Machine learning to predict pediatric choledocholithiasis: A Western Pediatric Surgery Research Consortium retrospective study

This multicenter study developed a machine learning model using nine clinical and laboratory features to predict choledocholithiasis in pediatric cholecystectomy patients with 93.5% accuracy. The Extra-Trees algorithm identified key predictors including CBD diameter, liver enzymes, and bilirubin levels in 1,597 patients across 10 institutions.