{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:04:58Z","timestamp":1784275498151,"version":"3.55.0"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T00:00:00Z","timestamp":1783468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Rheumatol Int"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Large language models (LLMs) with multimodal capabilities may support automated assessment of cutaneous disease activity in dermatomyositis (DM). We evaluated the performance of Claude v3.5 Sonnet in scoring the Cutaneous Dermatomyositis Disease Area and Severity Index (CDASI) compared with expert rheumatologists. Thirty published DM cases with available clinical images were retrospectively analyzed. Two expert rheumatologists independently scored CDASI activity and damage domains. Claude v3.5 Sonnet assessed the same images using structured prompting based on CDASI definitions. Agreement was evaluated using intraclass correlation coefficients (ICCs) with a two-way random-effects model for absolute agreement. The LLM demonstrated better agreement for activity than for damage assessment. Global CDASI activity showed good agreement with expert raters (ICC 0.71, 95% CI 0.45\u20130.86), whereas damage reliability was lower (ICC 0.41, 95% CI 0.25\u20130.67). Agreement was moderate for activity-related domains including erythema (ICC 0.61), scaling (ICC 0.57), and erosions (ICC 0.57), while lower concordance was observed for chronic damage-related features such as poikiloderma (ICC 0.47, 95% CI 0.10\u20130.73). Hand assessments demonstrated the strongest performance, particularly for periungual changes (ICC 1.0, 95% CI 1.0\u20131.0) and global hand scores (ICC 0.95, 95% CI 0.91\u20130.97). The model also markedly reduced evaluation time compared with clinicians (42\u00a0s vs. 8.4\u00a0min per case), corresponding to an approximately 92% reduction in scoring time. Multimodal LLMs demonstrated promising agreement with expert raters for CDASI activity assessment and markedly improved efficiency, although lower reliability in damage domains reinforces the continued need for physician oversight.<\/jats:p>","DOI":"10.1007\/s00296-026-06205-1","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:20:56Z","timestamp":1783524056000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessment of CDASI scoring by a multimodal large language model: a comparative study with expert assessors"],"prefix":"10.1007","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1716-7432","authenticated-orcid":false,"given":"Marco","family":"Fornaro","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2573-5930","authenticated-orcid":false,"given":"Vincenzo","family":"Venerito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3489-6283","authenticated-orcid":false,"given":"Swapnasha","family":"Panigrahi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3176-9958","authenticated-orcid":false,"given":"Sara","family":"Sabbagh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0474-5344","authenticated-orcid":false,"given":"Florenzo","family":"Iannone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2753-2990","authenticated-orcid":false,"given":"Latika","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"issue":"1","key":"6205_CR1","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1038\/s41572-021-00321-x","volume":"7","author":"IE Lundberg","year":"2021","unstructured":"Lundberg IE, Fujimoto M, Vencovsky J, Aggarwal R, Holmqvist M, Christopher-Stine L, Mammen AL, Miller FW (2021) Idiopathic inflammatory myopathies. Nat Rev Dis Primers 7(1):86. https:\/\/doi.org\/10.1038\/s41572-021-00321-x","journal-title":"Nat Rev Dis Primers"},{"issue":"2","key":"6205_CR2","doi-asserted-by":"publisher","first-page":"288","DOI":"10.55563\/clinexprheumatol\/kgpnbq","volume":"42","author":"M Fornaro","year":"2024","unstructured":"Fornaro M, Girolamo F, Giannini M, Coladonato L, Capuano A, Capodiferro M, D\u2019Abbicco D, Ruggieri M, Mastrapasqua M, Iannone F (2024) Clinical, histologic and prognostic features of clinically amyopathic dermatomyositis. Clin Exp Rheumatol 42(2):288\u2013294. https:\/\/doi.org\/10.55563\/clinexprheumatol\/kgpnbq","journal-title":"Clin Exp Rheumatol"},{"issue":"3","key":"6205_CR3","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1111\/j.1365-2133.2009.09521.x","volume":"162","author":"M Yassaee","year":"2010","unstructured":"Yassaee M, Fiorentino D, Okawa J, Taylor L, Coley C, Troxel AB, Werth VP (2010) Modification of the cutaneous dermatomyositis disease area and severity index, an outcome instrument. Br J Dermatol 162(3):669\u2013673. https:\/\/doi.org\/10.1111\/j.1365-2133.2009.09521.x","journal-title":"Br J Dermatol"},{"issue":"10","key":"6205_CR4","doi-asserted-by":"publisher","first-page":"3256","DOI":"10.1093\/rheumatology\/kead291","volume":"62","author":"V Venerito","year":"2023","unstructured":"Venerito V, Bilgin E, Iannone F, Kiraz S (2023) AI am a rheumatologist: a practical primer to large language models for rheumatologists. Rheumatology (Oxford) 62(10):3256\u20133260. https:\/\/doi.org\/10.1093\/rheumatology\/kead291","journal-title":"Rheumatology (Oxford)"},{"issue":"1","key":"6205_CR5","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s00296-025-06068-y","volume":"46","author":"P Kremer","year":"2026","unstructured":"Kremer P, Langballe E, Haase I, Bamberger J, Kuhn S, Krusche M, Knitza J (2026) Diagnostic performance of Prof. Valmed, ChatGPT-5 Thinking, and OpenEvidence in rheumatology: A comparative evaluation. Rheumatol Int 46(1):31. https:\/\/doi.org\/10.1007\/s00296-025-06068-y","journal-title":"Rheumatol Int"},{"issue":"9","key":"6205_CR6","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/s00296-025-05934-z","volume":"45","author":"T Hoffmann","year":"2025","unstructured":"Hoffmann T, Teichgraber U, Bruheim LB, Lassen-Schmidt B, Renz D, Weise T, Kramer M, Oelzner P, Bottcher J, Guttler F, Wolf G, Pfeil A (2025) The association of symptoms, pulmonary function test and computed tomography in interstitial lung disease at the onset of connective tissue disease: an observational study with artificial intelligence analysis of high-resolution computed tomography. Rheumatol Int 45(9):194. https:\/\/doi.org\/10.1007\/s00296-025-05934-z","journal-title":"Rheumatol Int"},{"issue":"4","key":"6205_CR7","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s00296-025-05825-3","volume":"45","author":"D Benavent","year":"2025","unstructured":"Benavent D, Carmona L, Garcia Llorente JF, Montoro M, Ramirez S, Oton T, Loza E, Gomez-Centeno A (2025) Artificial intelligence to predict treatment response in rheumatoid arthritis and spondyloarthritis: a scoping review. Rheumatol Int 45(4):91. https:\/\/doi.org\/10.1007\/s00296-025-05825-3","journal-title":"Rheumatol Int"},{"issue":"10","key":"6205_CR8","doi-asserted-by":"publisher","first-page":"e574","DOI":"10.1016\/S2665-9913(23)00216-3","volume":"5","author":"V Venerito","year":"2023","unstructured":"Venerito V, Puttaswamy D, Iannone F, Gupta L (2023) Large language models and rheumatology: a comparative evaluation. Lancet Rheumatol 5(10):e574\u2013e578. https:\/\/doi.org\/10.1016\/S2665-9913(23)00216-3","journal-title":"Lancet Rheumatol"},{"issue":"10","key":"6205_CR9","doi-asserted-by":"publisher","first-page":"e292","DOI":"10.1093\/rheumatology\/keae233","volume":"63","author":"V Venerito","year":"2024","unstructured":"Venerito V, Fornaro M, Sabbagh S, Ghosh S, Chinoy H, Gupta L, Myo LLMI (2024) Integrating large language models in medicine: a study of Claude 2\u2019s performance in MDAAT scoring for idiopathic inflammatory myopathies. Rheumatology (Oxford) 63(10):e292\u2013e293. https:\/\/doi.org\/10.1093\/rheumatology\/keae233","journal-title":"Rheumatology (Oxford)"},{"key":"6205_CR10","doi-asserted-by":"publisher","DOI":"10.1515\/dx-2025-0014","author":"L Cirkel","year":"2025","unstructured":"Cirkel L, Lechner F, Henk LA, Krusche M, Hirsch MC, Hertl M, Kuhn S, Knitza J (2025) Large language models for dermatological image interpretation - a comparative study. Diagnosis (Berl). https:\/\/doi.org\/10.1515\/dx-2025-0014","journal-title":"Diagnosis (Berl)"},{"issue":"2","key":"6205_CR11","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1111\/bjd.15140","volume":"176","author":"J Tiao","year":"2017","unstructured":"Tiao J, Feng R, Bird S, Choi JK, Dunham J, George M, Gonzalez-Rivera TC, Kaufman JL, Khan N, Luo JJ, Micheletti R, Payne AS, Price R, Quinn C, Rubin AI, Sreih AG, Thomas P, Okawa J, Werth VP (2017) The reliability of the Cutaneous Dermatomyositis Disease Area and Severity Index (CDASI) among dermatologists, rheumatologists and neurologists. Br J Dermatol 176(2):423\u2013430. https:\/\/doi.org\/10.1111\/bjd.15140","journal-title":"Br J Dermatol"},{"issue":"3","key":"6205_CR12","doi-asserted-by":"publisher","first-page":"e0001306","DOI":"10.1371\/journal.pdig.0001306","volume":"5","author":"V Mavrych","year":"2026","unstructured":"Mavrych V, Yousef EM, Yaqinuddin A, Shaikh AA, Bolgova O (2026) Visual recognition limitations in multimodal large language models: A comparative analysis of histological image interpretation. PLOS Digit Health 5(3):e0001306. https:\/\/doi.org\/10.1371\/journal.pdig.0001306","journal-title":"PLOS Digit Health"},{"issue":"10","key":"6205_CR13","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1007\/s00296-025-05996-z","volume":"45","author":"O Kuculmez","year":"2025","unstructured":"Kuculmez O, Usen A, Ahi ED (2025) Referential hallucination and clinical reliability in large language models: a comparative analysis using regenerative medicine guidelines for chronic pain. Rheumatol Int 45(10):240. https:\/\/doi.org\/10.1007\/s00296-025-05996-z","journal-title":"Rheumatol Int"},{"issue":"1","key":"6205_CR14","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13000-024-01464-7","volume":"19","author":"E Ullah","year":"2024","unstructured":"Ullah E, Parwani A, Baig MM, Singh R (2024) Challenges and barriers of using large language models (LLM) such as ChatGPT for diagnostic medicine with a focus on digital pathology - a recent scoping review. Diagn Pathol 19(1):43. https:\/\/doi.org\/10.1186\/s13000-024-01464-7","journal-title":"Diagn Pathol"},{"issue":"7","key":"6205_CR15","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1136\/ard-2023-224652","volume":"83","author":"D Saygin","year":"2024","unstructured":"Saygin D, Werth V, Paik JJ, Park JK, Needham M, Lundberg IE, Christopher-Stine L (2024) Current myositis clinical trials and tribulations. Ann Rheum Dis 83(7):826\u2013829. https:\/\/doi.org\/10.1136\/ard-2023-224652","journal-title":"Ann Rheum Dis"},{"issue":"6","key":"6205_CR16","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1097\/BOR.0000000000001044","volume":"36","author":"C Ricco","year":"2024","unstructured":"Ricco C, Stone CJ, Werth VP (2024) Clinical endpoints in myositis: challenges and ways forward. Curr Opin Rheumatol 36(6):430\u2013437. https:\/\/doi.org\/10.1097\/BOR.0000000000001044","journal-title":"Curr Opin Rheumatol"}],"container-title":["Rheumatology International"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00296-026-06205-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00296-026-06205-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00296-026-06205-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T07:17:03Z","timestamp":1784272623000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00296-026-06205-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,8]]},"references-count":16,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["6205"],"URL":"https:\/\/doi.org\/10.1007\/s00296-026-06205-1","relation":{},"ISSN":["1437-160X"],"issn-type":[{"value":"1437-160X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,8]]},"assertion":[{"value":"6 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have not conflict of interest to declare.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study used only anonymized images obtained from previously published reports and did not involve direct human subject research. Institutional ethics committee approval and informed consent were not required according to local regulations.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was conducted in accordance with the principles of the Declaration of Helsinki. As the study was based exclusively on analysis of previously published and anonymized clinical images, formal ethical committee approval and informed consent were not required.","order":3,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"ChatGPT (OpenAI, GPT-5-based model) was used for language editing and manuscript refinement, while Claude 3.5 Sonnet (Anthropic) was evaluated as the study tool for scoring cutaneous dermatomyositis activity from clinical images. All AI-generated outputs were critically reviewed, verified, and edited by the authors, who take full responsibility for the accuracy, integrity, and originality of the manuscript. No AI-assisted technology was listed as an author or co-author.","order":4,"name":"Ethics","label":"Artificial Intelligence-Assisted Technology Statement","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"196"}}