Construction and validation of a risk prediction model for postoperative pulmonary infection in patients with brain tumor: a retrospective study.

OBJECTIVES

This study aimed to investigate the influencing factors and construct a risk prediction model for postoperative pulmonary infection in patients with brain tumor.

METHODS

This investigation encompassed a cohort of 636 individuals who were diagnosed with brain tumors and underwent surgical treatment between October 2019 and October 2023. According to the ratio of 7:3, the patients were randomly divided into training set and validation set. Univariate analysis and multivariate Logistic regression analysis were performed on the data in the training set. Finally, the independent risk factors of postoperative pulmonary infection in patients with brain tumor were screened out. R software was used to establish a nomogram model for predicting the risk of postoperative pulmonary infection. Receiver operating characteristic (ROC) curve, calibration curve and Hosmer-Lemeshow test were used to evaluate the discrimination and calibration of the model. Decision curve analysis was used to evaluate the clinical benefit of the model.

RESULTS

The prevalence of postoperative pulmonary infection in patients with brain tumors was 17.9%. The nomogram contained several independent risk factors: age ≥ 60 years, diabetes mellitus, GCS score < 13 points, postoperative bedtime, and postoperative D-Dimer. The prediction model yielded an area under the curve (AUC) of 0.814 (95% confidence interval CI [0.756-0.873]) in the training set, and an AUC of 0.752 (95% CI [0.653-0.850]) in the validation set. The -values for the Hosmer-Lemeshow test in the training set are 0.629, while in the validation set, they are 0.128. Decision curve analysis demonstrated that the model's clinical effectiveness is satisfactory.

CONCLUSIONS

Age ≥ 60 years, diabetes mellitus, GCS score < 13 points, postoperative bedtime and postoperative D-Dimer are risk factors for postoperative pulmonary infection in patients with brain tumor. The developed prediction model demonstrates substantial predictive value and clinical applicability, serving as a valuable reference for medical professionals in recognizing postoperative pulmonary infections in patients with brain tumors and facilitating preventive nursing measures.