Spondyloarthritis & psoriatic arthritis
Identification of psoriatic arthritis (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
Authors' conclusion
Unsupervised machine learning identified eight PsA phenotype clusters with significant differences in demographics, clinical features and treatment responses.
Study context
- Population
- Bio-naïve patients with active PsA receiving guselkumab 100 mg every 8/4 weeks8 clusters
- Participants
- 661 patients
- Comparison
- Cluster 1 vs Cluster 2 vs Cluster 3 vs Cluster 4 vs Cluster 5 vs Cluster 6 vs Cluster 7 vs Cluster 8
- Primary endpoint
- Hypothesis-free PsA phenotype clusters identified by unsupervised machine learning
Methodological detailsunsupervised machine learning cluster analysis, pooled data, retrospective, non-negative matrix factorisation
- Unsupervised machine learning cluster analysis
- Pooled data
- Retrospective
- Non-negative matrix factorisation
Primary result
As reported in the abstract
PsA phenotype clusters
- Eight clusters identified: feet dominant; male, overweight, psoriasis dominant; hand dominant; dactylitis dominant; enthesitis, large joints; enthesitis, small joints; axial dominant; female, obese, large joints
- 8
Further findings
Minimal disease activity (MDA) response · week 24
- Highest in cluster 2; lowest in clusters 3, 5 and 6
MDA response · week 52
- Highest in cluster 2; lowest in cluster 5
DAPSA low disease activity (LDA) and remission · weeks 24 and 52
- Highest in cluster 2 and lowest in clusters 4 and 6, respectively
Response to guselkumab over 52 weeks
- All clusters improved with guselkumab
Original publication
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. RMD Open. Published 31 March 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →