{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T14:27:32Z","timestamp":1793543252709,"version":"4.5.0"},"reference-count":42,"publisher":"The Journal of Rheumatology","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Rheumatol"],"accepted":{"date-parts":[[2026,7,2]]},"published-print":{"date-parts":[[2026,11]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Large language models (LLMs) are increasingly evaluated for rheumatology tasks, but their performance in inflammatory arthritis (IA) remains unclear. We systematically reviewed LLM performance across clinical tasks in IA.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a systematic review (PROSPERO: CRD420261359100), searching PubMed, Scopus, and PubMed Central from January 2022 to April 2026 for studies evaluating LLM performance on clinical tasks in IA. Two reviewers (YA, AG) screened 113 records.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Eighteen studies covered rheumatoid arthritis (n = 3), axial spondyloarthritis (n = 7), psoriatic arthritis (n = 2), gout (n = 1), juvenile idiopathic arthritis (n = 1), and multiple diseases (n = 4). Most diseases and tasks were represented by only 1 to a few studies, and the evidence base remains early stage and uneven across conditions. Over 20 distinct LLMs were evaluated, including ChatGPT-3.5 to ChatGPT-4o, Gemini 2.0, DeepSeek-R1\/V3, Claude, and Perplexity; ChatGPT\/GPT variants were the most frequently tested models (16\/18 studies), so the current evidence base is predominantly ChatGPT\/GPT-based. Findings spanned patient education (n = 11), guideline adherence (n = 6), clinical reasoning (n = 3), and other applications (n = 1). All readability assessments exceeded the recommended thresholds. Guideline concordance ranged from 48% to 96%. Accuracy was lower for case-based clinical scenarios (4.24\/6) than for frequently asked questions and guideline-based questions (5.32-5.36\/6;\n                      <jats:italic>P<\/jats:italic>\n                      = 0.04). When compared with real clinical data, agreement was poor (Cohen and Fleiss \u03ba \u2248 0).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>LLMs may support patient education, factual medication queries, and structured guideline questions when used under clinician review, but should not be used for case-based reasoning, treatment selection, or autonomous clinical decisions. None of the 18 included studies evaluated retrieval-augmented or agent-based systems, and none prospectively validated LLMs in clinical workflows. Safe integration in rheumatology will require purpose-built, knowledge-grounded systems and prospective evaluation before routine clinical use.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3899\/jrheum.2026-0444","type":"journal-article","created":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T12:25:18Z","timestamp":1785587118000},"page":"1177-1187","source":"Crossref","is-referenced-by-count":0,"title":["ChatGPT and Other Large Language Models in Inflammatory Arthritis: A Systematic Review Across Clinical Tasks"],"prefix":"10.3899","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7678-633X","authenticated-orcid":false,"given":"Yosef","family":"Adiniaev","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0438-0827","authenticated-orcid":false,"given":"Mahmud","family":"Omar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9842-1636","authenticated-orcid":false,"given":"Tohar M.","family":"Timor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7242-1328","authenticated-orcid":false,"given":"Yiftach","family":"Barash","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7074-8909","authenticated-orcid":false,"given":"Olga R.","family":"Brook","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9777-2864","authenticated-orcid":false,"given":"Mohammad E.","family":"Naffaa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7542-8608","authenticated-orcid":false,"given":"Alon","family":"Gorenshtein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4567-3108","authenticated-orcid":false,"given":"Eyal","family":"Klang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2262","published-online":{"date-parts":[[2026,8,1]]},"reference":[{"key":"2026110105301039000_53.11.1177.1","doi-asserted-by":"publisher","DOI":"10.1007\/s00296-024-05733-y"},{"key":"2026110105301039000_53.11.1177.2","doi-asserted-by":"publisher","DOI":"10.1016\/S2665-9913(23)00211-4"},{"key":"2026110105301039000_53.11.1177.3","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2018.13103"},{"key":"2026110105301039000_53.11.1177.4","doi-asserted-by":"publisher","DOI":"10.1002\/acr.24596"},{"key":"2026110105301039000_53.11.1177.5","doi-asserted-by":"publisher","DOI":"10.1136\/ard-2022-223296"},{"key":"2026110105301039000_53.11.1177.6","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2016-210602"},{"key":"2026110105301039000_53.11.1177.7","doi-asserted-by":"publisher","DOI":"10.1002\/acr.24025"},{"key":"2026110105301039000_53.11.1177.8","doi-asserted-by":"publisher","DOI":"10.1002\/acr.24180"},{"key":"2026110105301039000_53.11.1177.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"2026110105301039000_53.11.1177.10","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.21700"},{"key":"2026110105301039000_53.11.1177.11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput Surv"},{"key":"2026110105301039000_53.11.1177.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03097-1"},{"key":"2026110105301039000_53.11.1177.13","doi-asserted-by":"crossref","first-page":"rkae120","DOI":"10.1093\/rap\/rkae120","article-title":"Advancing rheumatology with natural language processing: insights and prospects from a systematic review","volume":"8","author":"Omar","year":"2024","journal-title":"Rheumatol Adv Pract"},{"key":"2026110105301039000_53.11.1177.14","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1016\/j.joca.2026.03.001","article-title":"Generative artificial intelligence in osteoarthritis: a systematic scoping review of current applications and future directions","volume":"34","author":"Fairley","year":"2026","journal-title":"Osteoarthritis Cartilage"},{"key":"2026110105301039000_53.11.1177.15","doi-asserted-by":"crossref","first-page":"1670824","DOI":"10.3389\/fmed.2025.1670824","article-title":"Clinical applications of large language models in knee osteoarthritis: a systematic review","volume":"12","author":"Ma","year":"2025","journal-title":"Front Med"},{"key":"2026110105301039000_53.11.1177.16","doi-asserted-by":"crossref","first-page":"5687","DOI":"10.1093\/rheumatology\/keaf329","article-title":"Global variations in artificial intelligence-generated information on juvenile idiopathic arthritis","volume":"64","author":"La Bella","year":"2025","journal-title":"Rheumatology"},{"key":"2026110105301039000_53.11.1177.17","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71"},{"key":"2026110105301039000_53.11.1177.18","doi-asserted-by":"publisher","DOI":"10.1186\/s13643-016-0384-4"},{"key":"2026110105301039000_53.11.1177.19","doi-asserted-by":"crossref","first-page":"106246","DOI":"10.1016\/j.ijmedinf.2025.106246","article-title":"An old disease, a new linguistic challenge for large language models: patient education on psoriasis and psoriatic arthritis in an underrepresented medical language","volume":"209","author":"Atilan","year":"2026","journal-title":"Int J Med Inform"},{"key":"2026110105301039000_53.11.1177.20","doi-asserted-by":"crossref","first-page":"5700","DOI":"10.3390\/app15105700","article-title":"Generative artificial intelligence and risk appetite in medical decisions in rheumatoid arthritis","volume":"15","author":"Berghea","year":"2025","journal-title":"Appl Sci"},{"key":"2026110105301039000_53.11.1177.21","doi-asserted-by":"crossref","first-page":"e0326351","DOI":"10.1371\/journal.pone.0326351","article-title":"Evaluating the readability, quality, and reliability of responses generated by ChatGPT, Gemini, and Perplexity on the most commonly asked questions about ankylosing spondylitis","volume":"20","author":"Kara","year":"2025","journal-title":"PLoS One"},{"key":"2026110105301039000_53.11.1177.22","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/s00296-023-05473-5","article-title":"Assessing the accuracy and completeness of artificial intelligence language models in providing information on methotrexate use","volume":"44","author":"Coskun","year":"2024","journal-title":"Rheumatol Int"},{"key":"2026110105301039000_53.11.1177.23","doi-asserted-by":"crossref","unstructured":"Saji JG , Jabeen J , Antony JT. Evaluating readability, reliability, and originality of artificial intelligence\u2013generated patient education guides for common rheumatological conditions. J Public Health 2025. Available from: https:\/\/doi.org\/10.1007\/s10389-025-02628-5","DOI":"10.1007\/s10389-025-02628-5"},{"key":"2026110105301039000_53.11.1177.24","doi-asserted-by":"crossref","first-page":"1290","DOI":"10.1016\/j.ard.2025.11.012","article-title":"ChatGPT vs rheumatologists: cross-sectional study on accuracy and patient perception of AI-generated information for psoriatic arthritis","volume":"85","author":"Forte","year":"2025","journal-title":"Ann Rheum Dis"},{"key":"2026110105301039000_53.11.1177.25","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2024-097528"},{"key":"2026110105301039000_53.11.1177.26","doi-asserted-by":"crossref","first-page":"e79153","DOI":"10.2196\/79153","article-title":"Assessing the quality of AI responses to patient concerns about axial spondyloarthritis: Delphi-based evaluation","volume":"5","author":"Bai","year":"2026","journal-title":"JMIR AI"},{"key":"2026110105301039000_53.11.1177.27","doi-asserted-by":"crossref","first-page":"4015","DOI":"10.1007\/s10067-025-07648-w","article-title":"Evaluation of artificial intelligence use in ankylosing spondylitis with ChatGPT-4: patient and physician perspectives","volume":"44","author":"Altunel K\u0131l\u0131n\u00e7","year":"2025","journal-title":"Clin Rheumatol"},{"key":"2026110105301039000_53.11.1177.28","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1007\/s10067-025-07771-8","article-title":"AI-generated patient education for ankylosing spondylitis: a comparative study of readability and quality","volume":"45","author":"\u00c7abuk \u00c7elik","year":"2026","journal-title":"Clin Rheumatol"},{"key":"2026110105301039000_53.11.1177.29","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s10067-025-07789-y","article-title":"ChatGPT-4 vs. DeepSeek-V3: a comparative study of response quality, reliability, usefulness, and readability for exercise and rehabilitation strategies in patients with ankylosing spondylitis","volume":"45","author":"Sari","year":"2026","journal-title":"Clin Rheumatol"},{"key":"2026110105301039000_53.11.1177.30","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.1007\/s10067-025-07417-9","article-title":"Assessment of ChatGPT\u2019s adherence to EULAR diagnostic criteria and therapeutic protocols for rheumatoid arthritis at two distinct time points, 14 days apart, utilizing binary and multiple-choice inquiries","volume":"44","author":"\u00c7elik","year":"2025","journal-title":"Clin Rheumatol"},{"key":"2026110105301039000_53.11.1177.31","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.3390\/diagnostics15121455","article-title":"Evaluation of the performance of large language models in the management of axial spondyloarthropathy: analysis of EULAR 2022 recommendations","volume":"15","author":"Usen","year":"2025","journal-title":"Diagnostics"},{"key":"2026110105301039000_53.11.1177.32","doi-asserted-by":"crossref","first-page":"4831","DOI":"10.1038\/s41598-026-35166-5","article-title":"Evaluation of ChatGPT-4o and Gemini for gout management: a comparative analysis based on EULAR guidelines","volume":"16","author":"Meral","year":"2026","journal-title":"Sci Rep"},{"key":"2026110105301039000_53.11.1177.33","doi-asserted-by":"crossref","first-page":"7405","DOI":"10.3390\/jcm13237405","article-title":"Clinical reasoning and knowledge assessment of rheumatology residents compared to AI models: a pilot study","volume":"13","author":"Kayacan Erdo\u011fan","year":"2024","journal-title":"J Clin Med"},{"key":"2026110105301039000_53.11.1177.34","doi-asserted-by":"crossref","first-page":"ooaf132","DOI":"10.1093\/jamiaopen\/ooaf132","article-title":"Extracting TNFi switching reasons and trajectories from real-world data using large language models","volume":"8","author":"Miao","year":"2025","journal-title":"JAMIA Open"},{"key":"2026110105301039000_53.11.1177.35","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s41927-026-00618-y","article-title":"Artificial intelligence (AI) in rheumatology: a comparative evaluation of the ChatGPT and DeepSeek application","volume":"10","author":"Polyzou","year":"2026","journal-title":"BMC Rheumatol"},{"key":"2026110105301039000_53.11.1177.36","doi-asserted-by":"crossref","unstructured":"Gorenshtein A , Omar M , Glicksberg BS , Nadkarni GN , Klang E. AI agents in clinical medicine: a systematic review. medRxiv 2025:2025.08.22.25334232.","DOI":"10.1101\/2025.08.22.25334232"},{"key":"2026110105301039000_53.11.1177.37","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01091-y"},{"key":"2026110105301039000_53.11.1177.38","doi-asserted-by":"crossref","first-page":"AIoa2300068","DOI":"10.1056\/AIoa2300068","article-title":"Almanac \u2014 retrieval-augmented language models for clinical medicine","volume":"1","author":"Zakka","year":"2024","journal-title":"NEJM AI"},{"key":"2026110105301039000_53.11.1177.39","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1093\/jamia\/ocaf008","article-title":"Improving large language model applications in biomedicine with retrieval-augmented generation: a systematic review, meta-analysis, and clinical development guidelines","volume":"32","author":"Liu","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"2026110105301039000_53.11.1177.40","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1038\/s43856-025-01021-3","article-title":"Multi-model assurance analysis showing large language models are highly vulnerable to adversarial hallucination attacks during clinical decision support","volume":"5","author":"Omar","year":"2025","journal-title":"Commun Med"},{"key":"2026110105301039000_53.11.1177.41","doi-asserted-by":"crossref","unstructured":"Klang E , Glicksberg BS , Gorenshtein A , . Clinical agents don\u2019t care. medRxiv 2025.10.17.25338226.","DOI":"10.1101\/2025.10.17.25338226"},{"key":"2026110105301039000_53.11.1177.42","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/j.amjmed.2025.12.027","article-title":"Impact of patient communication style on agentic AI-generated clinical advice in E-medicine","volume":"139","author":"Omar","year":"2026","journal-title":"Am J Med"}],"container-title":["The Journal of Rheumatology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.3899\/jrheum.2026-0444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T13:30:50Z","timestamp":1793539850000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.jrheum.org\/lookup\/doi\/10.3899\/jrheum.2026-0444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":42,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,11,1]]},"published-print":{"date-parts":[[2026,11]]}},"alternative-id":["10.3899\/jrheum.2026-0444"],"URL":"https:\/\/doi.org\/10.3899\/jrheum.2026-0444","relation":{},"ISSN":["0315-162X","1499-2752"],"issn-type":[{"value":"0315-162X","type":"print"},{"value":"1499-2752","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,1]]}}}