{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T12:25:13Z","timestamp":1784550313119,"version":"3.55.0"},"reference-count":12,"publisher":"FapUNIFESP (SciELO)","issue":"2","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"am","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Rev. Assoc. Med. Bras."],"abstract":"<jats:p>SUMMARY  OBJECTIVE: The aim of this study was to evaluate the diagnostic accuracy of a pretrained Vision Transformer model on nailfold capillaroscopy images, comparing its performance to that of expert rheumatologists.  METHODS: We retrospectively analyzed 104 anonymized images (23 normal, 81 pathological) from publicly available datasets. The pretrained Vision Transformer model was applied without fine-tuning. Two rheumatologists independently assessed the same image set. Accuracy and interrater agreement were calculated.  RESULTS: The AI model produced 0% clinical applicability, failing to generate meaningful classifications. In contrast, the consensus of two rheumatologists achieved the highest diagnostic performance, with 94.2% accuracy and a Cohen\u2019s Kappa of 0.827. Individual rheumatologist evaluations yielded comparatively lower accuracy and agreement.  CONCLUSION: We retrospectively analyzed X anonymized images (XX normal, XX pathological) from publicly available datasets. The pretrained Vision Transformer model was applied without fine-tuning. Two rheumatologists independently assessed the same image set. Accuracy and interrater agreement were calculated.<\/jats:p>","DOI":"10.1590\/1806-9282.20251389","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T11:15:04Z","timestamp":1778238904000},"source":"Crossref","is-referenced-by-count":1,"title":["Comparison of artificial intelligence and rheumatologists in nailfold capillaroscopic evaluation"],"prefix":"10.1590","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9045-7105","authenticated-orcid":false,"given":"Ne\u015fe \u00c7abuk","family":"\u00c7elik","sequence":"first","affiliation":[{"name":"Sincan Training and Research Hospital,  T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2501-2473","authenticated-orcid":false,"given":"Elif Altunel","family":"K\u0131l\u0131n\u00e7","sequence":"additional","affiliation":[{"name":"Mersin Training and Research Hospital,  T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"530","published-online":{"date-parts":[[2026]]},"reference":[{"issue":"3","key":"ref1","doi-asserted-by":"crossref","first-page":"644","DOI":"10.55730\/1300-0144.6011","article-title":"Pulmonary artery wall thickness and systemic sclerosis: influence of inflammation on vascular changes.","volume":"55","author":"Altunel Kilin\u00e7 E","year":"2025","journal-title":"Turk J Med Sci"},{"issue":"4","key":"ref2","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1038\/s41584-020-0386-4","article-title":"Raynaud phenomenon and digital ulcers in systemic sclerosis.","volume":"16","author":"Hughes M","year":"2020","journal-title":"Nat Rev Rheumatol"},{"issue":"8","key":"ref3","doi-asserted-by":"crossref","first-page":"1435","DOI":"10.1093\/rheumatology\/keu533","article-title":"A study comparing videocapillaroscopy and dermoscopy in the assessment of nailfold capillaries in patients with systemic sclerosis-spectrum disorders.","volume":"54","author":"Hughes M","year":"2015","journal-title":"Rheumatology (Oxford)"},{"issue":"1","key":"ref4","doi-asserted-by":"crossref","first-page":"40","DOI":"10.4103\/idoj.idoj_460_24","article-title":"Artificial intelligence in diagnosis and management of nail disorders: a narrative review.","volume":"16","author":"Gaurav V","year":"2024","journal-title":"Indian Dermatol Online J"},{"issue":"10","key":"ref5","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.36849\/JDD.6519","article-title":"Artificial intelligence in hair and nail disorders.","volume":"21","author":"Jartarkar S","year":"2022","journal-title":"J Drugs Dermatol"},{"issue":"12","key":"ref6","doi-asserted-by":"crossref","first-page":"2637","DOI":"10.1007\/s13555-022-00833-8","article-title":"Artificial intelligence in dermatology: challenges and perspectives.","volume":"12","author":"Liopyris K","year":"2022","journal-title":"Dermatol Ther (Heidelb)"},{"issue":"4","key":"ref7","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1038\/s41390-023-02894-7","article-title":"Artificial intelligence for nailfold capillaroscopy analyses - a proof of concept application in juvenile dermatomyositis.","volume":"95","author":"Kassani PH","year":"2024","journal-title":"Pediatr Res"},{"issue":"5","key":"ref8","doi-asserted-by":"crossref","first-page":"352","DOI":"10.4103\/ijd.IJD_418_20","article-title":"Use of artificial intelligence in dermatology.","volume":"65","author":"De A","year":"2020","journal-title":"Indian J Dermatol"},{"issue":"9","key":"ref9","doi-asserted-by":"crossref","first-page":"e18091","DOI":"10.2196\/18091","article-title":"Artificial intelligence and its effect on dermatologists\u2019 accuracy in dermoscopic melanoma image classification: web-based survey study.","volume":"22","author":"Maron RC","year":"2020","journal-title":"J Med Internet Res"},{"issue":"6","key":"ref10","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 N\u00c7","year":"2025","journal-title":"Clin Rheumatol"},{"issue":"10","key":"ref11","doi-asserted-by":"crossref","first-page":"4015","DOI":"10.1007\/s10067-025-07648-w","article-title":"Evaluation of artificial \u0131ntelligence use in ankylosing spondylitis with ChatGPT-4: patient and physician perspectives.","volume":"44","author":"Altunel K\u0131l\u0131n\u00e7 E","year":"2025","journal-title":"Clin Rheumatol"},{"issue":"10","key":"ref12","doi-asserted-by":"crossref","first-page":"651","DOI":"10.28982\/josam.7977","article-title":"Performance of artificial intelligence chatbot as a source of patient information on anti-rheumatic drug use in pregnancy: artificial intelligence as source of information for anti-rheumatics during pregnancy.","volume":"7","author":"Oru\u00e7o\u011flu N","year":"2023","journal-title":"J Surg Med"}],"container-title":["Revista da Associa\u00e7\u00e3o M\u00e9dica Brasileira"],"original-title":[],"link":[{"URL":"http:\/\/www.scielo.br\/scielo.php?script=sci_pdf&pid=S0104-42302026000202226&tlng=en","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T11:15:06Z","timestamp":1778238906000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.scielo.br\/scielo.php?script=sci_arttext&pid=S0104-42302026000202226&tlng=en"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":12,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026]]}},"alternative-id":["S0104-42302026000202226"],"URL":"https:\/\/doi.org\/10.1590\/1806-9282.20251389","relation":{},"ISSN":["1806-9282","0104-4230"],"issn-type":[{"value":"1806-9282","type":"electronic"},{"value":"0104-4230","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]},"article-number":"e20251389"}}