Risk factors analysis and prediction model construction for pulmonary fungal infection in lung cancer patients

Abstract Objective To investigate the independent risk factors for pulmonary fungal infection in patients with lung cancer and to construct a risk prediction model. Methods The clinical data of 250 lung cancer patients admitted to Nanchong Central Hospital between February 2022 and March 2025 were retrospectively analyzed. Patients were randomly divided into a training set (n = 175) and a validation set (n = 75) at a 7:3 ratio. Potential predictors were initially screened using univariate logistic regression. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) regression. A prediction model was constructed via multivariate logistic regression based on the selected variables. The calibration curves assessed prediction accuracy. The area under the receiver operating characteristic (ROC) curve (AUC) evaluated the model discrimination. Decision curve analysis (DCA) quantified clinical net benefit. Results Significant differences were observed between the two groups in terms of diabetes mellitus, invasive operation, glucocorticoid use, CD4+ T-cell count, and length of hospital stay (> 14 days) (P 0.05, suggesting good model fit. The AUC values were 0.876 (95% CI: 0.809–0.944) for the training set and 0.861 (95% CI: 0.750–0.973) for the validation set. Within the probability threshold ranges of 0.03–0.90 (training set) and 0.04–0.78 (validation set), the model demonstrated net benefit according to DCA. Conclusion Diabetes mellitus, invasive operation, glucocorticoid use,lower CD4+ T-cell count, and Prolonged hospital stay are independent risk factors for pulmonary fungal infection in lung cancer patients. The prediction model constructed in this study provides valuable guidance for the early identification of high-risk patients.