Uncovering the heterogeneity of disease impact in axial spondyloarthritis: bivariate trajectories of disease activity and quality of life

Abstract

Objective: The goal of managing axial spondyloarthritis (axSpA) is to improve and maintain patients' health-related quality of life (HRQoL), mainly through targeting towards low disease activity. Here, we aim to gain insight into the joint evolution of HRQoL and disease activity by identifying and characterising latent subgroups of patients with longstanding disease displaying similar trajectories throughout 8 years of follow-up.

Methods: Data from Outcome in Ankylosing Spondylitis (AS) International Study (n=161) and Groningen Leeuwarden AS cohort (n=264) were used. Biennially, HRQoL was assessed by AS Quality of Life (ASQoL) and disease activity by AS Disease Activity Score-C reactive protein (ASDAS-CRP). Bivariate trajectories of these outcomes were estimated by group-based trajectory modelling. Next, trajectories were profiled by comparing the latent groups with respect to baseline factors using analysis of variance and χ² test.

Results: Five bivariate trajectories were distinguished, in which ASQoL and ASDAS-CRP were tightly linked: (t1) low impact of disease; (t2) moderate impact; (t3) high impact with major improvement; (t4) high impact with some improvement; (t5) very high impact. Profiling revealed, for example, that (t1) was characterised by male gender and Human Leucocyte Antigen B27 positivity; (t3) by younger age, shorter symptom duration and biological intake and (t5) by the highest proportion of females.

Conclusions: We identified five bivariate trajectories of HRQoL and disease activity demonstrating a clear mutual relationship. The profiles revealed that both individual-related and disease-related features define the type of disease course in respect to HRQoL and disease activity in axSpA. This may provide clinicians insight into the differences among patients and help in the management of the disease.

Keywords: axial spondyloarthritis; disease activity; group-based multi-trajectory modelling; health-related quality of life; trajectories.

Figure 1

Joint trajectory latent classes of ASQoL–ASDAS-CRP. At the top: spaghetti plots of observed ASQoL and ASDAS-CRP values for each individual over a period of 8 years (five measurements), coloured according to their final latent class assignment. Note that each class is represented by both an ASQoL and an ASDAS-CRP trajectory. At the bottom: estimated average trajectories’ lines with corresponding 95% confidence bands and baseline prevalence. ASDAS-CRP, Ankylosing Spondylitis Disease Activity Score—C reactive protein; ASQoL, Ankylosing Spondylitis Quality of Life.