Spondyloarthritis & psoriatic arthritis
Efficacy of Risankizumab across distinct psoriatic arthritis (PsA) phenotypes identified with machine learning analytics using data from biologic DMARD-Naïve patients in two phase 3 clinical trials
Authors' conclusion
Five distinct PsA phenotypes were identified in patients starting risankizumab. Moderate to High Disease Activity, the most frequent phenotype, showed the highest response, though risankizumab demonstrated efficacy across all phenotypes.
Study context
- Population
- bDMARD-naïve PsA patients treated with risankizumab for ≤ 4 years (196 weeks) in KEEPsAKE 1 and KEEPsAKE 25 phenotypes
- Participants
- 1,119 patients
- Comparison
- Distinct PsA phenotypes identified with machine learning, all treated with risankizumab
- Primary endpoint
- Classification of PsA patients into distinct phenotypes using machine learning (ML); response to risankizumab defined as MDA and DAPSA LDA
- Follow-up
- 4 years
Methodological detailsunsupervised machine learning (finite mixture model), biologic DMARD-naïve patients
- Unsupervised machine learning (finite mixture model)
- Biologic DMARD-naïve patients
Primary result
As reported in the abstract
Response to risankizumab across phenotypes (MDA; DAPSA LDA)
Minimal disease activity (MDA), range across phenotypes
42.9% to 58.8%
Disease Activity in PsA (DAPSA) low disease activity (LDA), range across phenotypes
66.0% to 82.0%
Original publication
Efficacy of Risankizumab across distinct PsA phenotypes identified with machine learning analytics using data from biologic DMARD-Naïve patients in two phase 3 clinical trials. Arthritis Res Ther. Published 29 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →