Radiomics-clinical model enhances prediction of difficult laparoscopic cholecystectomy

A novel predictive model combining preoperative CT radiomics and clinical data effectively identifies patients at risk for difficult laparoscopic cholecystectomy (DLC). An analysis of 2,055 cases revealed a top-performing model using random forest algorithms, achieving an AUC of 0.938 in the training cohort and 0.874 in validation. The model incorporates ten key features, including gallbladder wall thickness and inflammatory markers, outshining previous models and supporting safer surgical strategies tailored to individual patient needs.