Lin Z, Tang B, Cai J, et al. - Researchers aimed at constructing a radiomics model and a combined model for preoperative prediction of clinically relevant postoperative pancreatic fistula (CR-POPF) in patients undergoing pancreaticoduodenectomy. In addition, they compared the two models with the traditional Fistula Risk Score system with respect to their predictive performance. Division of a total of 250 patients who underwent pancreaticoduodenectomy (PD) with preoperative computed tomography (CT) was done into a training set (n = 175) and validation set (n = 75). For the radiomics model and combined model, a total of 11 and 18 features were extracted, respectively. In the preoperative prediction of CR-POPF, the combined model showed excellent predictive performance and had performance better than the traditional FRS system and radiomics model. A radiomics model was developed using radiomics features extracted from the volume of interest and a combined model was created using radiomics features, demographic information, and radiological features.