Patient-reported wellbeing and clinical disease measures over time captured by multivariate trajectories of disease activity in individuals with juvenile idiopathic arthritis in the UK: a multicentre prospective longitudinal study

Abstract

Summary Background Juvenile idiopathic arthritis (JIA) is a heterogeneous disease, the signs and symptoms of which can be summarised with use of composite disease activity measures, including the clinical Juvenile Arthritis Disease Activity Score (cJADAS). However, clusters of children and young people might experience different global patterns in their signs and symptoms of disease, which might run in parallel or diverge over time. We aimed to identify such clusters in the 3 years after a diagnosis of JIA. The identification of these clusters would allow for a greater understanding of disease progression in JIA, including how physician-reported and patient-reported outcomes relate to each other over the JIA disease course. Methods In this multicentre prospective longitudinal study, we included children and young people recruited before Jan 1, 2015, to the Childhood Arthritis Prospective Study (CAPS), a UK multicentre inception cohort. Participants without a cJADAS score were excluded. To assess groups of children and young people with similar disease patterns in active joint count, physician's global assessment, and patient or parental global evaluation, we used latent profile analysis at initial presentation to paediatric rheumatology and multivariate group-based trajectory models for the following 3 years. Optimal models were selected on the basis of a combination of model fit, clinical plausibility, and model parsimony. Finding Between Jan 1, 2001, and Dec 31, 2014, 1423 children and young people with JIA were recruited to CAPS, 239 of whom were excluded, resulting in a final study population of 1184 children and young people. We identified five clusters at baseline and six trajectory groups using longitudinal follow-up data. Disease course was not well predicted from clusters at baseline; however, in both cross-sectional and longitudinal analyses, substantial proportions of children and young people had high patient or parent global scores despite low or improving joint counts and physician global scores. Participants in these groups were older, and a higher proportion of them had enthesitis-related JIA and lower socioeconomic status, compared with those in other groups. Interpretation Almost one in four children and young people with JIA in our study reported persistent, high patient or parent global scores despite having low or improving active joint counts and physician's global scores. Distinct patient subgroups defined by disease manifestation or trajectories of progression could help to better personalise health-care services and treatment plans for individuals with JIA. Funding Medical Research Council, Versus Arthritis, Great Ormond Street Hospital Children's Charity, Olivia's Vision, and National Institute for Health Research.

Predicting long‐term trends in inflammatory neuropathy outcome measures using latent class modelling

“…Future studies, as have been performed in other conditions such as juvenile idiopathic arthritis, incorporating more extensive baseline information and further outcome measures, may allow development of prognostication tools. 15 The optimal model identified in this analysis for predicting the deteriorators ('deteriorator' latent class) was contiguous, sub-MCID deterioration from baseline in two or more outcome measures. All Our findings provide statistical evidence which supports expert guidance 5 to utilise clinical judgement to determine the multiple, disease appropriate outcome measures to best capture an individual's neuropathy-associated impairment.…”

“…This methodology has not previously been used in CIDP or MMNCB, but has been applied to serial outcome measures in other chronic conditions such as inclusion body myositis 14 and juvenile idiopathic arthritis. 15 The objective of our study was to determine, in a single-centre cohort of CIDP and MMNCB patients judged to be clinically stable by the treating clinician, the degree of random variability of commonly used outcome measures. We then aimed to determine if subclinical, non-random trends could be identified from this patient group, using LCMM, which could predict long-term outcome or need for treatment adjustment.…”

Nothing about us without us: involving patient collaborators for machine learning applications in rheumatology

“…Using group-based trajectory models, a form of unsupervised machine learning, we clustered approximately 1200 CYP, based on their recorded number of affected joints, a physician global assessment of their disease activity and a patient global assessment of their well-being over time. 12 The initial results from the clustering analysis revealed a shortlist of models that all fit criteria for good model adequacy, fit and discrimination between identified clusters. 6 These models were brought forward for discussion with key stakeholders through structured workshops.…”

“…Using group-based trajectory models, a form of unsupervised machine learning, we clustered approximately 1200 CYP, based on their recorded number of affected joints, a physician global assessment of their disease activity and a patient global assessment of their well-being over time. 12 …”

“…Figure2(A) Univariate and (B) Multivariate modelling approaches presented as alternatives to the focus groups, adapted from Shoop-Worrall et al12 Both groups considered multivariate modelling (B) more meaningful. Each trajectory represents an average outcome pattern for one cluster of CYP with JIA.…”