Risk prediction model for cervical lymph node metastasis of papillary thyroid microcarcinoma: a systematic review and meta-analysis.

Background: A growing number of risk prediction models for cervical lymph node metastasis (CLNM) in papillary thyroid microcarcinoma (PTMC) have been developed, but their performance and methodological rigor remain unclear. This study systematically reviews these models to evaluate their predictive performance and critically appraise their risk of bias. Methods: We conducted a systematic search of seven databases up to July 29, 2025. The methodological quality of the included studies was assessed using PROBAST. Model performance, measured by the area under the curve (AUC), was pooled using a random-effects meta-analysis. Results: A total of 15 studies, comprising 24 predictive models, were included. The pooled AUC was 0.794 (95% CI: 0.769-0.820), but with substantial heterogeneity ( Conclusion: Although existing CLNM prediction models for PTMC show moderate to good discrimination on average, their clinical utility is severely limited by widespread methodological weaknesses and a high risk of bias. The current evidence is not robust enough to recommend any specific model for routine clinical use, and future research must prioritize methodological rigor and independent external validation.