Development and validation of a predictive nomogram for ventilator-associated pneumonia in patients with traumatic brain injury: based on the MIMIC-IV database

基于MIMIC-IV数据库,构建并验证创伤性脑损伤患者呼吸机相关性肺炎预测列线图

阅读:2

Abstract

BACKGROUND: In patients with traumatic brain injury (TBI) requiring mechanical ventilation, ventilator-associated pneumonia (VAP) is a frequent and serious complication that often leads to prolonged hospitalization and increased mortality. However, reliable predictive tools for this specific patient population remain limited. This study aims to develop and validate an effective prediction model for VAP in TBI patients based on clinical variables. METHODS: We conducted a retrospective study using data from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. Univariate and multivariate logistic regression analyses were applied to identify independent predictors of VAP and to develop a nomogram. Model performance was assessed by receiver operating characteristic (ROC) curve analysis, calibration plots, and decision curve analysis (DCA). External validation was performed with clinical data from 43 TBI patients treated at the Third Affiliated Hospital of Anhui Medical University. RESULTS: Among 819 TBI patients admitted to the intensive care unit (ICU), 141 developed VAP. Four independent predictors of VAP were identified: sepsis, neuromuscular blocking agent (NMBA) use, ICU length of stay (LOS) and prothrombin time (PT). The nomogram demonstrated strong discriminative ability, with area under the curve (AUC) values of 0.800 [95% confidence interval (CI): 0.617-0.859] in the training cohort, 0.822 (95% CI: 0.621-0.929) in the testing cohort, and 0.711 (95% CI: 0.600-0.957) in the external validation cohort. The calibration curves demonstrated that the predictive model possesses satisfactory discriminative power with excellent model calibration. DCA revealed the nomogram's clinical utility across a probability threshold range of 5-45% for VAP intervention. CONCLUSIONS: We have developed and validated a predictive model for VAP in TBI patients. This high-performance tool can assist clinicians in early identification of high-risk cases and guide prevention strategies.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。