Cluster-defined gout subtypes exhibit divergent chronic kidney disease trajectories: a machine learning approach in a Chinese prospective cohort
Authors' conclusion
This study proposes a novel K-means clustering-based classification of gout, identifying subgroups with distinct CKD trajectories.
Study context
- Population
- Chinese gout patients
- Participants
- 1,497 patients4,166 person-years
- Exposure
- Data-driven clinical clusters of gout compared for chronic kidney disease (CKD) progression
- Outcome
- Incidence of CKD stage ≥3
Methodological detailsK-means clustering, Cox proportional hazards models, unweighted genetic risk score (20 SNPs)
- K-means clustering
- Cox proportional hazards models
- Unweighted genetic risk score (20 SNPs)
Main finding
As reported in the abstract
CKD stage ≥3
Each group vs cluster 1Adjusted hazard ratio (95% CI)
Cluster 4
2.19(1.20–4.01)
Cluster 5
3.52(1.91–6.48)
- Overall incidence of CKD stage ≥3
- 153 (10.22%)
Observational data: associations, not effects.
Further findings
Genetic risk score
- Genetic predisposition further amplified renal risk in Cluster 4
Target serum urate (SU) and kidney stone reduction
- Achieving target SU and reduced kidney stone burden independently associated with lower risk of CKD progression
Original publication
Cluster-defined gout subtypes exhibit divergent chronic kidney disease trajectories: a machine learning approach in a Chinese prospective cohort. Rheumatology (Oxford). Published 3 April 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →