To say that we are “operating in the dark” when it comes to venous thromboembolism (VTE) screening and prophylaxis in children is an understatement. In this issue of JAMA Surgery, Connelly and colleagues1 have published a technically well-done statistical analysis of the National Trauma Data Bank (NTDB) to develop a VTE risk prediction score for pediatric trauma patients. They ran a variety of permutations of clinical risk factors to develop the most accurate yet parsimonious risk prediction system from a training data set, and then they validated the accuracy using a validation data set. Their final best prediction model demonstrated an area under the receiver operating characteristic curve of 0.932, generating a simple scoring system that predicted deep vein thrombosis risk ranging from 0% to 14%. To their credit, the authors avoided using in their risk prediction calculator standard injury characterization variables such as the Injury Severity Score or the Abbreviated Injury Score, which (although predictive of outcomes) are useless for guiding clinical decisions in the early hospital course of a pediatric trauma patient.2,3
Martin MJ. Pediatric Venous Thromboembolism—Like Adult Clots, Only Smaller. JAMA Surg. 2016;151(1):57–58. doi:10.1001/jamasurg.2015.2680
Artificial Intelligence Resource Center
Customize your JAMA Network experience by selecting one or more topics from the list below.