Systematic review and meta-analysis of prediction models for trigeminal neuralgia recurrence

BackgroundPostoperative recurrence remains a major challenge in trigeminal neuralgia surgery. Prediction models are crucial for personalized management, but their quality and performance are unclear.MethodsWe searched eight databases up to September 23, 2025, for studies on trigeminal neuralgia recurrence prediction. Data extraction followed the CHARMS checklist, and risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool. A random-effects model was used to meta-analyze the area under the curve, with subgroup and sensitivity analyses.ResultsTwenty studies (4,291 patients) were included. The pooled area under the curve was 0.86 for the training set and 0.83 for the validation set. The main sources of bias included inaccuracies in predictor measurement, inconsistent definitions of recurrence, and incomplete reporting. Models based on microvascular decompression appeared to perform best. Key predictors included age 65 years or older, disease duration longer than 5 years, atypical pain, and specific surgical approaches.ConclusionThis is the first meta-analysis in this field, and suggests that prediction models for trigeminal neuralgia recurrence demonstrate promising discriminatory performance. However, given the potential risks of bias, publication bias, and heterogeneity, the pooled AUC may be overestimated and should therefore be interpreted with caution.Systematic review registrationhttps://www.crd.york.ac.uk/PROSPERO/recorddashboard, CRD420251153545.