Diagnostic value of chest radiography in the early management of severely injured patients with mediastinal vascular injury

Introduction Time is of the essence in the management of severely injured patients. This is especially true in patients with mediastinal vascular injury (MVI). This rare, yet life threatening injury needs early detection and immediate decision making. According to the ATLS guidelines [American College of Surgeon Committee on Trauma in Advanced Trauma Life Support (ATLS(R)), 10th edn, 2018], chest radiography (CXR) is one of the first-line imaging examinations in the Trauma Resuscitation Unit (TRU), especially in patients with MVI. Yet thorough interpretation and the competence of identifying pathological findings are essential for accurate diagnosis and drawing appropriate conclusion for further management. The present study evaluates the role of CXR in detecting MVI in the early management of severely injured patients. Method We addressed the question in two ways. (1) We performed a retrospective, observational, single-center study and included all primary blunt trauma patients over a period of 2 years that had been admitted to the TRU of a Level-I Trauma Center. Mediastinal/chest (M/C) ratio measurements were calculated from CXRs at three different levels of the mediastinum to identify MVI. Two groups were built: with MVI (VThx) and without MVI (control). The accuracy of the CXR findings were compared with the results of whole-body computed tomography scans (WBCT). (2) We performed another retrospective study and evaluated the usage of sonography, CXR and WBCT over 15 years (2005-2019) in level-I-III Trauma Centers in Germany as documented in the TraumaRegister DGU(R) (TR-DGU). Results Study I showed that in 2 years 267 patients suffered from a significant blunt thoracic trauma (AIS >= 3) and met the inclusion criteria. 27 (10%) of them suffered MVI (VThx). Through the initial CXR in a supine position, MVI was detected in 56-92.6% at aortic arch level and in 44.4-100% at valve level, depending on different M/C-ratios (2.0-3.0). The specificity at different thresholds of M/C ratio was 63.3-2.9% at aortic arch level and 52.9-0.4% at valve level. The ROC curve showed a statistically random process. No significant differences of the cardiac silhouette were observed between VThx and Control (mean cardiac width was 136.5 mm, p = 0.44). Study II included 251,095 patients from the TR-DGU. A continuous reduction of the usage of CXR in the TRU could be observed from 75% in 2005 to 25% in 2019. WBCT usage increased from 35% in 2005 to 80% in 2019. This development was observed in all trauma centers independently from their designated level of care. Conclusion According to the TRU management guidelines (American College of Surgeon Committee on Trauma in Advanced Trauma Life Support (ATLS (R)), 10th edn, 2018; Reissig and Kroegel in Eur J Radiol 53:463-470, 2005) CXR in supine position is performed to detect pneumothorax, hemothorax and MVI. Our study showed that sensitivity and specificity of CXR in detecting MVI was statistically and clinically not reliable. Previous studies have already shown that CXR is inferior to sonography in detecting pneumothorax and hemothorax. Therefore, we challenge the guidelines and suggest that the use of CXR in the early management of severely injured patients should be individualized. If sonography and WBCT are available and reasonable, CXR is unnecessary and time consuming. The clinical reality reflected in the usage of CXR and WBCT over time, as documented in the TR-DGU, seems to support our statement.