{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T18:51:37Z","timestamp":1791312697601,"version":"4.3.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Horizon Europe grant for the SPIDERR project","award":["101080711"],"award-info":[{"award-number":["101080711"]}]},{"name":"Horizon Europe grant for the SPIDERR project","award":["101080711"],"award-info":[{"award-number":["101080711"]}]},{"DOI":"10.13039\/501100014842","name":"Deutsche Rheumastiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014842","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Med Syst"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Patients with rheumatic diseases have persistent information needs that are not fully addressed in routine care. We developed and evaluated guideline-grounded, large language model (LLM) chatbots to support patient self-management and education in rheumatology.<\/jats:p>\n                  <jats:p>Ten disease-specific chatbots based on German guidelines were co-developed and deployed through 13 rheumatology centres and six patient organisations. Chatbot users rated responses and completed a questionnaire. User questions, feedback, and response characteristics were analysed using category-based coding and a six-dimensional LLM-as-a-judge assessment, with LLM-based ratings compared with rheumatologist ratings in random subsets.<\/jats:p>\n                  <jats:p>Between September 2025 and January 2026, 6291 questions were recorded. Thirteen question categories were identified, most commonly disease-specific questions (50.2%), medication and monitoring (37.3%) and diagnostics (28.2%). The chatbots were unable to answer in 263 interactions (4.2%). Of 2671 responses rated by users, 2481 (92.9%) received a positive rating. Insufficient detail was the most common reason for negative ratings (125\/190, 65.8%). Among 602 questionnaire respondents, 84.6% reported that the chatbot was easy to use, 84.1% that answers were easy to understand, and 80.2% that it was a useful addition to patient education. In the LLM-based evaluation, 95.3% of answers were rated as completely safe and 79.1% as completely correct. Guideline adherence was assessed separately, with 45.0% rated as fully adherent; agreement with physician assessment was weak.<\/jats:p>\n                  <jats:p>Guideline-grounded chatbots received predominantly positive user feedback in real-world use, while LLM-based evaluation suggested that most responses were safe and correct. User questions and feedback may help guide iterative improvements to source content and patient education materials. Further studies are needed to evaluate educational effectiveness and independently validate response quality and clinical safety.<\/jats:p>","DOI":"10.1007\/s10916-026-02470-6","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T01:26:22Z","timestamp":1791163582000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and Nationwide Multicentre Evaluation of Guideline-Grounded Large Language Model Chatbots to Support Patient Self-Management and Education in Rheumatology"],"prefix":"10.1007","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2400-2840","authenticated-orcid":false,"given":"Tim","family":"Wilhelmi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6029-2103","authenticated-orcid":false,"given":"Vanessa","family":"Bartsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marius","family":"Platt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asarnusch","family":"Rashid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Hornig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Krusche","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Axel J","family":"Hueber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Fink","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Pfeil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriel","family":"Dischereit","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Therese","family":"Holzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ulrich","family":"Drott","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peer","family":"Aries","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Max","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"B\u00f6hm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harriet","family":"Morf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannah","family":"Labinsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"M\u00fchlensiepen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego","family":"Benavent","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Kuhn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7911-4235","authenticated-orcid":false,"given":"Philipp","family":"Klemm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9695-0657","authenticated-orcid":false,"given":"Johannes","family":"Knitza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"2470_CR1","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1016\/j.semarthrit.2018.07.001","volume":"48","author":"K Connelly","year":"2019","unstructured":"Connelly K, Segan J, Lu A et al (2019) Patients\u2019 perceived health information needs in inflammatory arthritis: a systematic review. Semin Arthritis Rheum 48:900\u2013910. https:\/\/doi.org\/10.1016\/j.semarthrit.2018.07.001","journal-title":"Semin Arthritis Rheum"},{"key":"2470_CR2","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1136\/annrheumdis-2014-206807","volume":"74","author":"HA Zangi","year":"2015","unstructured":"Zangi HA, Ndosi M, Adams J et al (2015) EULAR recommendations for patient education for people with inflammatory arthritis. Ann Rheum Dis 74:954\u2013962. https:\/\/doi.org\/10.1136\/annrheumdis-2014-206807","journal-title":"Ann Rheum Dis"},{"key":"2470_CR3","doi-asserted-by":"publisher","first-page":"7071","DOI":"10.3390\/ijerph19127071","volume":"19","author":"C Becker","year":"2022","unstructured":"Becker C, Diener M, Hueber AJ et al (2022) Unmet information needs of patients with rheumatic diseases: results of a cross-sectional online survey study in Germany. Int J Environ Res Public Health 19:7071. https:\/\/doi.org\/10.3390\/ijerph19127071","journal-title":"Int J Environ Res Public Health"},{"key":"2470_CR4","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/s00393-024-01584-x","volume":"84","author":"L Schuster","year":"2025","unstructured":"Schuster L, Henes J, Diener M et al (2025) Measurement of disease-related knowledge of patients with axial spondyloarthritis\u2014development and application of the G-ASKQ7 questionnaire. Z Rheumatol 84:404\u2013409. https:\/\/doi.org\/10.1007\/s00393-024-01584-x","journal-title":"Z Rheumatol"},{"key":"2470_CR5","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1080\/03009742.2025.2463734","volume":"54","author":"LR Knudsen","year":"2025","unstructured":"Knudsen LR, Knitza J, M\u00fchlensiepen F et al (2025) Development and validation of a patient knowledge questionnaire for rheumatoid arthritis (PKQ-RA-11) in Danish and German. Scand J Rheumatol 54:166\u2013174. https:\/\/doi.org\/10.1080\/03009742.2025.2463734","journal-title":"Scand J Rheumatol"},{"key":"2470_CR6","doi-asserted-by":"publisher","first-page":"rkaf083","DOI":"10.1093\/rap\/rkaf083","volume":"9","author":"E Wang","year":"2025","unstructured":"Wang E, Smith J, Katz S et al (2025) Adoption and perception of LLM-based chatbots in health care: an exploratory cross-sectional survey of individuals with rheumatic diseases. Rheumatol Adv Pract 9:rkaf083. https:\/\/doi.org\/10.1093\/rap\/rkaf083","journal-title":"Rheumatol Adv Pract"},{"key":"2470_CR7","doi-asserted-by":"publisher","unstructured":"Labinsky H, Klemm P, Graalmann L et al (2025) Patient experiences, attitudes, and profiles regarding artificial intelligence in rheumatology: a German national cross-sectional survey study. Rheumatol Int 45. https:\/\/doi.org\/10.1007\/s00296-025-06023-x","DOI":"10.1007\/s00296-025-06023-x"},{"key":"2470_CR8","doi-asserted-by":"publisher","first-page":"e238","DOI":"10.1016\/S2665-9913(25)00370-4","volume":"8","author":"Z Karakikla-Mitsakou","year":"2026","unstructured":"Karakikla-Mitsakou Z, Cornet A, Andersen J et al (2026) LupusGPT: an AI-driven information model for patients with systemic lupus erythematosus. Lancet Rheumatol 8:e238\u2013e242. https:\/\/doi.org\/10.1016\/S2665-9913(25)00370-4","journal-title":"Lancet Rheumatol"},{"key":"2470_CR9","doi-asserted-by":"publisher","first-page":"e196","DOI":"10.1016\/S2665-9913(24)00056-0","volume":"6","author":"I Haase","year":"2024","unstructured":"Haase I, Xiong T, Rissmann A, Knitza J, Greenfield J, Krusche M (2024) ChatSLE: consulting ChatGPT-4 for 100 frequently asked lupus questions. Lancet Rheumatol 6:e196\u2013e199. https:\/\/doi.org\/10.1016\/S2665-9913(24)00056-0","journal-title":"Lancet Rheumatol"},{"key":"2470_CR10","doi-asserted-by":"publisher","first-page":"2450","DOI":"10.1093\/rheumatology\/keae238","volume":"63","author":"D Xu","year":"2024","unstructured":"Xu D, Zhao J, Liu R et al (2024) ChatGPT-4\u2019s proficiency in addressing patients\u2019 questions on systemic lupus erythematosus: a blinded comparative study with specialists. Rheumatology (Oxford) 63:2450\u20132456. https:\/\/doi.org\/10.1093\/rheumatology\/keae238","journal-title":"Rheumatology (Oxford)"},{"key":"2470_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ard.2025.11.012","author":"G Forte","year":"2025","unstructured":"Forte G, Mauro D, Raimondi M et al (2025) ChatGPT vs rheumatologists: cross-sectional study on accuracy and patient perception of AI-generated information for psoriatic arthritis. Ann Rheum Dis. https:\/\/doi.org\/10.1016\/j.ard.2025.11.012","journal-title":"Ann Rheum Dis"},{"key":"2470_CR12","doi-asserted-by":"publisher","first-page":"e70124","DOI":"10.1111\/1756-185X.70124","volume":"28","author":"F Lechner","year":"2025","unstructured":"Lechner F, Kuhn S, Knitza J (2025) Harnessing large language models for rheumatic disease diagnosis: advancing hybrid care and task shifting. Int J Rheum Dis 28:e70124. https:\/\/doi.org\/10.1111\/1756-185X.70124","journal-title":"Int J Rheum Dis"},{"key":"2470_CR13","doi-asserted-by":"publisher","DOI":"10.4135\/9781036212940","volume-title":"Qualitative Content Analysis: Methods, Practice and Software","author":"U Kuckartz","year":"2023","unstructured":"Kuckartz U, R\u00e4diker S (2023) Qualitative Content Analysis: Methods, Practice and Software, 2nd edn. SAGE, London.","edition":"2"},{"key":"2470_CR14","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1038\/s41746-025-02022-1","volume":"8","author":"T Thesen","year":"2025","unstructured":"Thesen T, Park SH (2025) A generative AI teaching assistant for personalized learning in medical education. npj Digit Med 8:627. https:\/\/doi.org\/10.1038\/s41746-025-02022-1","journal-title":"npj Digit Med"},{"key":"2470_CR15","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1038\/s41746-025-02166-0","volume":"8","author":"Y Hao","year":"2025","unstructured":"Hao Y, Holmes J, Waddle MR et al (2025) Personalizing prostate cancer education for patients using an EHR-integrated LLM agent. npj Digit Med 8:770. https:\/\/doi.org\/10.1038\/s41746-025-02166-0","journal-title":"npj Digit Med"},{"key":"2470_CR16","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1348\/000711006X126600","volume":"61","author":"KL Gwet","year":"2008","unstructured":"Gwet KL (2008) Computing inter-rater reliability and its variance in the presence of high agreement. Br J Math Stat Psychol 61:29\u201348. https:\/\/doi.org\/10.1348\/000711006X126600","journal-title":"Br J Math Stat Psychol"},{"key":"2470_CR17","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/0895-4356(90)90158-L","volume":"43","author":"AR Feinstein","year":"1990","unstructured":"Feinstein AR, Cicchetti DV (1990) High agreement but low kappa: I. The problems of two paradoxes. J Clin Epidemiol 43:543\u2013549. https:\/\/doi.org\/10.1016\/0895-4356(90)90158-L","journal-title":"J Clin Epidemiol"},{"key":"2470_CR18","volume-title":"Handbook of Inter-Rater Reliability: The Definitive Guide to Measuring the Extent of Agreement Among Raters","author":"KL Gwet","year":"2014","unstructured":"Gwet KL (2014) Handbook of Inter-Rater Reliability: The Definitive Guide to Measuring the Extent of Agreement Among Raters, 4th edn. Advanced Analytics, LLC, Gaithersburg","edition":"4"},{"key":"2470_CR19","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"33","author":"JR Landis","year":"1977","unstructured":"Landis JR, Koch GG (1977) The measurement of observer agreement for categorical data. Biometrics 33:159\u2013174. https:\/\/doi.org\/10.2307\/2529310","journal-title":"Biometrics"},{"key":"2470_CR20","doi-asserted-by":"publisher","first-page":"e2333511","DOI":"10.1001\/jamanetworkopen.2023.33511","volume":"6","author":"SA Graham","year":"2023","unstructured":"Graham SA, Pickus SK, Lockwood KG, Buch LS, Dunn P, Paruthi J (2023) Business vs after-hours use of an artificial intelligence-powered digital health platform among insured patients. JAMA Netw Open 6:e2333511. https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.33511","journal-title":"JAMA Netw Open"},{"key":"2470_CR21","doi-asserted-by":"publisher","first-page":"e20549","DOI":"10.2196\/20549","volume":"22","author":"KE Morse","year":"2020","unstructured":"Morse KE, Ostberg NP, Jones VG, Chan AS (2020) Use characteristics and triage acuity of a digital symptom checker in a large integrated health system: population-based descriptive study. J Med Internet Res 22:e20549. https:\/\/doi.org\/10.2196\/20549","journal-title":"J Med Internet Res"},{"key":"2470_CR22","doi-asserted-by":"publisher","first-page":"109393","DOI":"10.1016\/j.surg.2025.109393","volume":"183","author":"L Garcia Garcia","year":"2025","unstructured":"Garcia Garcia L, Emile SH, Linkeshwaran L, Wignakumar A, Wexner SD (2025) A literature review on the role of artificial intelligence-based chatbots in patient education in colorectal surgery. Surgery 183:109393. https:\/\/doi.org\/10.1016\/j.surg.2025.109393","journal-title":"Surgery"},{"key":"2470_CR23","doi-asserted-by":"publisher","unstructured":"Lumma F, Knitza J, M\u00fchlensiepen F (2025) Potentials and barriers of digital patient education in rheumatic disease management: an exploratory qualitative interview study. Rheumatol Int 45. https:\/\/doi.org\/10.1007\/s00296-025-05893-5","DOI":"10.1007\/s00296-025-05893-5"},{"key":"2470_CR24","doi-asserted-by":"publisher","first-page":"e099824","DOI":"10.1136\/bmjopen-2025-099824","volume":"15","author":"T Chen","year":"2025","unstructured":"Chen T, Li Q, Zhao D et al (2025) Utilisation of AI-driven chatbots for perioperative health information seeking: a descriptive qualitative study of orthopaedic patients and family members. BMJ Open 15:e099824. https:\/\/doi.org\/10.1136\/bmjopen-2025-099824","journal-title":"BMJ Open"},{"key":"2470_CR25","doi-asserted-by":"publisher","DOI":"10.1080\/10410236.2025.2601265","author":"A Reinhardt","year":"2025","unstructured":"Reinhardt A, Matthes J, Hodzic S et al (2025) Who trusts AI for health information? A cross-national survey on trust determinants in four European countries. Health Commun. https:\/\/doi.org\/10.1080\/10410236.2025.2601265","journal-title":"Health Commun"},{"key":"2470_CR26","doi-asserted-by":"publisher","first-page":"e260815","DOI":"10.1001\/jamanetworkopen.2026.0815","volume":"9","author":"A Bracic","year":"2026","unstructured":"Bracic A, Spector-Bagdady K, Towle S, Zhang R, James CA, Price WN (2026) Factors for patient trust and acceptance of medical artificial intelligence. JAMA Netw Open 9:e260815. https:\/\/doi.org\/10.1001\/jamanetworkopen.2026.0815","journal-title":"JAMA Netw Open"},{"key":"2470_CR27","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1097\/HEP.0000000000001037","volume":"80","author":"J Ge","year":"2024","unstructured":"Ge J, Sun S, Owens J et al (2024) Development of a liver disease-specific large language model chat interface using retrieval-augmented generation. Hepatology 80:1158\u20131168. https:\/\/doi.org\/10.1097\/HEP.0000000000001037","journal-title":"Hepatology"},{"key":"2470_CR28","doi-asserted-by":"publisher","first-page":"116168","DOI":"10.1016\/j.ejca.2025.116168","volume":"233","author":"N Carl","year":"2026","unstructured":"Carl N, Hetz MJ, Wies C et al (2026) Enhancing clinicians\u2019 trust in large language models via transparent source attribution: a randomized controlled evaluation in uro-oncology. Eur J Cancer 233:116168. https:\/\/doi.org\/10.1016\/j.ejca.2025.116168","journal-title":"Eur J Cancer"},{"key":"2470_CR29","doi-asserted-by":"publisher","first-page":"e73717","DOI":"10.2196\/73717","volume":"27","author":"S Donner","year":"2025","unstructured":"Donner S, Knauer P, Kienzle A et al (2025) Exploring patient perspectives, engagement, and output quality in doctor-supervised use of artificial intelligence during informed consent consultation with ChatGPT and retrieval augmented generation (RAG): quantitative exploratory study. J Med Internet Res 27:e73717. https:\/\/doi.org\/10.2196\/73717","journal-title":"J Med Internet Res"},{"key":"2470_CR30","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.jcms.2025.02.010","volume":"53","author":"D Steybe","year":"2025","unstructured":"Steybe D, Poxleitner P, Aljohani S et al (2025) Evaluation of a context-aware chatbot using retrieval-augmented generation for answering clinical questions on medication-related osteonecrosis of the jaw. J Craniomaxillofac Surg 53:355\u2013360. https:\/\/doi.org\/10.1016\/j.jcms.2025.02.010","journal-title":"J Craniomaxillofac Surg"},{"key":"2470_CR31","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.ero.2025.08.001","volume":"1","author":"A Madrid-Garc\u00eda","year":"2025","unstructured":"Madrid-Garc\u00eda A, Benavent D, Plasencia-Rodr\u00edguez C et al (2025) Optimising the clinical application of rheumatology guidelines using large language models: a retrieval-augmented generation framework integrating EULAR and ACR recommendations. EULAR Rheumatology Open 1:228\u2013236. https:\/\/doi.org\/10.1016\/j.ero.2025.08.001","journal-title":"EULAR Rheumatology Open"},{"key":"2470_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/s00296-025-06068-y","author":"P Kremer","year":"2026","unstructured":"Kremer P, Langballe E, Haase I et al (2026) Diagnostic performance of Prof. Valmed, ChatGPT-5 Thinking, and OpenEvidence in rheumatology: a comparative evaluation. Rheumatol Int 46. https:\/\/doi.org\/10.1007\/s00296-025-06068-y","journal-title":"Rheumatol Int 46"},{"key":"2470_CR33","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1038\/s41746-026-01637-4","volume":"9","author":"RL Draelos","year":"2026","unstructured":"Draelos RL, Afreen S, Blasko B et al (2026) Large language models provide unsafe answers to patient-posed medical questions. npj Digit Med 9:241. https:\/\/doi.org\/10.1038\/s41746-026-01637-4","journal-title":"npj Digit Med"},{"key":"2470_CR34","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1038\/s41746-025-02208-7","volume":"9","author":"S Zhou","year":"2026","unstructured":"Zhou S, Xie W, Li J et al (2026) Automating expert-level medical reasoning evaluation of large language models. npj Digit Med 9:34. https:\/\/doi.org\/10.1038\/s41746-025-02208-7","journal-title":"npj Digit Med"},{"key":"2470_CR35","first-page":"372","volume":"31","author":"DJ Wu","year":"2026","unstructured":"Wu DJ, Haredasht FN, Wu D et al (2026) Automated evaluation of large language model response concordance with human specialist responses on physician-to-physician eConsult cases. Pac Symp Biocomput 31:372\u2013387.","journal-title":"Pac Symp Biocomput"},{"key":"2470_CR36","doi-asserted-by":"publisher","unstructured":"Zhang J, Elluri S, Cherukuvada B et al (2026) Auditing multimodal LLM raters: central tendency bias in clinical ordinal scoring. arXiv:2605.16386. https:\/\/doi.org\/10.48550\/arXiv.2605.16386","DOI":"10.48550\/arXiv.2605.16386"},{"key":"2470_CR37","doi-asserted-by":"publisher","unstructured":"Stureborg R, Alikaniotis D, Suhara Y (2024) Large language models are inconsistent and biased evaluators. arXiv:2405.01724. https:\/\/doi.org\/10.48550\/arXiv.2405.01724","DOI":"10.48550\/arXiv.2405.01724"},{"key":"2470_CR38","doi-asserted-by":"publisher","first-page":"e2457879","DOI":"10.1001\/jamanetworkopen.2024.57879","volume":"8","author":"B Huo","year":"2025","unstructured":"Huo B, Boyle A, Marfo N et al (2025) Large language models for chatbot health advice studies: a systematic review. JAMA Netw Open 8:e2457879. https:\/\/doi.org\/10.1001\/jamanetworkopen.2024.57879","journal-title":"JAMA Netw Open"}],"container-title":["Journal of Medical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10916-026-02470-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10916-026-02470-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10916-026-02470-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T18:02:38Z","timestamp":1791309758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10916-026-02470-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2470"],"URL":"https:\/\/doi.org\/10.1007\/s10916-026-02470-6","relation":{},"ISSN":["1573-689X"],"issn-type":[{"value":"1573-689X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]},"assertion":[{"value":"1 July 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The Ethics Committee of Philipps University Marburg classified this study as exempt from ethical approval (reference: 25-237-Anz).","order":1,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Participation was voluntary. Completion of the questionnaire and use of the chatbot implied informed consent to participate.","order":2,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"A.R. is employed by Zentrum f\u00fcr Telemedizin Bad Kissingen. All other authors declare that they have no competing interests.","order":4,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":5,"name":"Ethics","label":"Clinical Trial Number","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"During the preparation of this manuscript, the authors used ChatGPT (OpenAI) and Claude (Anthropic) to assist with language editing and text refinement. All AI-generated output was critically reviewed, verified, and revised by the authors, who take full responsibility for the final content of the manuscript. Large language models were also used as part of the study methodology, as described in the Methods section.","order":6,"name":"Ethics","label":"AI Declaration","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"143"}}