Machine learning for screening and predicting the risk of developing uveitis in juvenile idiopathic arthritis
Authors' conclusion
This study established a predictive model using routine clinical indicators to assess the risk of uveitis in JIA patients.
Study context
- Population
- Patients with JIA admitted at Beijing Children's Hospital, 2018–2023
- Participants
- 255 patients
- Exposure
- Training vs Testing
- Outcome
- Prediction of uveitis in JIA (JIA-U)
Methodological detailssingle-centre, stepwise logistic regression and least absolute shrinkage and selection operator (LASSO) regression, calibration and decision curve analysis
- Single-centre
- Stepwise logistic regression and LASSO regression
- Calibration and decision curve analysis
Main finding
As reported in the abstract
Discrimination of nomogram (gender, age at onset, arthritis subtype, ANA status) for uveitis
| Group | AUC | 95% CI |
|---|---|---|
| Training | 0.8417 | 0.775-0.9085 |
| Testing | 0.782 | 0.6752-0.8884 |
AUC
Training0.8417
Testing0.782
95% CI
Training0.775-0.9085
Testing0.6752-0.8884
Observational data: associations, not effects.
Original publication
Machine learning for screening and predicting the risk of developing uveitis in juvenile idiopathic arthritis. Pediatr Rheumatol Online J. Published 11 November 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →