Appropriateness of Initial Course of Action in the Management of Blunt Trauma Based on a Diagnostic Workup Including an Extended Ultrasonography Scan.

Importance: The extended Focused Assessment With Sonography for Trauma (E-FAST) has become a cornerstone of the diagnostic workup in patients with trauma. The added value of a diagnostic workup including an E-FAST to support decision-making remains unknown. Objective: To determine how often an immediate course of action adopted in the resuscitation room based on a diagnostic workup that included an E-FAST and before whole-body computed tomography scanning (WBCT) in patients with blunt trauma was appropriate. Design, Setting, and Participants: This cohort study was conducted at 6 French level I trauma centers between November 5, 2018, and November 5, 2019. Consecutive patients treated for blunt trauma were assessed at the participating centers. Data analysis took place in February 2022. Exposures: Diagnostic workup associating E-FAST (including abdominal, thoracic, pubic, and transcranial Doppler ultrasonography scan), systematic clinical examination, and chest and pelvic radiographs. Main Outcomes and Measures: The main outcome criterion was the appropriateness of the observed course of action (including abstention) in the resuscitation room according to evaluation by a masked expert panel. Results: Of 515 patients screened, 510 patients (99.0%) were included. Among the 510 patients included, 394 were men (77.3%), the median (IQR) age was 46 years (29-61 years), and the median (IQR) Injury Severity Score (ISS) was 24 (17-34). Based on the initial diagnostic workup, no immediate therapeutic action was deemed necessary in 233 cases (45.7%). Conversely, the following immediate therapeutic actions were initiated before WBCT: 6 emergency laparotomies (1.2%), 2 pelvic angioembolisations (0.4%), 52 pelvic binders (10.2%), 41 chest drains (8.0%) and 16 chest decompressions (3.1%), 60 osmotherapies (11.8%), and 6 thoracotomies (1.2%). To improve cerebral blood flow based on transcranial doppler recordings, norepinephrine was initiated in 108 cases (21.2%). In summary, the expert panel considered the course of action appropriate in 493 of 510 cases (96.7%; 95% CI, 94.7%-98.0%). Among the 17 cases (3.3%) with inappropriate course of action, 13 (76%) corresponded to a deviation from existing guidelines and 4 (24%) resulted from an erroneous interpretation of the E-FAST. Conclusions and Relevance: This prospective, multicenter cohort study found that a diagnostic resuscitation room workup for patients with blunt trauma that included E-FAST with clinical assessment and targeted chest and pelvic radiographs was associated with the determination of an appropriate course of action prior to WBCT.

Machine learning-based prediction of emergency neurosurgery within 24 h after moderate to severe traumatic brain injury.

BACKGROUND: Rapid referral of traumatic brain injury (TBI) patients requiring emergency neurosurgery to a specialized trauma center can significantly reduce morbidity and mortality. Currently, no model has been reported to predict the need for acute neurosurgery in severe to moderate TBI patients. This study aims to evaluate the performance of Machine Learning-based models to establish to predict the need for neurosurgery procedure within 24 h after moderate to severe TBI. METHODS: Retrospective multicenter cohort study using data from a national trauma registry (Traumabase®) from November 2011 to December 2020. Inclusion criteria correspond to patients over 18 years old with moderate or severe TBI (Glasgow coma score ≤ 12) during prehospital assessment. Patients who died within the first 24 h after hospital admission and secondary transfers were excluded. The population was divided into a train set (80% of patients) and a test set (20% of patients). Several approaches were used to define the best prognostic model (linear nearest neighbor or ensemble model). The Shapley Value was used to identify the most relevant pre-hospital variables for prediction. RESULTS: 2159 patients were included in the study. 914 patients (42%) required neurosurgical intervention within 24 h. The population was predominantly male (77%), young (median age 35 years [IQR 24-52]) with severe head injury (median GCS 6 [3-9]). Based on the evaluation of the predictive model on the test set, the logistic regression model had an AUC of 0.76. The best predictive model was obtained with the CatBoost technique (AUC 0.81). According to the Shapley values method, the most predictive variables in the CatBoost were a low initial Glasgow coma score, the regression of pupillary abnormality after osmotherapy, a high blood pressure and a low heart rate. CONCLUSION: Machine learning-based models could predict the need for emergency neurosurgery within 24 h after moderate and severe head injury. Potential clinical benefits of such models as a decision-making tool deserve further assessment. The performance in real-life setting and the impact on clinical decision-making of the model requires workflow integration and prospective assessment.