- Design
- Multicentre retrospective model development and external validation
- Population
- 443 patients with biopsy-confirmed lupus nephritis, five centres
- Primary outcome
- Identification of proliferative lupus nephritis
- Effect
- AUC 0.852 (development), 0.895 (external validation)
This multicentre retrospective study included 443 patients with biopsy-confirmed lupus nephritis from five centres in China. A model built in one centre (337 patients) was externally validated in four others (106 patients).
The final model uses seven routine variables: lymphocyte percentage, haematuria, leukocyturia, eGFR, uric acid, anti-dsDNA positivity and C3. It discriminated proliferative from non-proliferative nephritis with an AUC of 0.852 in development and 0.895 in external validation, with acceptable calibration.
Biopsy remains the standard, and treatment decisions in lupus nephritis rest on histology. But where biopsy is contraindicated, refused or delayed, a model like this may help judge urgency and the intensity of initial treatment while waiting.
- Kidney biopsy remains the standard for classifying lupus nephritis.
- Where biopsy is delayed or contraindicated, routine variables may help estimate the likelihood of proliferative disease.
- Haematuria, leukocyturia, low C3, anti-dsDNA and reduced eGFR all pointed towards proliferative disease.
- The model has not been validated outside Chinese centres.
Why it matters
Biopsy access limits timely classification of lupus nephritis in many settings.
Don't overread it
Retrospective, small external validation, single-country data.
The statistics, in plain English
An AUC of 0.895 means the model ranks a proliferative case above a non-proliferative one about 90% of the time. Good discrimination does not guarantee the model works in a different population.
Read the rest in the app
You have read your two free briefings this month. The app carries all 27 specialties, every morning, free — and this finding is waiting in it.
Scan to keep reading on your phone. No account needed to start.
Tomorrow morning, before your first patient
One edition a day for rheumatology, written by the desk, every claim tied to its paper. Six minutes.
Get the app — free