A nomogram for predicting early mortality in patients with traumatic brain injury requiring mechanical ventilation based on clinical laboratory data

We developed an intuitive and user-friendly nomogram based on clinical laboratory data for early outcome predictions for patients with traumatic brain injury requiring mechanical ventilation who were admitted to the intensive care unit for the first time. We included 625 patients from the Medical Information Mart for Intensive Care IV 2.2 database as the training cohort and 107 patients from the Affiliated Dongyang Hospital of Wenzhou Medical University as the external validation cohort. The least absolute shrinkage and selection operator regression analysis, combined with univariate and multivariate Cox regression analyses, was used to identify independent risk factors. Age, sex, partial pressure of carbon dioxide, white blood cell count, creatinine levels, prothrombin time, and partial thromboplastin time were included in the nomogram. The area under the receiver operating characteristic curve was 0.811 for the training cohort and 0.770 for the external validation cohort. The calibration curves, clinical decision curve analysis, and clinical impact curve demonstrated that the nomogram had a good goodness-of-fit and clinical utility. We developed a nomogram based on clinical laboratory data for predicting the early (14-day) mortality rate of patients with traumatic brain injury requiring mechanical ventilation, which may help assess patient risk and decision-making.