Development and validation of a clinical prediction model for concurrent pulmonary infection in convalescent patients with intracerebral hemorrhage

Abstract

Abstract Objectives: This study aims to develop and validate a clinical prediction model for assessing the risk of concurrent pulmonary infection（PI）in patients recovering from intracerebral hemorrhage（ICH）. Methods: In this retrospective study, we compiled clinical data from 761 patients in the recovery phase of intracerebral hemorrhage, with 504 cases included in the PI group and 254 in the no PI group. Initially, univariate logistic regression was used to screen predictive factors. Subsequently, the Least Absolute Shrinkage and Selection Operator (LASSO) regression was employed to optimize these predictors. Variables identified from LASSO regression were included in a multivariable logistic regression analysis, incorporating variables with P < 0.05 into the final model. A nomogram was constructed, and its discriminative ability was evaluated using the Receiver Operating Characteristic (ROC) curve and Area Under the Curve (AUC). Model performance was assessed using calibration plots and the Hosmer-Lemeshow goodness-of-fit test (HL test). Additionally, the net clinical benefit was evaluated through clinical decision curve （DOC）analysis. Results Key predictors of PI included age, antibiotic use, consciousness disturbances, tracheotomy, dysphagia, bed rest duration, nasal feeding, and procalcitonin levels. The model demonstrated strong discrimination (C-index: 0.901, 95%CI: 0.878~0.924) and fit (Hosmer-Lemeshow test P=0.982), with significant clinical utility as per DCA. Conclusion This study constructed a nomogram prediction model based on the demographic and clinical characteristics of convalescent patients with intracerebral hemorrhage. Further studies showed that this model is of great value in the prediction of pulmonary infection in convalescent patients with intracerebral hemorrhage.