Data_Sheet_1.CSV

Abstract

Background: There is a high incidence of acute respiratory failure (ARF) in moderate or severe traumatic brain injury (M-STBI), worsening outcomes. The present work aimed to design a predictive model for ARF. Methods: Adult M-STBI (3 ≤ Glasgow Coma Scale (GCS) ≤ 12) patients with a definite history of brain trauma and abnormal head on CT images, obtained from September 2015 to May 2017, were included. Patients with age > 80 or < 18, multiple injuries with TBI upon admission, or pregnancy (in women) were excluded. Two models based on machine learning extreme gradient boosting (XGBoost) or logistic regression, respectively, were developed for predicting ARF within 48 hours upon admission. These models were evaluated by out-of-sample validation. The samples were assigned to the training and test sets at a ratio of 3:1. Result: Totally 312 patients were analyzed, including 132 (42.3%) who had ARF. GCS and CT Marshall score, procalcitonin (PCT), and C-reactive protein (CRP) on admission significantly predicted ARF. The novel machine learning XGBoost model was superior to logistic regression model in predicting ARF (AU-ROC=0.903, 95%CI 0.834-0.966 vs. AU-ROC=0.798, 95%CI 0.697-0.899; P < 0.05). Conclusion: The XGBoost model could better predict ARF in comparison with the logistic regression-based model. Therefore, machine learning methods could help develop and validate novel predictive models.