Epilepsy in children and adolescents harms cognitive development and quality of life, necessitating early risk identification to improve outcomes. Yet, current predictive models yielded inconsistent results, demanding a thorough evaluation of their accuracy and effectiveness to guide future research and inform evidence-based clinical strategies. This review aimed to integrate existing research findings on epilepsy prediction models for children and adolescents. China National Knowledge Infrastructure, Wanfang Database, SinoMed, China Science and Technology Journal Database, PubMed, Embase, CINAHL, and Web of Science were searched from inception to August 31, 2025. The Prediction Model Risk of Bias Assessment Tool was used to assess the risk of bias and applicability. The areas under the curve (AUC) with 95% confidence intervals were pooled using random-effects meta-analysis. The study was registered with PROSPERO (CRD42025637913). A total of 27 studies were included in this review. Sixteen studies were conducted in China. Twenty-five studies were at high risk of bias. The pooled AUC for 14 training models was 0.794 (95% CI: 0.747–0.840). For 17 validation models, the pooled AUC was 0.726 (95% CI: 0.659–0.792). Clinical features + EEG outperformed combinations with MRI in training (0.855 vs 0.725) and validation (0.743 vs 0.655). Non-machine learning models surpassed machine learning (training: 0.838 vs 0.717; validation: 0.778 vs 0.654), but the difference might not be statistically significant as the 95% CIs are overlapped in the validation; and external validation yielded higher AUC (0.807) than internal validation (0.634), though with extreme heterogeneity (I² = 90.93%). Current research showed uneven regional distribution. Models based on clinical features + EEG warrants further exploration. Predictor selection predominantly relies on univariate analysis, lacking standardized and scientific methodologies. Most studies carry a high risk of bias and rarely undergo validation, limiting their practical applicability. Validating existing models is crucial for identifying flaws and enhancing future research. 10.13039/501100004735 Natural Science Foundation of Hunan Province (grant No. 2024JJ8254).

Objective: This study aims to provide an overview of meta-analyses and systematic reviews on the effectiveness and safety of immunosuppressive drug therapy for neuromyelitis optica spectrum disorders (NMOSD) by evaluating the methodological quality and reporting quality of reviews. Methods: The Chinese National Knowledge Infrastructure (CNKI), WanFang Data, China Science and Technology Journal Database, Web of Science, the Cochrane Library, PubMed, and Embase databases were searched to collect systematic reviews or meta-analyses on the effectiveness and safety of immunosuppressive therapy for NMOSD from inception to December 2, 2021. Two researchers independently screened reviews and extracted data. Any differences in the procession of review assessment between the two researchers were re-evaluated, and the disagreement was resolved by discussion with other researchers. The following data were extracted: author, year of publication, the country where the study was conducted, study type, the number of included studies, sample size, risk bias tools, medication of immunosuppressive therapy, and main outcomes. Then, the AMSTAR-2, which is a critical appraisal tool for systematic reviews (2nd edition), and Grades of Recommendation, Assessment, Development and Evaluation (GRADE) were used to evaluate the methodological quality and reporting quality of evidence. A comprehensive analysis was conducted on the outcomes for all included reviews. Results: A total of 15 reviews were included. Of the included reviews, 3 were systematic reviews, 7 were meta-analyses, and 5 were systematic reviews and meta-analyses. According to the AMSTAR-2 criteria, 6 studies had high quality, 1 study had moderate quality, 4 studies had low quality, and 4 studies had critically low quality. Based on the GRADE, neither evidence quality for effectiveness nor safety was high. Conclusions: Immunosuppressive drug therapy is effective for patients with NMOSD, but its safety is controversial. Due to the poor quality of evidence, reliability needs to be considered. Thus, large sample, multi-center, double-blind, randomized controlled studies are still needed in the future.