7500(20)30317-4","article-title":"Health data poverty: an assailable barrier to equitable digital health care","volume":"3","author":"Ibrahim","journal-title":"Lancet Digit Health"},{"issue":"23","key":"R41","doi-asserted-by":"publisher","first-page":"12592","DOI":"10.1073\/pnas.1919012117","article-title":"Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis","volume":"117","author":"Larrazabal","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"2","key":"R42","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1111\/puar.13602","article-title":"\u2018Just like I thought\u2019: street\u2010level bureaucrats trust ai recommendations if they confirm their professional judgment","volume":"83","author":"Selten","journal-title":"Public Adm Rev"},{"issue":"13","key":"R43","doi-asserted-by":"publisher","first-page":"1456","DOI":"10.1016\/j.jacc.2015.07.052","article-title":"Fully automated versus standard tracking of left ventricular ejection fraction and longitudinal strain: the FAST-EFs multicenter study","volume":"66","author":"Knackstedt","journal-title":"J Am Coll Cardiol"},{"issue":"21","key":"R44","doi-asserted-by":"publisher","first-page":"2296","DOI":"10.1016\/j.jacc.2016.09.915","article-title":"Machine learning for echocardiographic imaging: embarking on another incredible journey","volume":"68","author":"Tajik","journal-title":"J Am Coll Cardiol"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e83541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:17:42Z","timestamp":1782843462000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e83541"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":44,"URL":"https:\/\/doi.org\/10.2196\/83541","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"article-number":"v28i1e83541"}}