{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T04:29:15Z","timestamp":1790137755386,"version":"4.0.1"},"reference-count":30,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2019,9,2]],"date-time":"2019-09-02T00:00:00Z","timestamp":1567382400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100001845","name":"Scleroderma Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100001845","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["5T32LM012204\u201003"],"award-info":[{"award-number":["5T32LM012204\u201003"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008590","name":"Dr. Ralph and Marian Falk Medical Research Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008590","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["acrjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Arthritis &amp; Rheumatology"],"published-print":{"date-parts":[[2019,10]]},"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>High\u2010throughput gene expression profiling of tissue samples from patients with systemic sclerosis (<jats:styled-content style=\"fixed-case\">SS<\/jats:styled-content>c) has identified 4 \u201cintrinsic\u201d gene expression subsets: inflammatory, fibroproliferative, normal\u2010like, and limited. Prior methods required agglomerative clustering of many samples. In order to classify individual patients in clinical trials or for diagnostic purposes, supervised methods that can assign single samples to molecular subsets are required. We undertook this study to introduce a novel machine learning classifier as a robust accurate intrinsic subset predictor.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Three independent gene expression cohorts were curated and merged to create a data set covering 297 skin biopsy samples from 102 unique patients and controls, which was used to train a machine learning algorithm. We performed external validation using 3 independent <jats:styled-content style=\"fixed-case\">SS<\/jats:styled-content>c cohorts, including a gene expression data set generated by an independent laboratory on a different microarray platform. In total, 413 skin biopsy samples from 213 individuals were analyzed in the training and testing cohorts.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Repeated cross\u2010fold validation identified consistent and discriminative markers using multinomial elastic net, performing with an average classification accuracy of 87.1% with high sensitivity and specificity. In external validation, the classifier achieved an average accuracy of 85.4%. Reanalyzing data from a previous study, we identified subsets of patients that represent the canonical inflammatory, fibroproliferative, and normal\u2010like subsets.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>We developed a highly accurate classifier for <jats:styled-content style=\"fixed-case\">SS<\/jats:styled-content>c molecular subsets for individual patient samples. The method can be used in <jats:styled-content style=\"fixed-case\">SS<\/jats:styled-content>c clinical trials to identify an intrinsic subset on individual samples. Our method provides a robust data\u2010driven approach to aid clinical decision\u2010making and interpretation of heterogeneous molecular information in <jats:styled-content style=\"fixed-case\">SS<\/jats:styled-content>c patients.<\/jats:p><\/jats:sec>","DOI":"10.1002\/art.40898","type":"journal-article","created":{"date-parts":[[2019,3,28]],"date-time":"2019-03-28T10:51:57Z","timestamp":1553770317000},"page":"1701-1710","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":74,"title":["A Machine Learning Classifier for Assigning Individual Patients With Systemic Sclerosis to Intrinsic Molecular Subsets"],"prefix":"10.1002","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2400-5431","authenticated-orcid":false,"given":"Jennifer M.","family":"Franks","sequence":"first","affiliation":[{"name":"Geisel School of Medicine at Dartmouth Department of Molecular and Systems Biology  Hanover and Lebanon New Hampshire"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viktor","family":"Martyanov","sequence":"additional","affiliation":[{"name":"Geisel School of Medicine at Dartmouth  Hanover New Hampshire"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoshuai","family":"Cai","sequence":"additional","affiliation":[{"name":"Arnold School of Public Health at University of South Carolina  Columbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Geisel School of Medicine at Dartmouth  Hanover New Hampshire"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghui","family":"Li","sequence":"additional","affiliation":[{"name":"Geisel School of Medicine at Dartmouth  Hanover New Hampshire"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tammara A.","family":"Wood","sequence":"additional","affiliation":[{"name":"Geisel School of Medicine at Dartmouth  Hanover New Hampshire"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael L.","family":"Whitfield","sequence":"additional","affiliation":[{"name":"Geisel School of Medicine at Dartmouth Department of Molecular and Systems Biology  Hanover and Lebanon New Hampshire"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2019,9,2]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31407-5"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0002696"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1038\/jid.2011.472"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/jid.2013.130"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004005"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1635114100"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-015-0695-1"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-017-0417-1"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0114017"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(17)30933-9"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1097\/BOR.0000000000000237"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-015-0669-3"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.40358"},{"key":"e_1_2_7_15_1","first-page":"1281","article-title":"Inter and intraobserver variability of total skin thickness score (modified Rodnan TSS) in systemic sclerosis","volume":"22","author":"Clements P","year":"1995","journal-title":"J Rheumatol"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.191367098"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/35021093"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/ng0506-500"},{"key":"e_1_2_7_19_1","unstructured":"WandMP JonesMC.KernSmooth: functions for kernel smoothing supporting Wand & Jones (1995).2015. URL:https:\/\/stat.ethz.ch\/R-manual\/R-devel\/library\/KernSmooth\/html\/00Index.html."},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v033.i01"},{"key":"e_1_2_7_21_1","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw A","year":"2002","journal-title":"R News"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v028.i05"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkw199"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-559"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btt480"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13075-015-0721-3"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/art.39289"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrrheum.2014.137"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1136\/ard.2007.082099"},{"key":"e_1_2_7_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbrc.2008.06.054"},{"key":"e_1_2_7_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty026"}],"container-title":["Arthritis &amp; Rheumatology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/art.40898","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/art.40898","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/art.40898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T20:18:48Z","timestamp":1759954728000},"score":1,"resource":{"primary":{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/10.1002\/art.40898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,2]]},"references-count":30,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["10.1002\/art.40898"],"URL":"https:\/\/doi.org\/10.1002\/art.40898","archive":["Portico"],"relation":{},"ISSN":["2326-5191","2326-5205"],"issn-type":[{"value":"2326-5191","type":"print"},{"value":"2326-5205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,2]]},"assertion":[{"value":"2018-08-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-03-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-09-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}