Construction of nomogram model for early death risk in patients with severe traumatic brain injury

Traumatic brain injury (TBI) poses significant challenges in prognostication and clinical management, particularly in severe cases. The need for precise prognostic tools to predict outcomes, including early death, in severe TBI is crucial. This study aimed to construct a nomogram model for early death risk in patients with severe TBI to enhance clinical decision-making.

This retrospective cohort study included severe TBI patients categorized into non-survivors and survivors groups from August 2018 to March 2024. Data on demographic, clinical, laboratory, and imaging parameters were collected and analyzed by using SPSS 29.0 statistical software. A nomogram model was constructed. The model's predictive performance was assessed using the Hosmer-Lemeshow goodness-of-fit test and ROC curve.

Lower Glasgow Coma Scale (GCS) scores, elevated neutrophil-to-lymphocyte ratio (NLR), prolonged prothrombin time, increased midline shift, and higher C-reactive protein (CRP) levels were associated with poor prognostic outcomes (p < 0.05). The collaborative nomogram model demonstrated an area under the ROC curve of 0.956, signifying its high predictive value for early death risk in severe TBI.

The study identified several prognostic indicators, including clinical, laboratory, and imaging parameters, associated with early death risk in severe TBI patients. The constructed nomogram model offers a comprehensive tool for predicting early death risk, facilitating individualized prognostication and informed decision-making.