Identification of PsA phenotypes with machine learning analytics using data from two phase III clinical trials of guselkumab in a bio-naïve population of patients with PsA.

OBJECTIVES: Psoriatic arthritis (PsA) phenotypes are typically defined by their clinical components, which may not reflect patients' overlapping symptoms. This post hoc analysis aimed to identify hypothesis-free PsA phenotype clusters using machine learning to analyse data from the phase III DISCOVER-1/DISCOVER-2 clinical trials. METHODS: Pooled data from bio-naïve patients with active PsA receiving guselkumab 100 mg every 8/4 weeks were retrospectively analysed. Non-negative matrix factorisation was applied as an unsupervised machine learning technique to identify PsA phenotype clusters; baseline patient characteristics and clinical observations were input features. Minimal disease activity (MDA), disease activity index for psoriatic arthritis (DAPSA) low disease activity (LDA) and DAPSA remission at weeks 24 and 52 were evaluated. RESULTS: Eight clusters (n=661) were identified: cluster 1 (feet dominant), cluster 2 (male, overweight, psoriasis dominant), cluster 3 (hand dominant), cluster 4 (dactylitis dominant), cluster 5 (enthesitis, large joints), cluster 6 (enthesitis, small joints), cluster 7 (axial dominant) and cluster 8 (female, obese, large joints). At week 24, MDA response was highest in cluster 2 and lowest in clusters 3, 5 and 6; at week 52, it was highest in cluster 2 and lowest in cluster 5. At weeks 24 and 52, DAPSA LDA and remission were highest in cluster 2 and lowest in clusters 4 and 6, respectively. All clusters improved with guselkumab treatment over 52 weeks. CONCLUSIONS: Unsupervised machine learning identified eight PsA phenotype clusters with significant differences in demographics, clinical features and treatment responses. In the future, such data could help support individualised treatment decisions.

Efficacy and safety of guselkumab in patients with active psoriatic arthritis who are inadequate responders to tumour necrosis factor inhibitors: results through one year of a phase IIIb, randomised, controlled study (COSMOS).

OBJECTIVE: To evaluate efficacy and safety of guselkumab, an anti-interleukin-23p19-subunit antibody, in patients with psoriatic arthritis (PsA) with prior inadequate response (IR) to tumour necrosis factor inhibitors (TNFi). METHODS: Adults with active PsA (≥3 swollen and ≥3 tender joints) who discontinued ≤2 TNFi due to IR (lack of efficacy or intolerance) were randomised (2:1) to subcutaneous guselkumab 100 mg or placebo at week 0, week 4, then every 8 weeks (Q8W) through week 44. Patients receiving placebo crossed over to guselkumab at week 24. The primary (ACR20) and key secondary (change in HAQ-DI, ACR50, change in SF-36 PCS and PASI100) endpoints, at week 24, underwent fixed-sequence testing (two-sided α=0.05). Adverse events (AEs) were assessed through week 56. RESULTS: Among 285 participants (female (52%), one (88%) or two (12%) prior TNFi), 88% of 189 guselkumab and 86% of 96 placebo→guselkumab patients completed study agent through week 44. A statistically significantly higher proportion of patients receiving guselkumab (44.4%) than placebo (19.8%) achieved ACR20 (%difference (95% CI): 24.6 (14.1 to 35.2); multiplicity-adjusted p<0.001) at week 24. Guselkumab was superior to placebo for each key secondary endpoint (multiplicity-adjusted p<0.01). ACR20 response (non-responder imputation) in the guselkumab group was 58% at week 48; >80% of week 24 responders maintained response at week 48. Through week 24, serious AEs/serious infections occurred in 3.7%/0.5% of 189 guselkumab-randomised and 3.1%/0% of 96 placebo-randomised patients; the guselkumab safety profile was similar through week 56, with no deaths or opportunistic infections. CONCLUSION: Guselkumab significantly improved joint and skin manifestations and physical function in patients with TNFi-IR PsA. A favourable benefit-risk profile was demonstrated through 1 year. TRIAL REGISTRATION NUMBER: NCT03796858.