Machine Learning Model for Predicting Acute Respiratory Failure in Individuals With Moderate-to-Severe Traumatic Brain Injury

Background: There is a high incidence of acute respiratory failure (ARF) in moderate or severe traumatic brain injury (M-STBI), worsening outcomes. This study aimed to design a predictive model for ARF.Methods: Adult patients with M-STBI [3 ≤ Glasgow Coma Scale (GCS) ≤ 12] 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 years or <18 years, 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 h 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.Results: In total, 312 patients were analyzed including 132 (42.3%) patients who had ARF. The GCS and the Marshall CT 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 [area under the receiver operating characteristic (AUROC) = 0.903, 95% CI, 0.834–0.966 vs. AUROC = 0.798, 95% CI, 0.697–0.899; p < 0.05].Conclusion: The XGBoost model could better predict ARF in comparison with logistic regression-based model. Therefore, machine learning methods could help to develop and validate novel predictive models.

Correlation between neutrophil lymphocyte count ratio and outcomes of severe traumatic head injury

Background: Raised peripheral neutrophil lymphocyte ratio is associated with poorer outcomes in conditions such as severe brain injury, ICH, cardiovascular conditions, cancer.Methods: Retrospective analysis of 96 severe Traumatic Brain injury data treated at our institute over a period of 1 year. The patients were followed up for a period of at least 1 month. The primary outcome of the study was 1 month GOS and the various variables which may be associated with the poor GOS at 1 month follow up. Model based analysis was done for NLCR <24 hrs at 48 hrs and GCS at the time of presentation and discriminative ability of the models were studied by the Area under the curve.Results: Univariate analysis were done of 96 patients of severe traumatic brain injury for various variables such as age, sex, mode of head injury, type of head injury, presenting GCS and NLCR at 24 hrs and 48 hrs to that of GOS at 1 month follow up. Initial GCS <7 (p=0.0138) with AUC=0.6689 and peak NLCR (<24 hr) of > 9.6 (AUC=0.931) with a p value of <0.001 with sensitivity of 100% and specificity of 79.27% and peak NLCR (48 hrs) of >12.4 (AUC= 0.973) with a p value of <0.001 with sensitivity of 100% and specificity of 89.02% were associated with unfavourable outcome.Conclusions: High NLCR and initial poor GCS are independent unfavourable prognostic factors in 1 month GOS following severe traumatic head injury.

Perioperative Management of Polytrauma Patients with Severe Traumatic Brain Injury Undergoing Emergency Extracranial Surgery: A Narrative Review

Managing the acute phase after a severe traumatic brain injury (TBI) with polytrauma represents a challenging situation for every trauma team member. A worldwide variability in the management of these complex patients has been reported in recent studies. Moreover, limited evidence regarding this topic is available, mainly due to the lack of well-designed studies. Anesthesiologists, as trauma team members, should be familiar with all the issues related to the management of these patients. In this narrative review, we summarize the available evidence in this setting, focusing on perioperative brain protection, cardiorespiratory optimization, and preservation of the coagulative function. An overview on simultaneous multisystem surgery (SMS) is also presented.