Abstract: Objective:To investigate the prognostic value of neutrophil/albumin ratio (NAR) in patients with metastatic pancreatic cancer(mPC)and construct a prediction model.Methods:The clinical data of 223 patients with mPC treated in the Guangxi Medical University Cancer Hospital from October 2013 to April 2022 were retrospectively collected.The patients were randomly divided into the training cohort and the validation cohort in a ratio of 2:1.The optimal cutoff value for NAR was obtained by X-tile and grouped.Kaplan-Meier method was used to draw the survival curves, and log-rank tests were performed.Multivariate Cox proportional hazard regression model was used to analyze the factors affecting the prognosis of mPC patients, and a nomogram model was constructed based on this.The performance of nomogram was evaluated by the area under receiver operating characteristic(ROC)curve(AUC), calibration plots and decision curve analysis(DCA).X-tile was used to divide the patients into high-risk group and low-risk group.Kaplan-Meier and log-rank tests were used to evaluate the survival differences between the two groups.Results:The optimal cutoff value for NAR was 0.13.The median overall survival(OS)was longer in the low NAR group than in the high NAR group(P=0.003).Multivariate Cox analysis results showed that high NAR was an independent risk factor for mPC prognosis (HR=1.455, 95% CI:1.065-1.988, P=0.018).ROC curve, calibration plots and DCA of training cohort and validation cohort all reflected that the nomogram model built based on NAR exhibited good discrimination ability, calibration abilityand clinical practicability.The nomogram model scores could effectively distinguish high and low risk groups.Conclusion:High NAR (NAR> 0.13) is an independent risk factor for the prognosis of mPC patients, and the nomogram model built based on NAR can assist in predicting the prognosis of mPC patients.