{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T13:40:25Z","timestamp":1788961225487,"version":"build-2803163510"},"reference-count":14,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T00:00:00Z","timestamp":1581292800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100001637","name":"Genentech Foundation for Biomedical Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100001637","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["UL1 TR000137"],"award-info":[{"award-number":["UL1 TR000137"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["AR060861"],"award-info":[{"award-number":["AR060861"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["AR061298\u201003"],"award-info":[{"award-number":["AR061298\u201003"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["N01\u2010AR\u20104\u20102273"],"award-info":[{"award-number":["N01\u2010AR\u20104\u20102273"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["R01 AR061298"],"award-info":[{"award-number":["R01 AR061298"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000069","name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","doi-asserted-by":"publisher","award":["R01 AR57781"],"award-info":[{"award-number":["R01 AR57781"]}],"id":[{"id":"10.13039\/100000069","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["acrjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["ACR Open Rheumatology"],"published-print":{"date-parts":[[2020,3]]},"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Published predictive models of disease outcomes in idiopathic inflammatory myopathies (<jats:styled-content style=\"fixed-case\">IIM<\/jats:styled-content>s) are sparse and of limited accuracy due to disease heterogeneity. Computational methods may address this heterogeneity by partitioning patients based on clinical and biological phenotype.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To identify new patient groups, we applied similarity network fusion (<jats:styled-content style=\"fixed-case\">SNF<\/jats:styled-content>) to clinical and biological data from 168 patients with myositis (64 adult polymyositis [<jats:styled-content style=\"fixed-case\">PM<\/jats:styled-content>], 65 adult dermatomyositis [<jats:styled-content style=\"fixed-case\">DM<\/jats:styled-content>], and 39 juvenile <jats:styled-content style=\"fixed-case\">DM<\/jats:styled-content> [<jats:styled-content style=\"fixed-case\">JDM<\/jats:styled-content>]) in the Rituximab in Myositis trial. We generated a sparse proof\u2010of\u2010concept bedside classifier using multinomial regression and identified characteristics that distinguished these groups. We conducted \u03c7<jats:sup>2<\/jats:sup> tests to link new patient groups with the myositis subtypes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p><jats:styled-content style=\"fixed-case\">SNF<\/jats:styled-content> identified five patient groups in the discovery cohort that subdivided the myositis subtypes. The sparse multinomial regressor to predict patient group assignments (areas under the receiver operating characteristic curve = [0.78, 0.97]; areas under the precision\u2010recall curve = [0.55, 0.96]) found that autoantibody enrichment defined four of these groups: anti\u2013Mi\u20102, anti\u2013signal recognition peptide (<jats:styled-content style=\"fixed-case\">SRP<\/jats:styled-content>), anti\u2013nuclear matrix protein 2 (<jats:styled-content style=\"fixed-case\">NXP<\/jats:styled-content>2), and anti\u2010synthetase (Syn). Depletion of immunoglobulin M (IgM) defined the fifth group. Each group was associated with one subtype, with adult <jats:styled-content style=\"fixed-case\">DM<\/jats:styled-content> being associated with anti\u2013Mi\u20102 and anti\u2010Syn autoantibodies, <jats:styled-content style=\"fixed-case\">JDM<\/jats:styled-content> being associated with anti\u2010<jats:styled-content style=\"fixed-case\">NXP<\/jats:styled-content>2 autoantibodies, and adult <jats:styled-content style=\"fixed-case\">PM<\/jats:styled-content> being associated with IgM depletion and anti\u2010<jats:styled-content style=\"fixed-case\">SRP<\/jats:styled-content> autoantibodies. These associations enabled us to further resolve the current myositis subtypes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Using unsupervised machine learning, we identified clinically and biologically homogeneous groups of patients with <jats:styled-content style=\"fixed-case\">IIM<\/jats:styled-content>s, forming the basis of an integrated disease classification based on both clinical and biological phenotype, thus validating other approaches and what has been previously described.<\/jats:p><\/jats:sec>","DOI":"10.1002\/acr2.11115","type":"journal-article","created":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T05:18:52Z","timestamp":1581311932000},"page":"158-166","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning"],"prefix":"10.1002","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5495-0157","authenticated-orcid":false,"given":"Simon W. M.","family":"Eng","sequence":"first","affiliation":[{"name":"Hospital for Sick Children (SickKids), University of Toronto Toronto Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeannette M.","family":"Olazagasti","sequence":"additional","affiliation":[{"name":"Mayo Clinic Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Goldenberg","sequence":"additional","affiliation":[{"name":"Hospital for Sick Children (SickKids), Vector Institute, University of Toronto Toronto Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5847-7475","authenticated-orcid":false,"given":"Cynthia S.","family":"Crowson","sequence":"additional","affiliation":[{"name":"Mayo Clinic Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chester V.","family":"Oddis","sequence":"additional","affiliation":[{"name":"University of Pittsburgh Pittsburgh Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy B.","family":"Niewold","sequence":"additional","affiliation":[{"name":"Mayo Clinic Rochester Minnesota"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2361-725X","authenticated-orcid":false,"given":"Rae S. M.","family":"Yeung","sequence":"additional","affiliation":[{"name":"Hospital for Sick Children (SickKids), University of Toronto Toronto Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4521-7647","authenticated-orcid":false,"given":"Ann M.","family":"Reed","sequence":"additional","affiliation":[{"name":"Duke University School of Medicine Durham North Carolina"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2020,2,10]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-6632.2009.05119.x"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1097\/00019052-200310000-00002"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.37754"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.38875"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.2810"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/keg427"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0889-857X(02)00032-7"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1101\/gr.1239303"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1101\/gr.092759.109"},{"key":"e_1_2_7_11_1","volume-title":"An introduction to categorical data analysis","author":"Agresti A","year":"2018"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.3899\/jrheum.090461"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.24547"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12016-015-8510-y"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/rheumatology\/keu259"}],"container-title":["ACR Open Rheumatology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Facr2.11115","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acr2.11115","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acr2.11115","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acr2.11115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T17:24:09Z","timestamp":1759425849000},"score":1,"resource":{"primary":{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/10.1002\/acr2.11115"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,10]]},"references-count":14,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["10.1002\/acr2.11115"],"URL":"https:\/\/doi.org\/10.1002\/acr2.11115","archive":["Portico"],"relation":{},"ISSN":["2578-5745","2578-5745"],"issn-type":[{"value":"2578-5745","type":"print"},{"value":"2578-5745","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,10]]},"assertion":[{"value":"2019-08-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-12-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-02-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}