{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T18:13:10Z","timestamp":1783620790640,"version":"3.55.0"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00c3\u00b3n y Universidades","doi-asserted-by":"publisher","award":["PID2021-126320NB-I00"],"award-info":[{"award-number":["PID2021-126320NB-I00"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003086","name":"Eusko Jaurlaritza","doi-asserted-by":"publisher","award":["IT1696-22"],"award-info":[{"award-number":["IT1696-22"]}],"id":[{"id":"10.13039\/501100003086","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>Despite their widespread adoption, Artificial Intelligence-based Patient Classification Systems sometimes rely on incorrect, outdated, or incomplete data, which can lead to inaccurate outputs. Nevertheless, health professionals are expected to override these errors, at least when they have access to critical information. To test this, we conducted two experiments in which professional physicians interacted with an Artificial Intelligence system that incorrectly classified fictitious patients as either highly or lowly sensitive to a treatment. The physicians administered the treatment to a series of fictitious patients and received feedback that was useful for learning that the patient classification was incorrect and that all patients were equally sensitive to the treatment. We ran two experiments: in Experiment 1, the medicine showed medium effectiveness for both types of patients, while in Experiment 2, the treatment was completely ineffective for both types of patients. The results showed that, in the two experiments, physicians generally trusted the AI-based patient classification and struggled to learn from the evidence. Furthermore, in Experiment 2, they failed to realize that the treatment was ineffective. Our findings have important implications for healthcare professionals and patients, underscoring the need to critically evaluate Patient Classification Systems.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001490","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:21:29Z","timestamp":1783617689000},"page":"e0001490","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Doctors vs. Algorithms: Physicians, too, struggle to learn from evidence that contradicts AI suggestions"],"prefix":"10.1371","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0454-0912","authenticated-orcid":true,"given":"Aranzazu","family":"Vinas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1283-8313","authenticated-orcid":true,"given":"Fernando","family":"Blanco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7221-1366","authenticated-orcid":true,"given":"Helena","family":"Matute","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"issue":"1","key":"pdig.0001490.ref001","doi-asserted-by":"crossref","first-page":"100333","DOI":"10.1016\/j.jik.2023.100333","article-title":"A systematic literature review of artificial intelligence in the healthcare sector: Benefits, challenges, methodologies, and functionalities","volume":"8","author":"O Ali","year":"2023","journal-title":"J Innov Knowl"},{"issue":"1","key":"pdig.0001490.ref002","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1038\/s41698-023-00491-9","article-title":"Cancer drug sensitivity prediction from routine histology images","volume":"8","author":"M Dawood","year":"2024","journal-title":"NPJ Precis Oncol"},{"key":"pdig.0001490.ref003","doi-asserted-by":"crossref","first-page":"117850","DOI":"10.1016\/j.socscimed.2025.117850","article-title":"AI in medical diagnosis: a contextualised study of patient motivations and concerns","volume":"371","author":"N Hajiheydari","year":"2025","journal-title":"Soc Sci Med"},{"key":"pdig.0001490.ref004","doi-asserted-by":"crossref","first-page":"102753","DOI":"10.1016\/j.artmed.2023.102753","article-title":"Diseases diagnosis based on artificial intelligence and ensemble classification","volume":"148","author":"AH Rabie","year":"2024","journal-title":"Artif Intell Med"},{"key":"pdig.0001490.ref005","doi-asserted-by":"crossref","first-page":"117560","DOI":"10.1016\/j.socscimed.2024.117560","article-title":"The role of artificial intelligence in enhancing healthcare for people with disabilities","volume":"364","author":"DB Olawade","year":"2025","journal-title":"Soc Sci Med"},{"issue":"2","key":"pdig.0001490.ref006","doi-asserted-by":"crossref","first-page":"94","DOI":"10.7861\/futurehosp.6-2-94","article-title":"The potential for artificial intelligence in healthcare","volume":"6","author":"T Davenport","year":"2019","journal-title":"Future Healthc J"},{"issue":"5","key":"pdig.0001490.ref007","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1007\/s10462-024-10768-5","article-title":"Revolutionizing personalized medicine with generative AI: a systematic review","volume":"57","author":"I Ghebrehiwet","year":"2024","journal-title":"Artif Intell Rev"},{"key":"pdig.0001490.ref008","doi-asserted-by":"crossref","first-page":"103062","DOI":"10.1016\/j.artmed.2024.103062","article-title":"Training and validating a treatment recommender with partial verification evidence","volume":"160","author":"V Unnikrishnan","year":"2025","journal-title":"Artif Intell Med"},{"issue":"1","key":"pdig.0001490.ref009","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"P Rajpurkar","year":"2022","journal-title":"Nat Med"},{"key":"pdig.0001490.ref010","unstructured":"European Commission. AI Act. Shaping Europe\u2019s digital future. 2024. Accessed 2026 March 9. https:\/\/digital-strategy.ec.europa.eu\/en\/policies\/regulatory-framework-ai"},{"issue":"12","key":"pdig.0001490.ref011","doi-asserted-by":"crossref","first-page":"2293","DOI":"10.1038\/s41562-024-02024-1","article-title":"When combinations of humans and AI are useful: a systematic review and meta-analysis","volume":"8","author":"M Vaccaro","year":"2024","journal-title":"Nat Hum Behav"},{"issue":"1","key":"pdig.0001490.ref012","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1038\/s41746-025-01543-z","article-title":"A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians","volume":"8","author":"H Takita","year":"2025","journal-title":"NPJ Digit Med"},{"key":"pdig.0001490.ref013","doi-asserted-by":"crossref","first-page":"102506","DOI":"10.1016\/j.artmed.2023.102506","article-title":"Rams, hounds and white boxes: investigating human-AI collaboration protocols in medical diagnosis","volume":"138","author":"F Cabitza","year":"2023","journal-title":"Artif Intell Med"},{"issue":"24","key":"pdig.0001490.ref014","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2426153122","article-title":"Human-AI collectives most accurately diagnose clinical vignettes","volume":"122","author":"N Z\u00f6ller","year":"2025","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"6","key":"pdig.0001490.ref015","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pdig.0000278","article-title":"Bias in artificial intelligence algorithms and recommendations for mitigation","volume":"2","author":"LH Nazer","year":"2023","journal-title":"PLOS Digit Health"},{"issue":"3","key":"pdig.0001490.ref016","article-title":"Sources of bias in artificial intelligence that perpetuate healthcare disparities-A global review","volume":"1","author":"LA Celi","year":"2022","journal-title":"PLOS Digit Health"},{"issue":"6","key":"pdig.0001490.ref017","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MIS.2023.3329745","article-title":"Seven pillars for the future of artificial intelligence","volume":"38","author":"E Cambria","year":"2023","journal-title":"IEEE Intell Syst"},{"issue":"1","key":"pdig.0001490.ref018","doi-asserted-by":"crossref","first-page":"3440","DOI":"10.1038\/s41598-024-53303-w","article-title":"The current state of artificial intelligence generative language models is more creative than humans on divergent thinking tasks","volume":"14","author":"KF Hubert","year":"2024","journal-title":"Sci Rep"},{"key":"pdig.0001490.ref019","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1177\/1094670517752459","article-title":"Artificial intelligence in service","volume":"21","author":"M Huang","year":"2018","journal-title":"J Ser Res"},{"key":"pdig.0001490.ref020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s41235-023-00529-3","article-title":"The impact of AI errors in a human-in-the-loop-process","volume":"9","author":"U Agudo","year":"2024","journal-title":"Cogn Res"},{"issue":"1","key":"pdig.0001490.ref021","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1038\/s41398-021-01224-x","article-title":"How machine-learning recommendations influence clinician treatment selections: the example of the antidepressant selection","volume":"11","author":"M Jacobs","year":"2021","journal-title":"Transl Psychiatry"},{"key":"pdig.0001490.ref022","doi-asserted-by":"crossref","first-page":"15737","DOI":"10.1038\/s41598-023-42384-8","article-title":"Humans inherit artificial intelligence biases","volume":"13","author":"L Vicente","year":"2023","journal-title":"Sci Rep"},{"issue":"1","key":"pdig.0001490.ref023","doi-asserted-by":"crossref","first-page":"15915","DOI":"10.1038\/s41598-025-01043-w","article-title":"The combined effect of patient classification systems and availability of resources can bias the judgments of treatment effectiveness","volume":"15","author":"A Vinas","year":"2025","journal-title":"Sci Rep"},{"issue":"1","key":"pdig.0001490.ref024","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1136\/amiajnl-2011-000089","article-title":"Automation bias: a systematic review of frequency, effect mediators, and mitigators","volume":"19","author":"K Goddard","year":"2012","journal-title":"J Am Med Inform Assoc"},{"key":"pdig.0001490.ref025","doi-asserted-by":"crossref","first-page":"78","DOI":"10.4324\/9781003154730-7","article-title":"Confirmation bias\u2013myside bias.","volume-title":"Phol RF, editor. Cognitive illusions","author":"H Mercier","year":"2022"},{"issue":"4","key":"pdig.0001490.ref026","doi-asserted-by":"crossref","first-page":"333","DOI":"10.3758\/s13420-013-0108-8","article-title":"Interactive effects of the probability of the cue and the probability of the outcome on the overestimation of null contingency","volume":"41","author":"F Blanco","year":"2013","journal-title":"Learn Behav"},{"issue":"4","key":"pdig.0001490.ref027","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1177\/074171369904900401","article-title":"Novice to expert: an exploration of how professionals learn","volume":"49","author":"BJ Daley","year":"1999","journal-title":"Adult Education Quarterly"},{"issue":"1","key":"pdig.0001490.ref028","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/(SICI)1520-6858(1999)2:1<32::AID-SYS3>3.0.CO;2-P","article-title":"Expert decision making","volume":"2","author":"RJB Hutton","year":"1999","journal-title":"Syst Engin"},{"issue":"1","key":"pdig.0001490.ref029","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1080\/07421222.1998.11518195","article-title":"Differences between novice and expert systems analysts: what do we know and what do we do?","volume":"15","author":"KD Schenk","year":"1998","journal-title":"J Manage Inform Syst"},{"key":"pdig.0001490.ref030","volume-title":"Simple heuristics that make us smart","author":"ABC Research Group","year":"1999"},{"issue":"4","key":"pdig.0001490.ref031","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1080\/1047840X.2010.520260","article-title":"Intuition: a challenge for psychological research on decision making","volume":"21","author":"RM Hogarth","year":"2010","journal-title":"Psychol Inq"},{"issue":"4","key":"pdig.0001490.ref032","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1007\/s11547-025-01964-6","article-title":"Automation bias in AI-assisted detection of cerebral aneurysms on time-of-flight MR angiography","volume":"130","author":"SH Kim","year":"2025","journal-title":"Radiol Med"},{"key":"pdig.0001490.ref033","first-page":"195","article-title":"The process-performance paradox in expert judgment: How can experts know so much and predict so badly.","volume-title":"Goldstein WM, Hogarth RM, editors. Research on judgment and decision making: currents, connections, and controversies","author":"CF Camerer","year":"1997"},{"issue":"3","key":"pdig.0001490.ref034","doi-asserted-by":"crossref","first-page":"225","DOI":"10.4997\/jrcpe.2018.306","article-title":"Cognitive bias in clinical medicine","volume":"48","author":"ED O\u2019Sullivan","year":"2018","journal-title":"J R Coll Physicians Edinb"},{"issue":"4","key":"pdig.0001490.ref035","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1007\/s11845-020-02235-1","article-title":"Medicine and heuristics: cognitive biases and medical decision-making","volume":"189","author":"DF Whelehan","year":"2020","journal-title":"Ir J Med Sci"},{"key":"pdig.0001490.ref036","doi-asserted-by":"crossref","first-page":"888","DOI":"10.3389\/fpsyg.2015.00888","article-title":"Illusions of causality: how they bias our everyday thinking and how they could be reduced","volume":"6","author":"H Matute","year":"2015","journal-title":"Front Psychol"},{"key":"pdig.0001490.ref037","first-page":"197","article-title":"The influence of attitudes on behavior.","volume-title":"Albarrac\u00edn D, Johnson BT, Zanna MP, editors. The handbook of attitudes, volume 1: Basic principles","author":"I Ajzen","year":"2018"},{"key":"pdig.0001490.ref038","volume-title":"Classifying health workers: Mapping occupations to the international standard classification","author":"World Health Organization","year":"2019"},{"issue":"13","key":"pdig.0001490.ref039","first-page":"2724","article-title":"The General Attitudes towards Artificial Intelligence Scale (GAAIS): confirmatory validation and associations with personality, corporate distrust, and general trust","volume":"39","author":"A Schepman","year":"2023","journal-title":"Int J Hum\u2013Comput Int"},{"key":"pdig.0001490.ref040","volume-title":"Sorting things out. Classification and its consequences","author":"GC Bowker","year":"2000"},{"key":"pdig.0001490.ref041","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1348\/014466604X23491","article-title":"Predictive models of implicit and explicit attitudes","volume":"44","author":"M Perugini","year":"2005","journal-title":"Br J Soc Psychol"},{"key":"pdig.0001490.ref042","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.chb.2018.04.029","article-title":"Toward explicit measures of intention to predict information system use: an exploratory study of the role of implicit attitudes","volume":"86","author":"C Belletier","year":"2018","journal-title":"Comput Hum Behav"},{"issue":"8","key":"pdig.0001490.ref043","doi-asserted-by":"crossref","first-page":"1439","DOI":"10.1007\/s12369-022-00917-7","article-title":"A Cross-Cultural Comparison on Implicit and Explicit Attitudes Towards Artificial Agents","volume":"15","author":"F Diana","year":"2023","journal-title":"Int J Soc Robot"},{"issue":"3","key":"pdig.0001490.ref044","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1109\/THMS.2021.3125280","article-title":"Dissociation between users\u2019 explicit and implicit attitudes toward artificial intelligence: an experimental study","volume":"52","author":"V Fietta","year":"2022","journal-title":"IEEE Trans Human-Mach Syst"},{"key":"pdig.0001490.ref045","doi-asserted-by":"crossref","first-page":"131","DOI":"10.5040\/9780761875857.ch-14","article-title":"Pseudoscience in Contemporary Clinical Psychology. What it is and what we can do about it.","volume-title":"Farha B, editor. Pseudoscience and deception: the smoke and mirrors of paranormal claims","author":"SO Lilienfeld","year":"2013"},{"key":"pdig.0001490.ref046","first-page":"224","article-title":"The self-report method.","volume-title":"Robins RW, Fraley C, editors. Handbook of research methods in personality psychology","author":"DL Paulhus","year":"2007"},{"key":"pdig.0001490.ref047","doi-asserted-by":"crossref","first-page":"4","DOI":"10.21037\/jmai-21-25","article-title":"Factors influencing trust in medical artificial intelligence for healthcare professionals: a narrative review","volume":"5","author":"V Tucci","year":"2022","journal-title":"J Med Artif Intell"},{"issue":"5","key":"pdig.0001490.ref048","doi-asserted-by":"crossref","first-page":"3503","DOI":"10.1007\/s10462-021-10088-y","article-title":"Explainable artificial intelligence: a comprehensive review","volume":"55","author":"D Minh","year":"2022","journal-title":"Artif Intell Rev"},{"issue":"28","key":"pdig.0001490.ref049","doi-asserted-by":"crossref","first-page":"24516","DOI":"10.1007\/s12144-022-03573-2","article-title":"A meta-analysis of the weight of advice in decision-making","volume":"42","author":"PE Bailey","year":"2023","journal-title":"Curr Psychol"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T17:21:36Z","timestamp":1783617696000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001490"}},"subtitle":[],"editor":[{"given":"Po-Chih","family":"Kuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":49,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,9]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001490","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]}}}