ObjectiveTo review the recent research progress on prediction models for pancreatic fistula after pancreaticoduodenectomy and explore the potential application of prediction models in personalized treatment, aiming to provide useful reference information for clinical doctors to improve patient treatment outcomes and quality of life. MethodsWe systematically searched and reviewed the literature on various prediction models for pancreatic fistula after pancreaticoduodenectomy in recent years domestically and internationally. ResultsSpecifically, the fistula risk score (FRS) and the alternative fistula risk score (a-FRS), as widely used tools, possessed a certain degree of subjectivity due to the lack of an objective evaluation standard for pancreatic texture. The updated alternative fistula risk score (ua-FRS) had demonstrated superior predictive efficacy in minimally invasive surgery compared to the original FRS and a-FRS. The NCCH (National Cancer Center Hospital) prediction system, based on preoperative indicators, showed high predictive accuracy. Prediction models based on CT imaging informatics had improved the accuracy and reliability of predictions. Prediction models based on elastography had provided new perspectives for the assessment of pancreatic texture and the prediction of clinically relevant postoperative pancreatic fistula. The Stacking ensemble machine learning model contributed to the individualization and localization of prediction models. The existing pancreatic fistula prediction models showed satisfactory predictive efficacy, but there were still limitations in identifying high-risk populations for pancreatic fistula. ConclusionsAfter pancreaticoduodenectomy, pancreatic fistula remains a major complication that is difficult to overcome. The prevention of pancreatic fistula is crucial for improving postoperative recovery and reducing mortality rates. Future research should focus on the development and validation of pancreatic fistula prediction models, thereby enhancing their predictive power and increasing their predictive efficacy in different regional populations, providing a scientific basis for medical decision-making.