Abstract: Objective: To investigate the influencing factors of postoperative infection of esophageal cancer and establish a Lasso-Nomogram risk prediction model. Methods: A total of 548 patients with esophageal cancer admitted to Tangdu Hospital of Air Force Military Medical University from March 2020 to January 2023 were randomly divided into modeling group(n=274) and validation group(n=274) according to the ratio of 1:1. Glmnet in R software was used for Lasso screening of predictive factors for postoperative pulmonary infection, the correlation between predictive factors and pulmonary infection was further analyzed through logistic regression, and a Nomogram risk prediction model was constructed using R language based on predictive factors. The combined prediction of age, smoking history, diabetes, and underlying lung diseases was used as the prediction model 1,and the combined prediction of age, smoking history, diabetes, underlying lung diseases, prognostic nutritional index(PNI), procalcitonin(PCT), interleukin-1β(IL-1β), soluble myeloid cell triggering receptor-1(sTREM-1),and CD4⁺/CD8⁺ was used as the prediction model 2. Prediction model 1 and prediction model 2 were constructed,and the external validation was performed using the area under the receiver operating characteristic(ROC) curve(AUC), net reclassification index(NRI) and integrated discrimination improvement(IDI) in the validation group.Results: Lasso screening predictors included age, smoking history, diabetes, underlying lung diseases, PNI, PCT,IL-1β, sTREM-1, and CD4⁺/CD8⁺; the AUC predicted by prediction model 2 for postoperative pulmonary infection was greater than that of prediction model 1, and the prediction effect was significantly improved(P＜0.05). Conclusion: The Nomogram risk prediction model established based on age, smoking history, diabetes, underlying lung diseases, PNI, PCT, IL-1β, sTREM-1, CD4⁺/CD8⁺ and other factors has a certain value in predicting postoperative pulmonary infection. It is helpful for early clinical screening of high-risk population and development of targeted intervention measures to reduce the risk of pulmonary infection.