Risk factors analysis and nomogram construction for pulmonary infection in traumatic brain injury patients:A retrospective cohort study based on the MIMIC-Ⅳ database
Zhu Yalin
Ge Yanan
Huang Jie
Wang Jiafeng
Abstract：Objective:To construct a risk prediction model for pulmonary infection in patients with traumatic brain injury(TBI),providing a tool for early identification of high-risk individuals in the intensive care unit(ICU).Methods:Based on the Medical Information Mart for Intensive Care(MIMIC-Ⅳ database),1,443 TBI patients admitted to the ICU were included.Independent risk factors for pulmonary infection in TBI patients were screened through univariate and multivariate logistic regression analysis,and a nomogram prediction model was constructed.Results:The overall incidence of pulmonary infection was 12.1%(174/1,443),and the 28-day ICU mortality rate in the pulmonary infection group was significantly higher than that in the non-pulmonary infection group[13.2%(23/174)vs 7.8%(99/1,269),P＜0.05].Chronic pulmonary disease,respiratory rate,body temperature,mechanical ventilation,and antibiotic therapy[OR(95%CI)were 2.09(1.28-3.41),1.09(1.03-1.16),1.86(1.29-2.68),2.05(1.34-3.14),and 4.24(2.65-6.81),respectively]were identified as independent risk factors for pulmonary infection in TBI patients(P＜0.05).The nomogram model based on these variables demonstrated good discrimination(AUC=0.782,95%CI 0.748-0.816).Conclusions:The nomogram model developed in this study integrates baseline comorbidities,dynamic physiological parameters,and therapeutic interventions,effectively identifying high-risk TBI patients for pulmonary infection(score＞60),providing evidence-based support for early clinical intervention.
Keywords：Traumatic brain injuryPulmonary infectionIntensive care unitRisk factorNomogram
Publication Date：2025-06-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 160-165 )