A stratified approach to juvenile idiopathic arthritis: leveraging machine learning to uncover subgroups of patients following treatment with etanercept

Stephanie J W Shoop-Worrall; Saskia Lawson-Tovey; UK JIA Biologics Register Investigators, CAPS Investigators, CHARMS Investigators, CLUSTER Consortium; Lucy R Wedderburn; Kimme L Hyrich; Nophar Geifman

doi:10.1093/rap/rkag088

A stratified approach to juvenile idiopathic arthritis: leveraging machine learning to uncover subgroups of patients following treatment with etanercept

Stephanie J W Shoop-Worrall, Saskia Lawson-Tovey, UK JIA Biologics Register Investigators, CAPS Investigators, CHARMS Investigators, CLUSTER Consortium, Lucy R Wedderburn, Kimme L Hyrich Nophar Geifman

Rheumatology advances in practice, Vol.10(3), rkag088

20/07/2026

: https://doi.org/10.1093/rap/rkag088

Biologics

Stratified medicine

Objectives To facilitate a stratified approach to treatment of juvenile idiopathic arthritis (JIA), to uncover trajectory-based patterns of key clinical outcomes following etanercept (ETN) initiation in children and young people (CYP). Methods ETN-naïve CYP with non-systemic JIA recruited to one of three UK, prospective, multicentre cohorts were selected if they started ETN between 2001 and 2019. JADAS71 components (active joint count, physician global assessment (PGA), parent global evaluation (PGE), ESR) were collected in the year following ETN initiation. Clusters of CYP based on JADAS71 component trajectory patterns following ETN initiation were identified using multivariate group-based trajectory models, adjusting for year of ETN initiation. Multinomial logistic regression identified independent predictors of outcome clusters. In a subset of CYP with previously determined MTX trajectories, response clusters were compared descriptively. Results In 1003 CYP, five clusters were identified following ETN initiation. In three clusters, JADAS components changed in parallel: Fast Improvers (16%), Slow Improvers (10%) and Persistent Disease (37%). In two, all components except for one improved over time: Persistent PGA (7%) and Persistent PGE (30%). Where both MTX and ETN trajectories were available (n = 139), 69% of CYP with Persistent Disease following MTX were assigned to other response clusters following ETN initiation. There was high consistency (73%) of CYP having Persistent PGE pattern following both drugs. Conclusions Across multiple disease-modifying anti-rheumatic drugs, JIA disease activity does not always improve to similar degrees across the different features of disease. A majority of CYP initially experiencing Persistent Disease with MTX fall into a response group following ETN.

(1)

url

https://doi.org/10.1093/rap/rkag088

Published (Version of record)

: A stratified approach to juvenile idiopathic arthritis: leveraging machine learning to uncover subgroups of patients following treatment with etanercept
: Stephanie J W Shoop-Worrall - University of Manchester
Saskia Lawson-Tovey - University of Manchester
UK JIA Biologics Register Investigators, CAPS Investigators, CHARMS Investigators, CLUSTER Consortium
Lucy R Wedderburn - Arthritis UK
Kimme L Hyrich
Nophar Geifman (Author) - University of Surrey, School of Health Sciences
: Rheumatology advances in practice, Vol.10(3), rkag088
: Oxford University Press
: 10
: 20/07/2026
: 26/06/2026
: CLUSTER is supported by grants from the Medical Research Council (MRC) [MR/R013926/1] and Versus Arthritis [Grant: 22084], Great Ormond Street Hospital Children’s Charity [VS0518], and Olivia’s Vision. This work is supported by the NIHR Manchester Biomedical Research Centre, the NIHR GOSH Biomedical Research Centre and the British Society for Rheumatology (BSR), and the “UK’s Experimental Arthritis Treatment Centre for Children, supported by Versus Arthritis (grant: 20621)”. LRW is additionally supported by Versus Arthritis (grant: 21593) at the Centre for Adolescent Versus Arthritis. KLH and SSW are additionally supported by the Centre for Epidemiology Versus Arthritis (grant: 21755), SSW additionally by the Medical Research Council (MR/W027151/1) and SLT by the Centre for Genetics and Genomics Versus Arthritis (UK grant number 21754) at the University of Manchester, UK. BSR has previously also received restricted income from Pfizer to fund this project; Childhood Arthritis Prospective Study (CAPS) (funded by Versus Arthritis UK, grant: 20542); Childhood Arthritis Response to Medication Study (CHARMS) (funded by Sparks UK, reference 08ICH09; and the Medical Research Council, reference MR/M004600/1).
: 991147295902346; WOS:001845388300001
: School of Health Sciences
: English
: Journal article
: Information regarding applying for access to UK JIA Biologics Register, CAPS and/or CHARMS data can found at: http://www.caps-jia.org.uk/clinicians-and-researchers/, https://sites.manchester.ac.uk/bcrdbspar/ and https://www.clusterconsortium.org.uk/2349-2/