{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T23:50:19Z","timestamp":1792108219867,"version":"4.4.0"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Acad Psychiatry"],"DOI":"10.1007\/s40596-026-02450-5","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T23:22:09Z","timestamp":1792106529000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From Model to Product: Understanding and Teaching AI Evidence"],"prefix":"10.1007","author":[{"given":"Matthew","family":"Flathers","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phuong Anh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haruka","family":"Notsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"Herpertz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean J.","family":"Ryan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5362-7937","authenticated-orcid":false,"given":"John","family":"Torous","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"key":"2450_CR1","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2025.1659134","volume":"7","author":"Y Artsi","year":"2025","unstructured":"Artsi Y, Sorin V, Glicksberg BS, Korfiatis P, Nadkarni GN, Klang E. Large language models in real-world clinical workflows: a systematic review of applications and implementation. Front Digit Health. 2025;7:1659134.","journal-title":"Front Digit Health"},{"key":"2450_CR2","doi-asserted-by":"crossref","unstructured":"Tierney AA, Gayre G, Hoberman B, Mattern B, Ballesca M, Kipnis P, et al. Ambient artificial intelligence scribes to alleviate the burden of clinical documentation. NEJM Catalyst Innovations in Care Delivery. 2024 Feb 21;5(3):CAT-23.","DOI":"10.1056\/CAT.23.0404"},{"key":"2450_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104620","volume":"151","author":"Q Wei","year":"2024","unstructured":"Wei Q, Yao Z, Cui Y, Wei B, Jin Z, Xu X. Evaluation of ChatGPT-generated medical responses: a systematic review and meta-analysis. J Biomed Inform. 2024;151:104620.","journal-title":"J Biomed Inform"},{"issue":"2","key":"2450_CR4","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1093\/jamia\/ocae294","volume":"32","author":"RJ Gallo","year":"2025","unstructured":"Gallo RJ, Baiocchi M, Savage TR, Chen JH. Establishing best practices in large language model research: an application to repeat prompting. J Am Med Inform Assoc. 2025;32(2):386\u201390.","journal-title":"J Am Med Inform Assoc"},{"issue":"4","key":"2450_CR5","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1038\/s41591-024-03456-y","volume":"31","author":"E Goh","year":"2025","unstructured":"Goh E, Gallo RJ, Strong E, Weng Y, Kerman H, Freed JA, et al. GPT-4 assistance for improvement of physician performance on patient care tasks: a randomized controlled trial. Nat Med. 2025;31(4):1233\u20138.","journal-title":"Nat Med"},{"issue":"4","key":"2450_CR6","doi-asserted-by":"publisher","DOI":"10.3390\/jpm15040160","volume":"15","author":"D Mikhail","year":"2025","unstructured":"Mikhail D, Milad D, Antaki F, Milad J, Farah A, Khairy T, et al. Multimodal performance of GPT-4 in complex ophthalmology cases. J Pers Med. 2025;15(4):160.","journal-title":"J Pers Med"},{"issue":"3","key":"2450_CR7","doi-asserted-by":"publisher","DOI":"10.1002\/lrh2.10438","volume":"8","author":"GW Rutledge","year":"2024","unstructured":"Rutledge GW. Diagnostic accuracy of GPT\u20104 on common clinical scenarios and challenging cases. Learn Health Syst. 2024;8(3):e10438.","journal-title":"Learn Health Syst"},{"key":"2450_CR8","unstructured":"OpenAI. Safety best practices [Internet]. San Francisco (CA): OpenAI; [last accessed 2026 Aug 1]. Available from: https:\/\/developers.openai.com\/api\/docs\/guides\/safety-best-practices"},{"key":"2450_CR9","unstructured":"OpenAI. Model spec (2025\/12\/18) [Internet]. San Francisco (CA): OpenAI; 2025 Dec 18 [last accessed 2026 Apr 28]. Available from: https:\/\/model-spec.openai.com\/2025-12-18.html"},{"key":"2450_CR10","unstructured":"Anthropic. Protecting the wellbeing of our users [Internet]. San Francisco (CA): Anthropic; 2025 Dec 18 [last accessed 2026 Apr 28]. Available from: https:\/\/www.anthropic.com\/news\/protecting-well-being-of-users"},{"key":"2450_CR11","unstructured":"Anthropic. Claude Opus 4.6 system card [Internet]. San Francisco (CA): Anthropic; 2026 Feb [last accessed 2026 Aug 1]. Available from: https:\/\/www.anthropic.com\/document\/claude-opus-4-6-system-card."},{"key":"2450_CR12","unstructured":"Anthropic. System prompts [Internet]. San Francisco (CA): Anthropic; [last accessed 2026 Aug 1]. Available from: https:\/\/platform.claude.com\/docs\/en\/release-notes\/system-prompts"},{"key":"2450_CR13","unstructured":"Korom R, Kiptinness S, Adan N, Said K, Ithuli C, Rotich O, et al. AI-based clinical decision support for primary care: a real-world study. arXiv preprint arXiv:2507.16947. 2025 Jul 22."},{"key":"2450_CR14","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.5317da47","author":"L Chen","year":"2024","unstructured":"Chen L, Zaharia M, Zou J. How is ChatGPT\u2019s behavior changing over time? Harvard Data Sci Rev. 2024. https:\/\/doi.org\/10.1162\/99608f92.5317da47.","journal-title":"Harvard Data Sci Rev"},{"key":"2450_CR15","doi-asserted-by":"crossref","unstructured":"Wu W, Xu X, Gao C, Diao X, Li S, Salas LA, et al. Assessing and mitigating medical knowledge drift and conflicts in large language models. In: Findings of the association for computational linguistics: EMNLP 2025. Suzhou (China): Association for Computational Linguistics; 2025. p. 707\u201330.","DOI":"10.18653\/v1\/2025.findings-emnlp.38"},{"key":"2450_CR16","doi-asserted-by":"publisher","first-page":"e69534","DOI":"10.2196\/69534","volume":"17","author":"A Parks","year":"2025","unstructured":"Parks A, Travers E, Perera-Delcourt R, Major M, Economides M, Mullan P. Is this chatbot safe and evidence-based? A call for the critical evaluation of generative AI mental health chatbots. J Particip Med. 2025;17:e69534.","journal-title":"J Particip Med"},{"issue":"3","key":"2450_CR17","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1002\/wps.21352","volume":"24","author":"Y Hua","year":"2025","unstructured":"Hua Y, Siddals S, Ma Z, Galatzer\u2010Levy I, Xia W, Hau C, et al. Charting the evolution of artificial intelligence mental health chatbots from rule\u2010based systems to large language models: a systematic review. World Psychiatry. 2025;24(3):383\u201394.","journal-title":"World Psychiatry"},{"key":"2450_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.landig.2025.100974","author":"M Flathers","year":"2026","unstructured":"Flathers M, Roux S, Torous J. Beyond artificial intelligence psychosis: a functional typology of large language model-associated psychotic phenomena. Lancet Digit Health. 2026. https:\/\/doi.org\/10.1016\/j.landig.2025.100974.","journal-title":"Lancet Digit Health"},{"issue":"9","key":"2450_CR19","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1038\/s41591-020-1034-x","volume":"26","author":"X Liu","year":"2020","unstructured":"Liu X, Cruz Rivera S, Moher D, Calvert MJ, Denniston AK, Chan AW, et al. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat Med. 2020Sep;26(9):1364\u201374.","journal-title":"Nat Med"},{"key":"2450_CR20","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2022-070904","author":"B Vasey","year":"2022","unstructured":"Vasey B, Nagendran M, Campbell B, Clifton DA, Collins GS, Denaxas S, et al. Reporting guideline for the early stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. BMJ. 2022. https:\/\/doi.org\/10.1136\/bmj-2022-070904.","journal-title":"BMJ"},{"issue":"390","key":"2450_CR21","volume":"1","author":"The CHART Collaborative","year":"2025","unstructured":"The CHART Collaborative. Reporting guidelines for chatbot health advice studies: explanation and elaboration for the Chatbot Assessment Reporting Tool (CHART). The BMJ. 2025Aug;1(390):e083305.","journal-title":"The BMJ"}],"container-title":["Academic Psychiatry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40596-026-02450-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40596-026-02450-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40596-026-02450-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T23:22:11Z","timestamp":1792106531000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40596-026-02450-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,15]]},"references-count":21,"alternative-id":["2450"],"URL":"https:\/\/doi.org\/10.1007\/s40596-026-02450-5","relation":{},"ISSN":["1042-9670","1545-7230"],"issn-type":[{"value":"1042-9670","type":"print"},{"value":"1545-7230","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,15]]},"assertion":[{"value":"2 June 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This work did not involve human subjects, animal subjects, or identifiable patient data. Ethics committee approval was not required. The illustrative messages sent to the model in the example described in the manuscript were authored by the study team and contained no patient information.","order":1,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","label":"Disclosures","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors used a large language model (Anthropic Claude, accessed via\n                      Claude.ai\n                      and Claude Code) to assist with copyediting and proofreading of author-written text and to generate the code (HTML\/CSS) used to lay out and render Figs.\u00a0\n                      \n                      and\n                      \n                      . The content of both figures was authored or collected by the authors; no AI-generated images were used. No scientific content, argument, or reference was generated by AI. All AI-assisted output was reviewed and edited by the authors, who take full responsibility for the manuscript. Separately, and as described in the manuscript, Claude Opus 4.6 was the object of the illustrative comparison in Fig.\u00a0\n                      \n                      and its outputs are reproduced as study material, not as authored text.","order":3,"name":"Ethics","label":"Use of Generative AI and AI-Assisted Technologies","group":{"name":"EthicsHeading","label":"Declarations"}}]}}