{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T10:05:48Z","timestamp":1784541948053,"version":"3.55.0"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-025-01792-y","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T09:04:10Z","timestamp":1753175050000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Pitfalls of large language models in medical ethics reasoning"],"prefix":"10.1038","volume":"8","author":[{"given":"Shelly","family":"Soffer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vera","family":"Sorin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Girish N.","family":"Nadkarni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eyal","family":"Klang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,22]]},"reference":[{"key":"1792_CR1","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/0010-0277(74)90017-1","volume":"3","author":"PC Wason","year":"1974","unstructured":"Wason, P. C. & Evans, St J. B. T. Dual processes in reasoning?. Cognition 3, 141\u2013154 (1974).","journal-title":"Cognition"},{"key":"1792_CR2","unstructured":"Kahneman, D. Thinking, Fast and Slow (Farrar, Straus and Giroux, 2011)."},{"key":"1792_CR3","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1177\/1745691612460685","volume":"8","author":"StJBT Evans","year":"2013","unstructured":"Evans, St J. B. T. & Stanovich, K. E. Dual-process theories of higher cognition: advancing the debate. Perspect. Psychol. Sci. 8, 223\u2013241 (2013).","journal-title":"Perspect. Psychol. Sci."},{"key":"1792_CR4","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1177\/1745691613483474","volume":"8","author":"G Keren","year":"2013","unstructured":"Keren, G. A tale of two systems: a scientific advance or a theoretical stone soup? Commentary on Evans & Stanovich (2013). Perspect. Psychol. Sci. 8, 287\u2013292 (2013).","journal-title":"Perspect. Psychol. Sci."},{"key":"1792_CR5","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1038\/s43588-023-00527-x","volume":"3","author":"T Hagendorff","year":"2023","unstructured":"Hagendorff, T., Fabi, S. & Kosinski, M. Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in ChatGPT. Nat. Comput. Sci. 3, 833\u2013838 (2023).","journal-title":"Nat. Comput. Sci."},{"key":"1792_CR6","unstructured":"Biderman, S. et al. Emergent and predictable memorization in large language models. Preprint at https:\/\/arxiv.org\/abs\/2304.11158 (2023)."},{"key":"1792_CR7","unstructured":"McKenzie, I. R. et al. Inverse scaling: When bigger isn\u2019t better. Preprint at https:\/\/arxiv.org\/abs\/2306.09479 (2023)."},{"key":"1792_CR8","unstructured":"OpenAI. Introducing OpenAI o3. OpenAI. https:\/\/openai.com\/index\/introducing-o3-and-o4-mini\/ (2025)."},{"key":"1792_CR9","doi-asserted-by":"publisher","first-page":"1921","DOI":"10.1093\/jamia\/ocae103","volume":"31","author":"BS Glicksberg","year":"2024","unstructured":"Glicksberg, B. S. et al. Evaluating the accuracy of a state-of-the-art large language model for prediction of admissions from the emergency room. Am. Med. Inform. Assoc. 31, 1921\u20131928 (2024).","journal-title":"Am. Med. Inform. Assoc."},{"key":"1792_CR10","doi-asserted-by":"publisher","first-page":"e662","DOI":"10.1016\/S2589-7500(24)00124-9","volume":"6","author":"O Freyer","year":"2024","unstructured":"Freyer, O. et al. A future role for health applications of large language models depends on regulators enforcing safety standards. Lancet Digit. Health 6, e662\u2013e672 (2024).","journal-title":"Lancet Digit. Health"},{"key":"1792_CR11","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.22399","volume":"7","author":"WR Small","year":"2024","unstructured":"Small, W. R. et al. Large language model\u2013based responses to patients\u2019 In-Basket messages. JAMA Netw. Open. 7, e2422399 (2024).","journal-title":"JAMA Netw. Open."},{"key":"1792_CR12","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","volume":"1838","author":"JW Ayers","year":"2023","unstructured":"Ayers, J. W. et al. Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern. Med. 1838, 589\u2013596 (2023).","journal-title":"JAMA Intern. Med."},{"key":"1792_CR13","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1080\/15265161.2023.2233358","volume":"23","author":"V Rahimzadeh","year":"2023","unstructured":"Rahimzadeh, V., Kostick-Quenet, K., Blumenthal-Barby, J. & McGuire, A. L. Ethics education for healthcare professionals in the era of ChatGPT and other large language models: Do we still need it?. Am. J. Bioeth. 23, 17\u201327 (2023).","journal-title":"Am. J. Bioeth."},{"key":"1792_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-06801-y","volume":"25","author":"S Okamoto","year":"2025","unstructured":"Okamoto, S., Kataoka, M., Itano, M. & Sawai, T. AI-based medical ethics education: examining the potential of large language models as a tool for virtue cultivation. BMC Med. Educ. 25, 185 (2025).","journal-title":"BMC Med. Educ."},{"key":"1792_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-86510-0","volume":"15","author":"D Dillion","year":"2025","unstructured":"Dillion, D., Mondal, D., Tandon, N. & Gray, K. AI language model rivals expert ethicist in perceived moral expertise. Sci. Rep. 15, 4084 (2025).","journal-title":"Sci. Rep."},{"key":"1792_CR16","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1038\/s42256-024-00969-6","volume":"7","author":"L Jiang","year":"2025","unstructured":"Jiang, L. et al. Investigating machine moral judgement through the Delphi experiment. Nat. Mach. Intell. 7, 145\u2013160 (2025).","journal-title":"Nat. Mach. Intell."},{"key":"1792_CR17","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1080\/15265161.2023.2296402","volume":"24","author":"BD Earp","year":"2024","unstructured":"Earp, B. D. et al. A personalized patient preference predictor for substituted judgments in healthcare: technically feasible and ethically desirable. Am. J. Bioeth. 24, 13\u201326 (2024).","journal-title":"Am. J. Bioeth."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01792-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01792-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01792-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T16:05:37Z","timestamp":1757261137000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01792-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,22]]},"references-count":17,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1792"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01792-y","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,22]]},"assertion":[{"value":"21 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"461"}}