{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:03:31Z","timestamp":1784099011806,"version":"3.55.0"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pediatr."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>JADAS27 is widely used to assess juvenile idiopathic arthritis (JIA) disease activity, but complete scoring is impractical in many clinical settings because it requires simultaneous physician global assessment (PhGA), patient\/parent global assessment (PtGA), active joint count (AJC), and erythrocyte sedimentation rate (ESR). We asked whether non\u2013component clinical variables alone\u2013strictly excluding all four JADAS27 constituents\u2013can classify JADAS27\u2013defined activity strata.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this retrospective multi\u2013center study, 800 patients with JIA were enrolled from CARRA (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009400), PRCSG (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009240), and LHTCM (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009160). Disease activity was categorized as inactive, low, moderate, or high by established JADAS27 cutoffs. PhGA, PtGA, AJC, and ESR were excluded from all model inputs to prevent circular prediction. Thirteen remaining non\u2013component variables (18 encoded features) were used to train four machine learning algorithms on CARRA\u2009+\u2009PRCSG (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009640), with independent external validation on LHTCM (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009160). Pre\u2013specified ablation analyses quantified contributions of proxy variables (CHAQ, pain score, limited joint count).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>SVM achieved the best external validation performance (accuracy 0.731, 95% CI 0.657\u20130.797; macro AUC 0.918, 95% CI 0.887\u20130.945). Class\u2013wise recall was highest for inactive (82.4%) and high activity (77.4%), with most errors between adjacent classes. SHAP and permutation importance analyses consistently identified CHAQ score, JIA subtype, pain score, limited joint count, and C\u2013reactive protein as the most influential predictors. Removing all three proxy variables reduced accuracy to 0.619 and macro AUC to 0.843, indicating that both proxy and non\u2013proxy features contribute independently. Sensitivity analysis with subtype\u2013specific cutoffs yielded comparable performance (accuracy 0.713).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Strictly non\u2013component clinical features can stratify JADAS27\u2013defined disease activity with clinically meaningful external performance. This approach may support early risk stratification when formal JADAS27 scoring is unavailable, and complements rather than replaces physician assessment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fped.2026.1820800","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:03:52Z","timestamp":1784095432000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Non\u2013component clinical feature\u2013based machine learning for disease activity risk stratification in juvenile idiopathic arthritis: a multi\u2013center retrospective validation study"],"prefix":"10.3389","volume":"14","author":[{"given":"Peipei","family":"Dong","sequence":"first","affiliation":[{"name":"Pediatric Department, Lianyungang Hospital of Traditional Chinese Medicine","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Song","sequence":"additional","affiliation":[{"name":"Traditional Chinese Medicine Department, The First People\u2019s Hospital of Lianyungang","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Lianyungang Hospital of Traditional Chinese Medicine","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Lianyungang Hospital of Traditional Chinese Medicine","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyang","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Lianyungang Hospital of Traditional Chinese Medicine","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Lianyungang Hospital of Traditional Chinese Medicine","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Cong","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Lianyungang Hospital of Traditional Chinese Medicine","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuansheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Rheumatology, Lianyungang Hospital of Traditional Chinese Medicine","place":["Lianyungang, Jiangsu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1016\/S0140-6736(07)60363-8","article-title":"Juvenile idiopathic arthritis","volume":"369","author":"Ravelli","year":"2007","journal-title":"Lancet"},{"key":"B2","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.jbspin.2013.09.003","article-title":"Prevalence and incidence of juvenile idiopathic arthritis: a systematic review","volume":"81","author":"Thierry","year":"2014","journal-title":"Joint Bone Spine"},{"key":"B3","first-page":"390","article-title":"International league of associations for rheumatology. International league of associations for rheumatology classification of juvenile idiopathic arthritis: second revision, Edmonton, 2001","volume":"31","author":"Petty","year":"2004","journal-title":"J Rheumatol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2138","DOI":"10.1016\/S0140-6736(11)60244-4","article-title":"Juvenile idiopathic arthritis","volume":"377","author":"Prakken","year":"2011","journal-title":"Lancet"},{"key":"B5","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s12969-016-0085-5","article-title":"Clinical outcome measures in juvenile idiopathic arthritis","volume":"14","author":"Consolaro","year":"2016","journal-title":"Pediatr Rheumatol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1002\/art.24516","article-title":"Development and validation of a composite disease activity score for juvenile idiopathic arthritis","volume":"61","author":"Consolaro","year":"2009","journal-title":"Arthritis Care Res"},{"key":"B7","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High\u2013performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e190606","DOI":"10.1001\/jamanetworkopen.2019.0606","article-title":"Assessment of a deep learning model based on electronic health record data to forecast clinical outcomes in patients with rheumatoid arthritis","volume":"2","author":"Norgeot","year":"2019","journal-title":"JAMA Netw Open"},{"key":"B10","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1002\/bjs.9736","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"102","author":"Collins","year":"2015","journal-title":"J Br Surg"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1320","DOI":"10.1038\/s41591-020-1041-y","article-title":"Minimum information about clinical artificial intelligence modeling: the MI\u2013CLAIM checklist","volume":"26","author":"Norgeot","year":"2020","journal-title":"Nat Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s12969-017-0160-6","article-title":"The new childhood arthritis and rheumatology research alliance (CARRA) registry: design, rationale, and characteristics of patients enrolled in the first 12 months","volume":"15","author":"Beukelman","year":"2017","journal-title":"Pediatr Rheumatol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1186\/s13075-017-1462-2","article-title":"Experience with etanercept, tocilizumab and interleukin\u20131 inhibitors in systemic onset juvenile idiopathic arthritis patients from the BIKER registry","volume":"19","author":"Horneff","year":"2017","journal-title":"Arthritis Res Ther"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1002\/art.1780371209","article-title":"Measurement of health status in children with juvenile rheumatoid arthritis","volume":"37","author":"Singh","year":"1994","journal-title":"Arthritis Rheum"},{"key":"B15","doi-asserted-by":"publisher","first-page":"938","DOI":"10.3899\/jrheum.100930","article-title":"A new approach to clinical care of juvenile idiopathic arthritis: the juvenile arthritis multidimensional assessment report","volume":"38","author":"Filocamo","year":"2011","journal-title":"J Rheumatol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support\u2013vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"B17","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann Stat"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied Logistic Regression","author":"Hosmer","year":"2013"},{"key":"B20","doi-asserted-by":"publisher","first-page":"20150202","DOI":"10.1098\/rsta.2015.0202","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philos Trans A Math Phys Eng Sci"},{"key":"B21","first-page":"2825","article-title":"Scikit\u2013learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"B22","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1186\/s12874-025-02515-3","article-title":"Handling of missing component information for common composite score outcomes used in axial spondyloarthritis research when complete\u2013case analysis is unbiased","volume":"25","author":"Polysopoulos","year":"2025","journal-title":"BMC Med Res Methodol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1136\/ard.2008.100156","article-title":"The responsiveness of joint counts, patient\u2013reported measures and proposed composite scores in hand osteoarthritis: analyses from a placebo\u2013controlled trial","volume":"69","author":"Haugen","year":"2010","journal-title":"Ann Rheum Dis"},{"key":"B24","doi-asserted-by":"publisher","first-page":"68","DOI":"10.2174\/1874213001003020068","article-title":"Strengths and weaknesses of quantitative climate reconstructions based on late\u2013quaternary biological proxies","volume":"3","author":"Birks","year":"2010","journal-title":"Open Ecology J"},{"key":"B25","first-page":"189","article-title":"Current validated clinical and patient reported disease outcome measures in juvenile idiopathic arthritis","author":"Balay\u2013Dustrude","year":"2023","journal-title":"Open Access Rheumatol Res Rev"},{"key":"B26","doi-asserted-by":"publisher","first-page":"603","DOI":"10.3899\/jrheum.2023-0722","article-title":"Psychometric properties of patient global assessment in psoriatic arthritis: a systematic literature review","volume":"51","author":"Chessa","year":"2024","journal-title":"J Rheumatol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"134797","DOI":"10.1016\/j.jclepro.2022.134797","article-title":"Modeling circularity as functionality over use\u2013time to reflect on circularity indicator challenges and identify new indicators for the circular economy","volume":"379","author":"Hatzfeld","year":"2022","journal-title":"J Clean Prod"},{"key":"B28","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1093\/rheumatology\/ket310","article-title":"Interpretation of the juvenile arthritis disease activity score: responsiveness, clinically important differences and levels of disease activity in prospective cohorts of patients with juvenile idiopathic arthritis","volume":"53","author":"Bulatovi\u0107 \u0106alasan","year":"2014","journal-title":"Rheumatology"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e1002750","DOI":"10.1371\/journal.pmed.1002750","article-title":"Patterns of joint involvement in juvenile idiopathic arthritis and prediction of disease course: a prospective study with multilayer non\u2013negative matrix factorization","volume":"16","author":"Eng","year":"2019","journal-title":"PLoS Med"}],"container-title":["Frontiers in Pediatrics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1820800\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:03:53Z","timestamp":1784095433000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1820800\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":29,"alternative-id":["10.3389\/fped.2026.1820800"],"URL":"https:\/\/doi.org\/10.3389\/fped.2026.1820800","relation":{},"ISSN":["2296-2360"],"issn-type":[{"value":"2296-2360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1820800"}}