Artificial Intelligence–Based Diagnostic and Surgical Planning Accuracy in Pediatric Craniofacial and Maxillofacial Surgery: A Systematic Review and Meta-Analysis

Main outcome(s) Segmentation accuracy and diagnostic accuracy. Additional outcome(s) Predictive performance, clinical feasibility, osteotomy accuracy, and workflow efficiency.Data management Two independent reviewers performed study selection, data extraction, and quality assessment using piloted for ms.Discrepancies were resolved through discussion or a third reviewer.Data were analysed using Comprehensive Meta-Analysis software.Quality assessment / Risk of bias analysis Risk of bias was assessed using QUADAS-2 for diagnostic accuracy studies and ROBINS-I for non-randomized segmentation/surgical planning studies. Strategy of data synthesisResults were c o m b i n e d u s i n g r a n d o m -e ff e c t s m o d e l s , accounting for study differences.Heterogeneity and publication bias were statistically examined. Subgroup analysisPlanned but not performed due to limited studies and inconsistent reporting of key variables. Sensitivity analysisConducted by excluding studies with serious risk of bias to ensure robustness of pooled estimates.