{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T05:52:43Z","timestamp":1791006763571,"version":"4.1.0"},"reference-count":21,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["acrjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Arthritis &amp;amp; Rheumatology"],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Antinuclear antibody (ANA) indirect immunofluorescence (IIF) is the reference standard but depends on subjective pattern interpretation. We tested whether artificial intelligence (AI) applied to ANA IIF images could identify specific autoantibodies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We assembled a cohort of ANA\u2010positive patients (human epithelial type 2 IIF titer \u22651:80) with anti\u2013double\u2010stranded DNA (dsDNA), anti\u2010Smith (Sm) antibody, ribonucleoprotein (RNP), anti\u2010Sj\u00f6gren's disease\u2010related antigen A (SSA), anti\u2010Sj\u00f6gren's disease\u2010related antigen B (SSB), anti\u2010topoisomerase I (Scl\u201070), or centromere antibody (CMA) testing within 90 days. The development cohort (December 12, 2016\u2013December 31, 2022) included the first ANA test per patient. Two AI architectures were trained for each autoantibody. Performance was assessed using area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, and accuracy; comparisons with IIF patterns were summarized as pattern\u2010antibody agreement. A prospective cohort (January 1, 2023\u2013August 20, 2024), including a dsDNA assay transition, provided temporal validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 512,959 patients, 47,890 met inclusion criteria (mean age 55 [SD 17.6], 78% female). Models for CMA, dsDNA, Sm, SSA, and SSB achieved AUROC \u22650.80 (CMA highest: AUROC 0.95, accuracy 94.2%, specificity 95.3%). Compared with associated IIF patterns, dsDNA and Sm models more often classified antibody\u2010negative cases as negative (dsDNA 88.2% vs 54.7%; Sm 82.6% vs 60.3%) while similarly classifying antibody\u2010positive cases. Performance for RNP (AUROC 0.68) and Scl\u201070 (AUROC 0.59) was lower. In the prospective cohort (n\u00a0=\u00a021,427), performance was similar; dsDNA discrimination remained stable across assays (AUROC\u2009~0.85).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI applied to ANA IIF images identified specific autoantibodies and often improved classification of antibody\u2010negative cases versus simplified pattern\u2010based comparators. These findings support its potential to standardize ANA interpretation and triage or reduce confirmatory testing.<\/jats:p>\n                    <jats:p>\n                      <jats:boxed-text content-type=\"graphic\" position=\"anchor\">\n                        <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mimetype=\"image\/png\" position=\"anchor\" specific-use=\"enlarged-web-image\" xlink:href=\"graphic\/art70312-gra-0001-m.png\">\n                          <jats:alt-text>image<\/jats:alt-text>\n                        <\/jats:graphic>\n                      <\/jats:boxed-text>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/art.70312","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T10:28:09Z","timestamp":1787912889000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and Temporal Validation of\n                    <scp>AI<\/scp>\n                    \u2010Enhanced Human Epithelial Type 2 Indirect Immunofluorescence Image Analysis for Specific Autoantibody Prediction in Systemic Autoimmune Rheumatic Diseases"],"prefix":"10.1002","author":[{"given":"Patrick","family":"Vanderboom","sequence":"first","affiliation":[{"name":"Department of Laboratory Medicine and Pathology Mayo Clinic  Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Surendra","family":"Dasari","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences Mayo Clinic  Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-0871","authenticated-orcid":false,"given":"Marlon J.","family":"Sandino\u2010Berm\u00fadez","sequence":"additional","affiliation":[{"name":"Division of Rheumatology Mayo Clinic  Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne","family":"Tebo","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine and Pathology Mayo Clinic  Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Snyder","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine and Pathology Mayo Clinic  Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1749-5719","authenticated-orcid":false,"given":"Al\u00ed","family":"Duarte\u2010Garc\u00eda","sequence":"additional","affiliation":[{"name":"Division of Rheumatology Mayo Clinic  Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,2]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2015.00412"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2013-203863"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1136\/annrheumdis-2018-214436"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00376-2"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0195-0"},{"issue":"9","key":"e_1_2_7_7_1","first-page":"2024","article-title":"Rheumatology diagnostics utilizing artificial intelligence (ANA Reader\u00a9) for ANA pattern identification and titer quantification [abstract]","volume":"76","author":"Choi MMF","year":"2024","journal-title":"Arthritis Rheumatol"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2018.11.002"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.103031"},{"key":"e_1_2_7_10_1","first-page":"4510","volume-title":"In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Sandler M","year":"2018"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1177\/0961203316640920"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03953-8"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1515\/cclm-2023-0209"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.autrev.2024.103608"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.103030"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12026-025-09623-8"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/clinchem\/hvae106.466"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/315179"},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.42330"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/acr.23518"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2021.798322"}],"container-title":["Arthritis &amp; Rheumatology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/art.70312","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/art.70312","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/art.70312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T04:55:08Z","timestamp":1791003308000},"score":1,"resource":{"primary":{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/10.1002\/art.70312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,2]]},"references-count":21,"alternative-id":["10.1002\/art.70312"],"URL":"https:\/\/doi.org\/10.1002\/art.70312","archive":["Portico"],"relation":{},"ISSN":["2326-5191","2326-5205"],"issn-type":[{"value":"2326-5191","type":"print"},{"value":"2326-5205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,2]]},"assertion":[{"value":"2026-01-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"art.70312"}}