{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T01:26:03Z","timestamp":1788312363990,"version":"build-2803163510"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T00:00:00Z","timestamp":1756339200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T00:00:00Z","timestamp":1756339200000},"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":["Sci Rep"],"DOI":"10.1038\/s41598-025-16902-9","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T08:02:55Z","timestamp":1756368175000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["The impact of prompting on ChatGPT\u2019s adherence to status epilepticus treatment guidelines"],"prefix":"10.1038","volume":"15","author":[{"given":"Paulina S. C.","family":"Kliem","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Urs","family":"Fisch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sira M.","family":"Baumann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Berger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon A.","family":"Amacher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabina","family":"Hunziker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raoul","family":"Sutter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,28]]},"reference":[{"key":"16902_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s12028-012-9695-z","volume":"17","author":"GM Brophy","year":"2012","unstructured":"Brophy, G. M. et al. Guidelines for the evaluation and management of status epilepticus. Neurocrit. Care 17, 3\u201323. https:\/\/doi.org\/10.1007\/s12028-012-9695-z (2012).","journal-title":"Neurocrit. Care"},{"key":"16902_CR2","doi-asserted-by":"publisher","first-page":"48","DOI":"10.5698\/1535-7597-16.1.48","volume":"16","author":"T Glauser","year":"2016","unstructured":"Glauser, T. et al. Evidence-based guideline: Treatment of convulsive status epilepticus in children and adults: Report of the guideline committee of the American epilepsy society. Epilepsy Curr. 16, 48\u201361. https:\/\/doi.org\/10.5698\/1535-7597-16.1.48 (2016).","journal-title":"Epilepsy Curr."},{"key":"16902_CR3","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1111\/j.1468-1331.2009.02917.x","volume":"17","author":"H Meierkord","year":"2010","unstructured":"Meierkord, H. et al. EFNS guideline on the management of status epilepticus in adults. Eur. J. Neurol. 17, 348\u2013355. https:\/\/doi.org\/10.1111\/j.1468-1331.2009.02917.x (2010).","journal-title":"Eur. J. Neurol."},{"key":"16902_CR4","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11020435","author":"PSC Kliem","year":"2022","unstructured":"Kliem, P. S. C. et al. First-response ABCDE management of status epilepticus: A prospective high-fidelity simulation study. J. Clin. Med. https:\/\/doi.org\/10.3390\/jcm11020435 (2022).","journal-title":"J. Clin. Med."},{"key":"16902_CR5","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1212\/wnl.0000000000008461","volume":"93","author":"R Sutter","year":"2019","unstructured":"Sutter, R. et al. Emergency management of status epilepticus in a high-fidelity simulation: A prospective study. Neurology 93, 838\u2013848. https:\/\/doi.org\/10.1212\/wnl.0000000000008461 (2019).","journal-title":"Neurology"},{"key":"16902_CR6","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1002\/ana.24986","volume":"82","author":"CE Hill","year":"2017","unstructured":"Hill, C. E., Parikh, A. O., Ellis, C., Myers, J. S. & Litt, B. Timing is everything: Where status epilepticus treatment fails. Ann. Neurol. 82, 155\u2013165. https:\/\/doi.org\/10.1002\/ana.24986 (2017).","journal-title":"Ann. Neurol."},{"key":"16902_CR7","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2023-100978","author":"U Fisch","year":"2024","unstructured":"Fisch, U., Kliem, P., Grzonka, P. & Sutter, R. Performance of large language models on advocating the management of meningitis: A comparative qualitative study. BMJ Health Care Inform. https:\/\/doi.org\/10.1136\/bmjhci-2023-100978 (2024).","journal-title":"BMJ Health Care Inform."},{"key":"16902_CR8","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","volume":"183","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. 183, 589\u2013596. https:\/\/doi.org\/10.1001\/jamainternmed.2023.1838 (2023).","journal-title":"JAMA Intern. Med."},{"key":"16902_CR9","doi-asserted-by":"publisher","DOI":"10.2196\/45312","volume":"9","author":"A Gilson","year":"2023","unstructured":"Gilson, A. et al. How does ChatGPT perform on the united states medical licensing examination (USMLE)? The implications of large language models for medical education and knowledge assessment. JMIR Med. Educ. 9, e45312. https:\/\/doi.org\/10.2196\/45312 (2023).","journal-title":"JMIR Med. Educ."},{"key":"16902_CR10","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230424","volume":"307","author":"HL Haver","year":"2023","unstructured":"Haver, H. L. et al. Appropriateness of breast cancer prevention and screening recommendations provided by ChatGPT. Radiology 307, e230424. https:\/\/doi.org\/10.1148\/radiol.230424 (2023).","journal-title":"Radiology"},{"key":"16902_CR11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198","volume":"2","author":"TH Kung","year":"2023","unstructured":"Kung, T. H. et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digit. Health 2, e0000198. https:\/\/doi.org\/10.1371\/journal.pdig.0000198 (2023).","journal-title":"PLOS Digit. Health"},{"key":"16902_CR12","doi-asserted-by":"publisher","DOI":"10.1101\/2023.01.30.23285067","author":"DM Levine","year":"2023","unstructured":"Levine, D. M. et al. The diagnostic and triage accuracy of the GPT-3 artificial intelligence model. medRxiv https:\/\/doi.org\/10.1101\/2023.01.30.23285067 (2023).","journal-title":"medRxiv"},{"key":"16902_CR13","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180. https:\/\/doi.org\/10.1038\/s41586-023-06291-2 (2023).","journal-title":"Nature"},{"key":"16902_CR14","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1136\/bmj.39003.640567.AE","volume":"333","author":"H Tang","year":"2006","unstructured":"Tang, H. & Ng, J. H. Googling for a diagnosis\u2013use of Google as a diagnostic aid: Internet based study. BMJ 333, 1143\u20131145. https:\/\/doi.org\/10.1136\/bmj.39003.640567.AE (2006).","journal-title":"BMJ"},{"key":"16902_CR15","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.7680","volume":"5","author":"T Russell-Rose","year":"2017","unstructured":"Russell-Rose, T. & Chamberlain, J. Expert search strategies: The information retrieval practices of healthcare information professionals. JMIR Med. Inform. 5, e33. https:\/\/doi.org\/10.2196\/medinform.7680 (2017).","journal-title":"JMIR Med. Inform."},{"key":"16902_CR16","unstructured":"Shryock, T. AI Special Report: What patients and doctors really think about AI in health care. 100 (2023). <https:\/\/www.medicaleconomics.com\/view\/ai-special-report-what-patients-and-doctors-really-think-about-ai-in-health-care>."},{"key":"16902_CR17","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1186\/s12911-025-02996-8","volume":"25","author":"S Saglam","year":"2025","unstructured":"Saglam, S. et al. Comparative evaluation of artificial intelligence models GPT-4 and GPT-3.5 in clinical decision-making in sports surgery and physiotherapy: A cross-sectional study. BMC Med. Inform. Decis. Mak. 25, 163. https:\/\/doi.org\/10.1186\/s12911-025-02996-8 (2025).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"16902_CR18","doi-asserted-by":"publisher","DOI":"10.2196\/53559","volume":"11","author":"J Davis","year":"2024","unstructured":"Davis, J., Van Bulck, L., Durieux, B. N. & Lindvall, C. The temperature feature of ChatGPT: Modifying creativity for clinical research. JMIR Hum. Factors 11, e53559. https:\/\/doi.org\/10.2196\/53559 (2024).","journal-title":"JMIR Hum. Factors"},{"key":"16902_CR19","doi-asserted-by":"publisher","DOI":"10.1101\/2024.04.13.24305773","author":"Y Luo","year":"2025","unstructured":"Luo, Y. et al. The clinical value of ChatGPT for epilepsy presurgical decision making: Systematic evaluation on seizure semiology interpretation. medRxiv https:\/\/doi.org\/10.1101\/2024.04.13.24305773 (2025).","journal-title":"medRxiv"},{"key":"16902_CR20","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","volume":"30","author":"P Hager","year":"2024","unstructured":"Hager, P. et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat. Med. 30, 2613\u20132622. https:\/\/doi.org\/10.1038\/s41591-024-03097-1 (2024).","journal-title":"Nat. Med."},{"key":"16902_CR21","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41746-024-01029-4","volume":"7","author":"L Wang","year":"2024","unstructured":"Wang, L. et al. Prompt engineering in consistency and reliability with the evidence-based guideline for LLMs. NPJ Digit. Med. 7, 41. https:\/\/doi.org\/10.1038\/s41746-024-01029-4 (2024).","journal-title":"NPJ Digit. Med."},{"key":"16902_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J. J. & Wang, V. X. Assessing consistency and reproducibility in the outputs of large language models: Evidence across diverse finance and accounting tasks. (arXiv, 2025).","DOI":"10.2139\/ssrn.5189069"},{"key":"16902_CR23","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1038\/s41746-025-01519-z","volume":"8","author":"YH Ke","year":"2025","unstructured":"Ke, Y. H. et al. Retrieval augmented generation for 10 large language models and its generalizability in assessing medical fitness. NPJ Digit. Med. 8, 187. https:\/\/doi.org\/10.1038\/s41746-025-01519-z (2025).","journal-title":"NPJ Digit. Med."},{"key":"16902_CR24","doi-asserted-by":"publisher","DOI":"10.3390\/medicina60030445","author":"J Miao","year":"2024","unstructured":"Miao, J., Thongprayoon, C., Suppadungsuk, S., Garcia Valencia, O. A. & Cheungpasitporn, W. Integrating retrieval-augmented generation with large language models in nephrology: Advancing practical applications. Medicina (Kaunas) https:\/\/doi.org\/10.3390\/medicina60030445 (2024).","journal-title":"Medicina (Kaunas)"},{"key":"16902_CR25","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1007\/s12020-024-03750-2","volume":"85","author":"MS Deniz","year":"2024","unstructured":"Deniz, M. S. & Guler, B. Y. Assessment of ChatGPT\u2019s adherence to ETA-thyroid nodule management guideline over two different time intervals 14 days apart: In binary and multiple-choice queries. Endocrine 85, 794\u2013802. https:\/\/doi.org\/10.1007\/s12020-024-03750-2 (2024).","journal-title":"Endocrine"},{"key":"16902_CR26","doi-asserted-by":"publisher","DOI":"10.1111\/epi.18215","author":"SA Amacher","year":"2024","unstructured":"Amacher, S. A. et al. Can the large language model ChatGPT-4omni predict outcomes in adult patients with status epilepticus?. Epilepsia https:\/\/doi.org\/10.1111\/epi.18215 (2024).","journal-title":"Epilepsia"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-16902-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-16902-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-16902-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T08:02:58Z","timestamp":1756368178000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-16902-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,28]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["16902"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-16902-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,28]]},"assertion":[{"value":"30 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Simon Amacher is supported by the Mach-Gaensslen Foundation Switzerland and the Nora van Meeuwen-Haefliger Foundation of the University of Basel, Switzerland. Sabina Hunziker is supported by the Swiss National Foundation (SNF) (Ref 10001C_192850\/1 and 10531C_182422), the Gottfried Julia Bangerter-Rhyner Foundation (8472\/HEG-DSV), and the Swiss Society of General Internal Medicine (SSGIM). Raoul Sutter received research grants from the Swiss National Foundation (No 320030_169379), the Research Fund of the University Basel, the Scientific Society Basel, and the Gottfried Julia Bangerter- Rhyner Foundation. He received personal grants from UCB-pharma and holds stocks from Alcon, Johnson & Johnson, Novartis, Roche, and Sandoz. The remaining authors have no disclosures.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Since all prompts were entirely fictional and the only person interacting with ChatGPT-3.5 was PSCK, no ethical approval was deemed necessary. With no participants included in the study, after consulting with regulatory affairs of the Department of Clinical Research of the University of Basel, a study registration was not pursued.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"31712"}}