Answers are grounded in this paper and cite their sources.
Objectives This study aimed to identify the independent predictors and develop a predictive model for autoimmune encephalitis (AE) in pediatric populations. Methods This retrospective study comprised 88 pediatric patients with encephalitis (37 AE cases and 51 non- AE cases) at Children’s Hospital Affiliated to Shandong University between May 2020 and April 2025. Lasso regression analysis, univariate and multivariate logistic analysis was used to identify autoimmune encephalitis associated risk factors. The nomogram visualized the results. Receiver operating characteristic (ROC) curves, calibration plots, Brier scoring and decision curve analysis (DCA) were used to evaluate the diagnostic model. Results 16 clinical variables significantly differed between the autoimmune encephalitis and non-autoimmune encephalitis groups. Lasso regression analysis, univariate and multivariate logistic analysis identified four significant independent predictors: age (OR: 1.44; 95% CI: 1.09–1.91; P = 0.010), proteins in the cerebrospinal fluid/100(C.Protein.100) (OR: 0.80; 95% CI: 0.65–1.00; P = 0.049), chloride in the cerebrospinal fluid(C. Chloride) (OR: 1.38; 95% CI: 1.00–1.92; P = 0.050), and spontaneous remission (OR: 21.14; 95% CI: 3.17–141.17; P = 0.002) were risk factors for autoimmune encephalitis. The predictive model demonstrated excellent discrimination (AUC 0.976, 95% CI 0.947-1.000) and calibration (Hosmer-Lemeshow p = 0.886, R²=0.9796, Brier score 0.052). Conclusions This study established and validated a high-performance predictive model incorporating four clinically accessible parameters for the diagnosis of pediatric autoimmune encephalitis.
No takes yet. Share an insight, caveat, or question.
Sun et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: