NPJ Digit Med. 2026 Apr 23. doi: 10.1038/s41746-026-02640-3. Online ahead of print.
ABSTRACT
This systematic review evaluated the performance and risk of bias in Systemic Lupus Erythematosus (SLE) disease manifestations and case fatality prediction models, based on a search of PubMed, Embase, and Cochrane Library up to October 17, 2025. Risk of bias was assessed using the Prediction model Risk Of Bias Assessment Tool (PROBAST). A random-effects meta-analysis pooled the Area Under the Curve (AUC) values with 95% Confidence Intervals (CIs), with sensitivity and subgroup analyses. The study included 35 studies comprising 89 prediction models, primarily from China (92.3%). Designs were mainly cross-sectional (46.2%) or retrospective cohort (42.3%). Common predictor categories included immunologic/autoantibody profile s (n = 148) and biochemical parameters (n = 126). During development, pulmonary (AUC = 0.92, 95% CI: 0.78-0.87), perinatal (0.92, 0.83-1.03), and case fatality models (0.91, 0.89-0.95) performed highly, while cardiovascular models scored lower (0.78, 0.74-0.81). Upon validation, pulmonary models remained superior (0.86, 0.81-0.91); perinatal (0.82, 0.77-0.87) and cardiovascular models (0.80, 0.76-0.83) remained robust, whereas case fatality models declined markedly. Machine learning models showed greater potential for pulmonary outcomes (0.83, 0.78-0.89). Predictor number improved renal model performance but reduced accuracy for case fatality. All 89 models were rated high risk of bias and mostly low applicability per PROBAST.
PMID:42026152 | DOI:10.1038/s41746-026-02640-3