{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:38:26Z","timestamp":1782409106553,"version":"3.54.5"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1011073","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T00:00:00Z","timestamp":1686700800000}}],"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Cycling of biologic or targeted synthetic disease modifying antirheumatic drugs (b\/tsDMARDs) in rheumatoid arthritis (RA) patients due to non-response is a problem preventing and delaying disease control. We aimed to assess and validate treatment response of b\/tsDMARDs among clusters of RA patients identified by deep learning. We clustered RA patients clusters at first-time b\/tsDMARD (cohort entry) in the Swiss Clinical Quality Management in Rheumatic Diseases registry (SCQM) [1999\u20132018]. We performed comparative effectiveness analyses of b\/tsDMARDs (ref. adalimumab) using Cox proportional hazard regression. Within 15 months, we assessed b\/tsDMARD stop due to non-response, and separately a \u226520% reduction in DAS28-esr as a response proxy. We validated results through stratified analyses according to most distinctive patient characteristics of clusters. Clusters comprised between 362 and 1481 patients (3516 unique patients). Stratified (validation) analyses confirmed comparative effectiveness results among clusters: Patients with \u22652 conventional synthetic DMARDs and prednisone at b\/tsDMARD initiation, male patients, as well as patients with a lower disease burden responded better to tocilizumab than to adalimumab (hazard ratio [HR] 5.46, 95% confidence interval [CI] [1.76\u201316.94], and HR 8.44 [3.43\u201320.74], and HR 3.64 [2.04\u20136.49], respectively). Furthermore, seronegative women without use of prednisone at b\/tsDMARD initiation as well as seropositive women with a higher disease burden and longer disease duration had a higher risk of non-response with golimumab (HR 2.36 [1.03\u20135.40] and HR 5.27 [2.10\u201313.21], respectively) than with adalimumab. Our results suggest that RA patient clusters identified by deep learning may have different responses to first-line b\/tsDMARD. Thus, it may suggest optimal first-line b\/tsDMARD for certain RA patients, which is a step forward towards personalizing treatment. However, further research in other cohorts is needed to verify our results.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1011073","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T18:24:49Z","timestamp":1685730289000},"page":"e1011073","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":18,"title":["Patient groups in Rheumatoid arthritis identified by deep learning respond differently to biologic or targeted synthetic DMARDs"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4581-8810","authenticated-orcid":true,"given":"Maria","family":"Kalweit","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7082-8530","authenticated-orcid":true,"given":"Andrea M.","family":"Burden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joschka","family":"Boedecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3276-9581","authenticated-orcid":true,"given":"Thomas","family":"H\u00fcgle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1313-4473","authenticated-orcid":true,"given":"Theresa","family":"Burkard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,6,2]]},"reference":[{"key":"pcbi.1011073.ref001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/nrdp.2018.1","article-title":"Rheumatoid arthritis","volume":"4","author":"JS Smolen","year":"2018","journal-title":"Nat Rev Dis Primers"},{"key":"pcbi.1011073.ref002","first-page":"1","article-title":"EULAR recommendations for the management of rheumatoid arthritis with synthetic and biological disease-modifying antirheumatic drugs: 2019 update","author":"JS Smolen","year":"2020","journal-title":"Ann Rheum Dis"},{"issue":"5","key":"pcbi.1011073.ref003","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1093\/rheumatology\/kev421","article-title":"Personalized biological treatment for rheumatoid arthritis: A systematic review with a focus on clinical applicability","volume":"55","author":"BVJ Cuppen","year":"2016","journal-title":"Rheumatology (United Kingdom)"},{"issue":"7","key":"pcbi.1011073.ref004","first-page":"1","article-title":"Deep Learning to Assess Long-term Mortality from Chest Radiographs","volume":"2","author":"MT Lu","year":"2019","journal-title":"JAMA Netw Open"},{"issue":"1","key":"pcbi.1011073.ref005","first-page":"1","article-title":"Development of machine learning-based clinical decision support system for hepatocellular carcinoma","volume":"10","author":"GH Choi","year":"2020","journal-title":"Sci Rep"},{"issue":"1","key":"pcbi.1011073.ref006","first-page":"1","article-title":"Applied machine learning and artificial intelligence in rheumatology","volume":"4","author":"M H\u00fcgle","year":"2021","journal-title":"Rheumatol Adv Pract"},{"issue":"6","key":"pcbi.1011073.ref007","doi-asserted-by":"crossref","first-page":"e0252289","DOI":"10.1371\/journal.pone.0252289","article-title":"Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network","volume":"16","author":"M Kalweit","year":"2021","journal-title":"PLoS One"},{"issue":"12","key":"pcbi.1011073.ref008","doi-asserted-by":"crossref","first-page":"1987","DOI":"10.1002\/art.41056","article-title":"Machine Learning to Predict Anti\u2013Tumor Necrosis Factor Drug Responses of Rheumatoid Arthritis Patients by Integrating Clinical and Genetic Markers","volume":"71","author":"Y Guan","year":"2019","journal-title":"Arthritis and Rheumatology"},{"issue":"6","key":"pcbi.1011073.ref009","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1002\/art.41622","article-title":"The Pretreatment Gut Microbiome Is Associated With Lack of Response to Methotrexate in New-Onset Rheumatoid Arthritis","volume":"73","author":"A Artacho","year":"2021","journal-title":"Arthritis and Rheumatology"},{"issue":"8","key":"pcbi.1011073.ref010","first-page":"2006","article-title":"Subgrouping of rheumatoid arthritis patients based on pain, fatigue, inflammation and psychosocial factors","volume":"66","author":"YC Lee","year":"2014","journal-title":"Arhtiritis Rheumatol"},{"issue":"4","key":"pcbi.1011073.ref011","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1002\/acr.24471","article-title":"Data-Driven Patient Clustering and Differential Clinical Outcomes in the Brigham and Women\u2019s Rheumatoid Arthritis Sequential Study Registry","volume":"73","author":"JR Curtis","year":"2021","journal-title":"Arthritis Care Res (Hoboken)"},{"key":"pcbi.1011073.ref012","article-title":"Clinical phenotype with high risk for initiation of biologic therapy in rheumatoid arthritis: a data-driven cluster analysis Unsupervised clustering of RA \/ S.M. Jung","volume":"39","author":"S Jung","year":"2022","journal-title":"Clinical and Experimental Rheumatology"},{"issue":"5","key":"pcbi.1011073.ref013","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1080\/03009742.2021.1944306","article-title":"Cluster analysis identifies unmet healthcare needs among patients with rheumatoid arthritis","volume":"51","author":"N Mars","year":"2022","journal-title":"Scand J Rheumatol"},{"issue":"5","key":"pcbi.1011073.ref014","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1002\/art.40428","article-title":"Identification of Three Rheumatoid Arthritis Disease Subtypes by Machine Learning Integration of Synovial Histologic Features and RNA Sequencing Data","volume":"70","author":"DE Orange","year":"2018","journal-title":"Arthritis Rheumatol"},{"issue":"5","key":"pcbi.1011073.ref015","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1093\/rheumatology\/39.5.542","article-title":"Clinical quality management in rheumatoid arthritis: Putting theory into practice","volume":"39","author":"E Uitz","year":"2000","journal-title":"Rheumatology"},{"issue":"1","key":"pcbi.1011073.ref016","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1002\/art.21491","article-title":"The effectiveness of anti-tumor necrosis factor therapy in preventing progressive radiographic joint damage in rheumatoid arthritis: A population-based study","volume":"54","author":"A Finckh","year":"2006","journal-title":"Arthritis Rheum"},{"key":"pcbi.1011073.ref017","first-page":"1753","article-title":"Improved deep embedded clustering with local structure preservation","volume":"0","author":"X Guo","year":"2017","journal-title":"IJCAI International Joint Conference on Artificial Intelligence"},{"key":"pcbi.1011073.ref018","unstructured":"Kalweit M, Kalweit G, Boedecker J. AnyNets: Adaptive Deep Neural Networks for Medical Data with Missing Values. Accepted at IJCAI 2021 Workshop on Artificial Intelligence for Function, Disability, and Health. 2nd Workshop on Artificial Intelligence for Function, Disability, and Health. 2021;"},{"key":"pcbi.1011073.ref019","volume-title":"Statistical Analysis with Missing Data","author":"J. A. Roderick","year":"2014","edition":"2"},{"key":"pcbi.1011073.ref020","first-page":"37","article-title":"Autoencoders, Unsupervised Learning, and Deep Architectures","author":"P Baldi","year":"2012","journal-title":"ICML Unsupervised and Transfer Learning"},{"issue":"1","key":"pcbi.1011073.ref021","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1093\/bib\/bbz170","article-title":"Deep learning-based clustering approaches for bioinformatics","volume":"22","author":"MR Karim","year":"2021","journal-title":"Brief Bioinform"},{"key":"pcbi.1011073.ref022","author":"A Vaswani","year":"2017","journal-title":"Attention Is All You Need"},{"issue":"2","key":"pcbi.1011073.ref023","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.jbspin.2012.05.003","article-title":"Disease activity in rheumatoid arthritis patients at initiation of biologic agents and 1 year of treatment: Results from the Swiss SCQM registry","volume":"80","author":"P Zufferey","year":"2013","journal-title":"Joint Bone Spine"},{"issue":"9","key":"pcbi.1011073.ref024","doi-asserted-by":"crossref","first-page":"2759","DOI":"10.1007\/s00296-011-2033-5","article-title":"Impact of patient and disease characteristics on therapeutic success during adalimumab treatment of patients with rheumatoid arthritis: Data from a German noninterventional observational study","volume":"32","author":"S Kleinert","year":"2012","journal-title":"Rheumatol Int"},{"issue":"1","key":"pcbi.1011073.ref025","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1093\/rheumatology\/ket301","article-title":"Predictors of response and remission in a large cohort of rheumatoid arthritis patients treated with tocilizumab in clinical practice","volume":"53","author":"YM Pers","year":"2014","journal-title":"Rheumatology (United Kingdom)"},{"issue":"1","key":"pcbi.1011073.ref026","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.semarthrit.2017.01.008","article-title":"Golimumab in real-life settings: 2 Years drug survival and predictors of clinical outcomes in rheumatoid arthritis, spondyloarthritis, and psoriatic arthritis","volume":"47","author":"F Iannone","year":"2017","journal-title":"Semin Arthritis Rheum"},{"issue":"2","key":"pcbi.1011073.ref027","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1093\/rheumatology\/keaa259","article-title":"Effect of disease duration and other characteristics on efficacy outcomes in clinical trials of tocilizumab for rheumatoid arthritis","volume":"60","author":"A Rubbert-Roth","year":"2021","journal-title":"Rheumatology (United Kingdom)"},{"issue":"1","key":"pcbi.1011073.ref028","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.semarthrit.2012.11.007","article-title":"Rheumatoid factor as predictor of response to abatacept, rituximab and tocilizumab in rheumatoid arthritis: Systematic review and meta-analysis","volume":"43","author":"RJ Maneiro","year":"2013","journal-title":"Semin Arthritis Rheum"},{"issue":"Suppl 1","key":"pcbi.1011073.ref029","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1136\/annrheumdis-2020-eular.4029","article-title":"THU0206 \u0410 VERY EARLY (7\u201328 DAYS) RESPONSE ON JAK INHIBITOR TOFACITINIB IN PATIENTS WITH ACTIVE RHEUMATOID ARTHRITIS: EFFECT ON PAIN AND CENTRAL SENSITIZATION","volume":"79","author":"A Karateev","year":"2020","journal-title":"Ann Rheum Dis"},{"issue":"Suppl 1","key":"pcbi.1011073.ref030","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1136\/annrheumdis-2020-eular.3118","article-title":"THU0205 RESPONSE TO SMALL MOLECULES IS MOSTLY DRIVEN BY PATIENT GLOBAL ASSESSMENT OF DISEASE: A REAL WORLD OBSERVATION","volume":"79","author":"C Joseph","year":"2020","journal-title":"Ann Rheum Dis"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1011073","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T00:00:00Z","timestamp":1686700800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T17:43:58Z","timestamp":1686764638000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1011073"}},"subtitle":[],"editor":[{"given":"Jennifer","family":"Wilson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,6,2]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,6,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1011073","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1011073","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,2]]}}}