Vasculitis & polymyalgia rheumatica

Clinical phenotypes of ANCA-associated vasculitis using ensemble clustering: prognostic and therapeutic insights from two Japanese cohorts

Rheumatology (Oxford)Published Retrospective cohort study

Authors' conclusion

Organ involvement-based ensemble clustering identifies clinically meaningful and reproducible AAV phenotypes with distinct prognostic and therapeutic profiles.

Study context

Population
Patients with newly diagnosed microscopic polyangiitis (MPA) or granulomatosis with polyangiitis (GPA) in two nationwide Japanese registries
Participants
726 patients
Exposure
Data-driven organ-involvement phenotypes of MPA and GPA
Outcome
Data-driven clinical phenotypes based on patterns of organ involvement
Methodological detailsmulticentre, two nationwide Japanese registries (J-CANVAS derivation; JPVAS validation), ensemble clustering, classification and regression tree (CART) replication
  • Multicentre
  • Two nationwide Japanese registries (J-CANVAS derivation; JPVAS validation)
  • Ensemble clustering
  • CART replication

Main finding

As reported in the abstract

Clinical phenotypes identified by ensemble clustering
  • Four reproducible clinical phenotypes identified: renal-dominant without interstitial lung disease (ILD); renal-dominant with ILD; systemic multi-organ; Ear, nose and throat (ENT)-dominant
  • CART reproduced these clusters with good concordance

Observational data: associations, not effects.

Further findings

Overall survival and relapse incidence

Overall survival and relapse incidence differed across clusters
ENT-dominant: favourable survival but higher relapse risk

Relapse-free survival with RTX vs CYC in ENT-dominant cluster

Trend towards improved relapse-free survival with RTX compared with CYC, even among MPO-ANCA-positive patients

Original publication

Clinical phenotypes of ANCA-associated vasculitis using ensemble clustering: prognostic and therapeutic insights from two Japanese cohorts. Rheumatology (Oxford). Published 17 September 2026. doi:10.1093/rheumatology/keag483

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.