Optimizing Prediction Models for Pancreatic Fistula after Pancreatectomy

Postoperative pancreatic fistula (POPF) is a common complication following pancreatectomy, with over sixty prediction models existing primarily for pancreaticoduodenectomy. However, these models have shown suboptimal accuracy across diverse populations. Future research should focus on developing and validating prediction models for distal and central pancreatectomy, incorporating machine learning and personalized variables. Integration of novel imaging technologies like AI-based radiomics may further enhance predictive accuracy and revolutionize patient care.