Pitt, Carnegie Mellon team up to create 'trauma care in rucksack' for combat soldiers

Academic researchers are working to create an autonomous trauma care system that uses robotics and artificial intelligence to treat injured soldiers in combat. (Rawf8/Getty Images)

The University of Pittsburgh School of Medicine and Carnegie Mellon University are teaming up to create a trauma care system that fits in a backpack.

As part of a project the U.S. Department of Defense (DOD) calls Trauma Care In a Rucksack, or TRACIR, the two universities are working to build a portable, rapidly deployable, autonomous medical system to provide robotically controlled critical care interventions to patients in remote and austere environments with the goal of extending the “golden hour” for treating combat casualties.

They just won two four-year contracts totaling more than $7.2 million from the DOD for the project.

“Battlefields are becoming increasingly remote, making medical evacuations more difficult,” Ron Poropatich, M.D., retired U.S. Army colonel, director of Pitt’s Center for Military Medicine Research and professor in Pitt’s Division of Pulmonary, Allergy and Critical Care Medicine, said in a statement. “By fusing data captured from multiple sensors and applying machine learning, we are developing more predictive cardio-pulmonary resuscitation opportunities, which hopefully will conserve an injured soldier’s strength."

The multidisciplinary team of Pitt researchers and clinicians from emergency medicine, surgery, critical care and pulmonary fields will provide real-world trauma data and medical algorithms. Carnegie roboticists and computer scientists will incorporate those algorithms into the creation of a “hard and soft robotic suit” into which an injured person can be placed, according to a release.

According to researchers, the design of the suit will include monitors embedded in the suit to assess the injury, and AI algorithms will guide the appropriate critical care interventions and robotically apply stabilizing treatments such as intravenous fluids and medications. 

RELATED: J&J picks up robotic surgery maven Auris Health, and founder Fred Moll himself, in $3.4B deal

The goal of the project is to treat and stabilize soldiers in the battlefield, even during periods of prolonged field care when evacuation is not possible, said Poropatich, who is the overall principal investigator on the $3.71 million Pitt contract.

Researchers envision that the end product will be an autonomous or nearly autonomous system requiring little human assistance and what human assistance it might need could be provided by someone without medical training.

While the immediate goal of the project is to treat soldiers on the battlefield, there are numerous potential civilian applications, Poropatich said. 

The system could be deployed by drone to hikers or mountain climbers injured in the wilderness; it could be used by people in submarines or boats; it could give trauma care capabilities to rural health clinics or be used by aid workers responding to natural disasters, he said. 

RELATED: Verily’s India project reveals the work of applying AI to real-world clinical care

Much technology still needs to be developed to enable robots to reliably and safely perform tasks, such as inserting IV needles or placing a chest tube in the field, according to Artur Dubrawski, Ph.D., research professor at Carnegie's Robotics Institute.

Initially, the research will be “a series of baby steps,” demonstrating the practicality of individual components the system will eventually require, said Dubrawski, who is the principal investigator on the $3.5 million Carnegie contract.

“Everybody has a slightly different vision of what the final system will look like,” Dubrawski said. “But we see this as being an autonomous or nearly autonomous system—a backpack containing an inflatable vest or perhaps a collapsed stretcher that you might toss toward a wounded soldier. It would then open up, inflate, position itself and begin stabilizing the patient.”

With a digital library of detailed physiologic data collected from more than 5,000 UPMC trauma patients, Michael Pinsky of Pitt's Department of Critical Care Medicine and Dubrawski previously created algorithms that could allow a computer program to “learn” the signals that an injured patient’s health is deteriorating before damage is irreversible and tell the robotic system to administer the best treatments and therapies to save that person’s life.

According to Dubrawski, the University of Pittsburgh School of Medicine is an ideal location for the project due to its experience in critical care medicine, artificial intelligence and robotics.