• Jeremy C Pamplin, Mason H Remondelli, Darshan Thota, Jeremy Trapier, William T Davis, Nathan Fisher, Paul Kwon, and Matthew T Quinn.
• The Telemedicine and Advanced Technology Research Center, Frederick, MD, 21702 USA.
• Mil Med. 2024 May 14.

AbstractThe potential impact of large-scale combat operations and multidomain operations against peer adversaries poses significant challenges to the Military Health System including large volumes of critically ill and injured casualties, prolonged care times in austere care contexts, limited movement, contested logistics, and denied communications. These challenges contribute to the probability of higher casualty mortality and risk that casualty care hinders commanders' forward momentum or opportunities for overmatch on the battlefield. Novel technical solutions and associated concepts of operation that fundamentally change the delivery of casualty care are necessary to achieve desired medical outcomes that include maximizing Warfighter battle-readiness, minimizing return-to-duty time, optimizing medical evacuation that clears casualties from the battlefield while minimizing casualty morbidity and mortality, and minimizing resource consumption across the care continuum. These novel solutions promise to "automate" certain aspects of casualty care at the level of the individual caregiver and the system level, to unburden our limited number of providers to do more and make better (data-driven) decisions. In this commentary, we describe concepts of casualty digital twins-virtual representations of a casualty's physical journey through the roles of care-and how they, combined with passive data collection about casualty status, caregiver actions, and real-time resource use, can lead to human-machine teaming and increasing automation of casualty care across the care continuum while maintaining or improving outcomes. Our path to combat casualty care automation starts with mapping and modeling the context of casualty care in realistic environments through passive data collection of large amounts of unstructured data to inform machine learning models. These context-aware models will be matched with patient physiology models to create casualty digital twins that better predict casualty needs and resources required and ultimately inform and accelerate decision-making across the continuum of care. We will draw from the experience of the automotive industry as an exemplar for achieving automation in health care and inculcate automation as a mechanism for optimizing the casualty care survival chain.Published by Oxford University Press on behalf of the Association of Military Surgeons of the United States 2024. This work is written by (a) US Government employee(s) and is in the public domain in the US.

26 keywords...

hide…