Objective To investigate the risk factors associated with postoperative pulmonary infection after pancreaticoduodenectomy （PD） and construct a predictive model for guiding early clinical intervention. Methods A retrospective analysis was carried out on 220 patients who underwent PD at the First Affiliated Hospital of Xinjiang Medical University between January 2022 and October 2024. Cases with preoperative pulmonary infection， incomplete data， or perioperative mortality were excluded. Preoperative， intraoperative， and postoperative clinical data were meticulously collected. Univariate analysis was employed to screen potential risk factors， and multivariate logistic regression was utilized to identify independent risk factors. Subsequently， a nomogram prediction model was constructed. Results Pulmonary infection occurred in 84 patients （38.2%） following surgery. Multivariate analysis indicated that a high body mass index （BMI） （OR = 1.12， 95%CI： 1.02 ~ 1.23， P < 0.05）， low albumin levels on postoperative day 3 （OR = 0.91， 95% CI： 0.83 ~ 0.99， P < 0.05）， an extended retention time of the postoperative abdominal drainage tube （OR = 1.05， 95% CI： 1.01 ~ 1.09， P < 0.05）， a prolonged postoperative bed rest duration （OR = 1.56， 95% CI： 1.22 ~ 1.99， P < 0.05）， and the occurrence of non?pulmonary complications （OR = 2.23， 95% CI： 1.05 ~ 4.75， P < 0.05） were independent risk factors for pulmonary infection. The prediction model attained an area under the receiver operating characteristic curve （AUC） of 0.82 （95% CI： 0.76 ~ 0.88）， with the calibration curve showing a good fit. After internal validation， the AUC remained stable at 0.80 （95% CI： 0.71 ~ 0.88）， validating the robust predictive ability of the model. Conclusions Elevated BMI， low postoperative albumin levels， extended retention time of the abdominal drainage tube， prolonged duration of bed rest， and non?pulmonary complications are identified as independent risk factors for pulmonary infection following PD. The established risk prediction model demonstrates robust predictive capabilities， thereby furnishing a foundation for individualized risk assessment and targeted preventive strategies.