Key points are not available for this paper at this time.
Hemorrhage is the leading cause of preventable death on the battlefield, yet combat medics lack clinical decision support systems to help stratify hemorrhage risk in trauma casualties. We previously trained the Automated Processing of the Physiological Registry for Assessment of Injury Severity - Hemorrhage Risk Index (APPRAISE-HRI) software to associate patterns in vital signs (heart rate and blood pressure) collected from trauma patients with three HRI levels: I (low), II (average), or III (high). To independently validate APPRAISE-HRI and obtain U.S. Food and Drug Administration (FDA) clearance, we collected trauma registry and continuous vital sign data from 5895 trauma patients (543 with hemorrhagic injuries and 5352 controls) in an emergency department or during prehospital transport to one of eight medical centers. The study outcome was hemorrhagic injury, defined by documented injuries and blood transfusion. Using the likelihood ratio to assess the ability of APPRAISE-HRI to stratify hemorrhage risk, we found that hemorrhagic patients were 6.88 times as likely as controls to be at level III, strongly suggesting the presence of hemorrhage at this level. Similarly, hemorrhagic patients were 0.18 times as likely as controls to be at level I, suggesting the absence of hemorrhage at this level. Hemorrhagic patients were almost as likely as controls to be at level II (0.70 times as likely). Subsequently, the U.S. Department of Defense obtained FDA 510(k) clearance for the artificial intelligence-enabled APPRAISE-HRI Class II device (K233249), the first software as a medical device approved for assessing hemorrhage risk in trauma patients, allowing for triage and identification of casualties who need immediate attention and evacuation. (Funded by the U.S. Army Medical Materiel Development Activity and the Combat Casualty Care Program Area Directorate (CCCPAD) of the U.S. Army Medical Research and Development Command (USAMRDC), Fort Detrick, MD and others.).
Frock et al. (Thu,) studied this question.