{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T05:44:09Z","timestamp":1777355049777,"version":"3.51.4"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T00:00:00Z","timestamp":1764892800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"vor","delay-in-days":33,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"publisher","award":["12409"],"award-info":[{"award-number":["12409"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Recent studies have found that physicians with access to a large language model (LLM) chatbot during clinical reasoning tests may score no better to worse compared to the same chatbot performing alone with an input that included the entire clinical case. This study explores how physicians approach using LLM chatbots during clinical reasoning tasks and whether the amount of clinical case content included in the input affects performance. We conducted semi-structured interviews with U.S. physicians on experiences using an LLM chatbot and developed a typology based on input patterns. We then analyzed physician chat logs from two randomized controlled trials, coding each clinical case to an input approach type. Lastly, we used a linear mixed-effects model to compare the case scores of different input approach types. We identified four input approach types based on patterns of content amount: copy-paster (entire case), selective copy-paster (pieces of a case), summarizer (user-generated case summary), and searcher (short queries). Copy-pasting and searching were utilized most. No single type was associated with scoring higher on clinical cases. Other factors such as different prompting strategies, cognitive engagement, and interpretation of the outputs may have more impact and should be explored in future studies.<\/jats:p>","DOI":"10.1038\/s41746-025-02184-y","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T10:16:30Z","timestamp":1764929790000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A typology of physician input approaches to using AI chatbots for clinical decision-making"],"prefix":"10.1038","volume":"9","author":[{"given":"Rachel","family":"Siden","sequence":"first","affiliation":[]},{"given":"Hannah","family":"Kerman","sequence":"additional","affiliation":[]},{"given":"Robert J.","family":"Gallo","sequence":"additional","affiliation":[]},{"given":"Jos\u00e9phine A.","family":"Cool","sequence":"additional","affiliation":[]},{"given":"Jason","family":"Hom","sequence":"additional","affiliation":[]},{"given":"Ethan","family":"Goh","sequence":"additional","affiliation":[]},{"given":"Neera","family":"Ahuja","sequence":"additional","affiliation":[]},{"given":"Paul","family":"Heidenreich","sequence":"additional","affiliation":[]},{"given":"Lisa","family":"Shieh","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jonathan H.","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Adam","family":"Rodman","sequence":"additional","affiliation":[]},{"given":"Laura M.","family":"Holdsworth","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,5]]},"reference":[{"key":"2184_CR1","unstructured":"Hu, K. ChatGPT sets record for fastest-growing user base - analyst note. Reuters https:\/\/www.reuters.com\/technology\/chatgpt-sets-record-fastest-growing-user-base-analyst-note-2023-02-01\/ (2023)."},{"key":"2184_CR2","doi-asserted-by":"crossref","unstructured":"Kisvarday, S. et al. ChatGPT Use Among Pediatric Healthcare Providers (Preprint). JMIR Form Res. 8, e56797 (2024).","DOI":"10.2196\/56797"},{"key":"2184_CR3","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.eururo.2023.10.014","volume":"85","author":"M Eppler","year":"2024","unstructured":"Eppler, M. et al. Awareness and Use of ChatGPT and Large Language Models: A Prospective Cross-sectional Global Survey in Urology. Eur. Urol. 85, 146\u2013153 (2024).","journal-title":"Eur. Urol."},{"key":"2184_CR4","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1001\/jamainternmed.2023.2909","volume":"183","author":"E Strong","year":"2023","unstructured":"Strong, E. et al. Chatbot vs Medical Student Performance on Free-Response Clinical Reasoning Examinations. JAMA Intern. Med. 183, 1028\u20131030 (2023).","journal-title":"JAMA Intern. Med."},{"key":"2184_CR5","doi-asserted-by":"crossref","unstructured":"Lahat, A. et al. Assessing Generative Pretrained Transformers (GPT) in Clinical Decision-Making: Comparative Analysis of GPT-3.5 and GPT-4. J. Med. Internet Res. 26, e54571 (2024).","DOI":"10.2196\/54571"},{"key":"2184_CR6","doi-asserted-by":"crossref","unstructured":"Wang, L. et al. Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs. NPJ Digit. Med. 7, 41 (2024).","DOI":"10.1038\/s41746-024-01029-4"},{"key":"2184_CR7","unstructured":"Zhang, C. et al. One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era. arXiv http:\/\/arxiv.org\/abs\/2304.06488 (2023)."},{"key":"2184_CR8","unstructured":"Muktadir, G. M. D. A Brief History of Prompt: Leveraging Language Models. (Through Advanced Prompting). arXiv https:\/\/www.researchgate.net\/publication\/372830312 (2023)."},{"key":"2184_CR9","doi-asserted-by":"crossref","unstructured":"Mesk\u00f3, B. Prompt Engineering as an Important Emerging Skill for Medical Professionals: Tutorial. J Med. Internet Res. 25, e50638 (2023).","DOI":"10.2196\/50638"},{"key":"2184_CR10","doi-asserted-by":"crossref","unstructured":"Chen, C., Lee, S., Jang, E. & Sundar, S. S. Is Your Prompt Detailed Enough? Exploring the Effects of Prompt Coaching on Users\u2019 Perceptions, Engagement, and Trust in Text-to-Image Generative AI Tools. In ACM International Conference Proceeding Series. Association for Computing Machinery (ACM, 2024).","DOI":"10.1145\/3686038.3686060"},{"key":"2184_CR11","doi-asserted-by":"crossref","unstructured":"Zamfirescu-Pereira, J. D., Wong, R. Y., Hartmann, B. & Yang, Q. Why Johnny Can\u2019t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts. In: Conference on Human Factors in Computing Systems - Proceedings (Association for Computing Machinery, 2023).","DOI":"10.1145\/3544548.3581388"},{"key":"2184_CR12","unstructured":"McDuff, D. et al. Towards Accurate Differential Diagnosis with Large Language Models. http:\/\/arxiv.org\/abs\/2312.00164 (2023)."},{"key":"2184_CR13","doi-asserted-by":"publisher","first-page":"e2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","volume":"7","author":"E Goh","year":"2024","unstructured":"Goh, E. et al. Large Language Model Influence on Diagnostic Reasoning. JAMA Netw. Open 7, e2440969 (2024).","journal-title":"JAMA Netw. Open"},{"key":"2184_CR14","unstructured":"Ayres, L., Knafl, K. A., Fisher, L. & Ransom, D. C. Typological Analysis. In: The SAGE encyclopedia of qualitative research methods. https:\/\/methods.sagepub.com\/ency\/edvol\/sage-encyc-qualitative-research-methods\/chpt\/typological-analysis#_=_ (SAGE Publications, 2008)."},{"key":"2184_CR15","doi-asserted-by":"crossref","unstructured":"Goh, E. et al. GPT-4 assistance for improvement of physician performance on patient care tasks: a randomized controlled trial. Nat. Med. 31, 1233\u20131238 (2025).","DOI":"10.1038\/s41591-024-03456-y"},{"key":"2184_CR16","doi-asserted-by":"crossref","unstructured":"Krupp, L. et al. Unreflected Acceptance -- Investigating the Negative Consequences of ChatGPT-Assisted Problem Solving in Physics Education. http:\/\/arxiv.org\/abs\/2309.03087 (2023).","DOI":"10.3233\/FAIA240195"},{"key":"2184_CR17","doi-asserted-by":"crossref","unstructured":"Khurana, A., Subramonyam, H. & Chilana, P. K. Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking. In: ACM International Conference Proceeding Series. Association for Computing Machinery, 288\u2013303.(ACM, 2024).","DOI":"10.1145\/3640543.3645200"},{"key":"2184_CR18","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1111\/j.1365-2923.1987.tb00673.x","volume":"21","author":"RH JONES","year":"1987","unstructured":"JONES, R. H. Data collection in decision-making: a study in general practice. Med Educ. 21, 99\u2013104 (1987).","journal-title":"Med Educ."},{"key":"2184_CR19","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1080\/01421590500084818","volume":"27","author":"MR Nendaz","year":"2005","unstructured":"Nendaz, M. R. et al. Common strategies in clinical data collection displayed by experienced clinician-teachers in internal medicine. Med Teach. 27, 415\u2013421 (2005).","journal-title":"Med Teach."},{"key":"2184_CR20","unstructured":"Du, X. et al. Generative Large Language Models in Electronic Health Records for Patient Care Since 2023: A Systematic Review. medRxiv http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/39228726 (2024)."},{"key":"2184_CR21","doi-asserted-by":"crossref","unstructured":"Vrdoljak, J., Boban, Z., Vilovi\u0107, M., Kumri\u0107, M. & Bo\u017ei\u0107, J. A Review of Large Language Models in Medical Education, Clinical Decision Support, and Healthcare Administration. Healthcare 13, 603 (2025).","DOI":"10.3390\/healthcare13060603"},{"key":"2184_CR22","unstructured":"Kerman, H. et al. \u201cI double checked it with my own knowledge:\u201d Physician perspectives on the use of AI chatbots for clinical decision making (2025). [Manuscript submitted for publication.]"},{"key":"2184_CR23","doi-asserted-by":"crossref","unstructured":"Barman, K. G., Wood, N. & Pawlowski, P. Beyond transparency and explainability: on the need for adequate and contextualized user guidelines for LLM use. Ethics Inf. Technol. 26, 47 (2024).","DOI":"10.1007\/s10676-024-09778-2"},{"key":"2184_CR24","doi-asserted-by":"crossref","unstructured":"Patel, D. et al. Evaluating prompt engineering on GPT-3.5\u2019s performance in USMLE-style medical calculations and clinical scenarios generated by GPT-4. Sci. Rep. 14, 17341 (2024).","DOI":"10.1038\/s41598-024-66933-x"},{"key":"2184_CR25","doi-asserted-by":"crossref","unstructured":"Shah K. et al. Large Language Model Prompting Techniques for Advancement in Clinical Medicine. J. Clin. Med. 13, 5101 (2024).","DOI":"10.3390\/jcm13175101"},{"key":"2184_CR26","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-13-117","volume":"13","author":"NK Gale","year":"2013","unstructured":"Gale, N. K., Heath, G., Cameron, E., Rashid, S. & Redwood, S. Using the framework method for the analysis of qualitative data in multi-disciplinary health research. BMC Med. Res. Methodol. 13, 117 (2013).","journal-title":"BMC Med. Res. Methodol."},{"key":"2184_CR27","unstructured":"Ritchie, J. & Lewis, J. eds. Qualitative Research Practice: A Guide for Social Science Students and Researchers (SAGE Publications; 2003)."},{"key":"2184_CR28","doi-asserted-by":"crossref","unstructured":"Ogden, S. N. et al. \u201cYou need money to get high, and that\u2019s the easiest and fastest way:\u201d A typology of sex work and health behaviours among people who inject drugs. Int. J. Drug Policy 96, 103285 (2021).","DOI":"10.1016\/j.drugpo.2021.103285"},{"key":"2184_CR29","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1111\/hae.12543","volume":"21","author":"SJ Lane","year":"2015","unstructured":"Lane, S. J. et al. Treatment decision-making among Canadian youth with severe haemophilia: A qualitative approach. Haemophilia 21, 180\u2013189 (2015).","journal-title":"Haemophilia"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02184-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02184-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02184-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T14:26:12Z","timestamp":1767795972000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02184-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,5]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2184"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02184-y","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,5]]},"assertion":[{"value":"16 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"J.H. reports: Being an advisor for Cognita Imaging and having equity options. J.C. has received additional research funding support in part by: NIH\/National Institute of Allergy and Infectious Diseases (1R01AI17812101); NIH-NCATS-Clinical & Translational Science Award (UM1TR004921); NIH\/National Institute on Drug Abuse Clinical Trials Network (UG1DA015815 - CTN-0136); Stanford Bio-X Interdisciplinary Initiatives Seed Grants Program (IIP) [R12] [JHC]; NIH\/Center for Undiagnosed Diseases at Stanford (U01 NS134358); Stanford Institute for Human-Centered Artificial Intelligence (HAI); Stanford RAISE Health Seed Grant 2024; Josiah Macy Jr. Foundation (AI in Medical Education). J.C. reports being: Co-founder of Reaction Explorer LLC that develops and licenses organic chemistry education software; Paid medical expert witness fees from Sutton Pierce, Younker Hyde MacFarlane, Sykes McAllister, and Elite Experts; Paid consulting fees from ISHI Health; Paid honoraria or travel expenses for invited presentations by General Reinsurance Corporation, Cozeva, and other industry conferences, academic institutions, and health systems. A.R. reports additional research funding paid in part by: Josiah Jr. Macy Foundation (P25-04). A.R. reports being: A part-time visiting researcher at Google. All other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"14"}}