Machine Learning for Predicting the Low Risk of Postoperative Pancreatic Fistula After Pancreaticoduodenectomy: Toward a Dynamic and Personalized Postoperative Management Strategy.

Background: Postoperative pancreatic fistula (POPF) remains one of the most relevant complications following pancreaticoduodenectomy (PD), significantly impacting short-term outcomes and delaying adjuvant therapies. Current predictive models offer limited accuracy, often failing to incorporate early postoperative data. This retrospective study aimed to develop and validate machine learning (ML) models to predict the absence and severity of POPF using clinical, surgical, and early postoperative variables.