Influencing factors of severe traumatic brain injury patients with acute respiratory distress syndrome and construction of predictive model

To explore the risk factors associated with the development of acute respiratory distress syndrome (ARDS) in patients with severe traumatic brain injury (sTBI) and to construct and validate a risk prediction model for ARDS in these patients.

Clinical data from 371 sTBI patients admitted to Yangzhou Affiliated Hospital of Yangzhou University between January 2017 and December 2023 were retrospectively collected. Patients were randomly divided into modeling group (n=259) and validation group (n=112) at a 7-to-3 ratio. A nomogram model was constructed after screening for risk factors using the Least Absolute Shrinkage and Selection Operator (LASSO) and multivariate Logistic regression analysis. Model performance was evaluated using the receiver operating characteristic (ROC) curve, area under the curve (AUC), Hosmer-Lemeshow test, calibration curve, and decision curve analysis (DCA).

Statistically significant differences were observed in heart rate, respiratory rate, pupil size, percutaneous oxygen saturation (SpO₂), Glasgow Coma Scale (GCS) score, Acute Physiology and Chronic Health Evaluation Ⅱ(APACHE Ⅱ) score, head Abbreviated Injury Scale (AIS) score, chest AIS score, emergency intubation, pulmonary infection, associated chest trauma, midline shift, blood transfusion within 12 hours of admission, fluid intake within 24 hours of admission, shock, mechanical ventilation, hemoglobin level, hematocrit, white blood cell count, prothrombin time, international normalized ratio, total protein, albumin, serum calcium, oxygenation index, and base excess between the two groups (P < 0.05). Multivariate Logistic regression analysis revealed that SpO₂, pulmonary infection, and fluid intake within 24 hours of admission were predictors of ARDS in sTBI patients. The Hosmer-Lemeshow test results for the modeling and validation groups showed good fit (χ²=10.373, P=0.240; χ²=13.21, P=0.105). DCA results for both groups indicated net benefit at threshold probabilities ranging from 0% to 72% and 0% to 50%, respectively.

SpO₂, pulmonary infection, and fluid intake within 24 hours of admission are risk factors for ARDS in sTBI patients. The model constructed using these factors demonstrates good performance and provides a reliable tool for clinical screening of high-risk ARDS populations among sTBI patients.