Abstract: OBJECTIVE To explore the risk factors of pulmonary infection in patients with head and neck cancer undergoing radiotherapy, and to construct a prediction model. METHODSA total of 466 patients with head and neck cancer who underwent radiotherapy at the Cancer Hospital of Chinese Academy of Medical Sciences and Peking Union Medical College from Aug. 2020 to Aug. 2025 were selected as the study subjects. Patients were divided into two groups based on whether they developed a pulmonary infection during radiotherapy. Multivariate logistic regression analysis was used to identify independent predictors, and a prediction model was subsequently constructed with R software. RESULTSThe incidence of pulmonary infection in 466 patients with head and neck cancer undergoing radiotherapy was 16.31%. Age, smoking history, history of pulmonary disease, serum C-reactive protein (CRP) and serum D-dimer were influencing factors for the development of pulmonary infection in these patients (all P<0.05). Based on the aforementioned influencing factors, the area under the receiver operating characteristic (ROC) curve for internal validation was 0.929 (95% CI: 0.901-0.950, P<0.001), indicating good model discrimination. The Hosmer-Lemeshow test showed good model fit (χ²=9.024, P=0.340). CONCLUSIONThe model established in this study exhibits excellent predictive performance and high clinical value, and can be served as an effective decision-support tool. It assists medical staff in identifying individuals with a high risk of infection, enabling timely intervention. This provides crucial practical guidance for improving patient clinical outcomes and promoting the efficacy of radiotherapy.