2016 Science, Technology and Environment

Jaques Reifman and the APPRAISE Team

Developed an artificial intelligence system for medics to quickly detect if severely injured patients in transit are hemorrhaging, improving survival rates by preparing trauma centers to act immediately upon the patient’s arrival.

When critically injured soldiers and civilians are rushed to the hospital while hemorrhaging, their lives may hang in the balance. Now, a portable computer system can quickly and accurately detect internal bleeding during emergency transport, allowing medics to take appropriate measures and trauma centers to provide faster care that can save lives.

Jaques Reifman, a senior research scientist with the Department of the Army, led the team that created APPRAISE, a first of its kind, life-saving system that uses artificial intelligence and automated, pattern-recognition algorithms to interpret patient vital signs. Medical personnel can then be informed whether an individual coming to a hospital will need a massive and immediate blood transfusion.

“The APPRAISE system addresses the number one killer on the battlefield by identifying casualties at risk for uncontrolled bleeding who must be immediately evacuated to a hospital,” said Anders Wallqvist, deputy director of the Army’s Biotechnology High Performance Computing Software Applications Institute.

“The system not only helps sustain a victim’s life while being transported, but it makes information available that hospital staff need when a patient arrives,” Wallqvist said.

The APPRAISE system can equally help civilian trauma, especially in remote areas, where specialized trauma centers may be hours away from where the injury occurred.

For decades, the U.S. military has sought to develop technologies to identify casualties with internal bleeding. Now, Reifman and his Army team, together with a group from Massachusetts General Hospital, have successfully tested the APPRAISE system for several years, paving the way for Boston-area trauma units to be ready for immediate surgery and replenishment of lost blood without wasting time and resources on false alarms.

An APPRAISE unit initially was installed in two medical helicopters operated by Boston MedFlight. Between February 2010 and December 2012, the units collected vital sign data on 209 trauma patients transported to three trauma centers. The automated system successfully identified 75 to 80 percent of patients with life-threatening bleeding after just 10 minutes of monitoring.

By 2015, APPRAISE had been tested on more than 1,000 civilian trauma patients during both hospital transport and at the Emergency Department of the Massachusetts General Hospital. 

“Jaques Reifman saw the need to predict when someone is going to require a blood transfusion after watching 12 years of war,” said George Ludwig, the acting principal assistant for research and technology with the U.S. Army Medical Research and Materiel Command. “The APPRAISE tool has far-reaching application.”

To create APPRAISE, Reifman assembled a team from many disciplines—engineers, software developers and medical clinicians—and embarked on a 10-year quest. Along the way, the group met numerous challenges, including having to construct a system that operated without failure in uncontrollable environments and would be fully automated so that the data could be analyzed without human input or supervision. This was necessary to assist combat medics who could be tired, distracted, inexperienced or overwhelmed by a large number of causalities.

The system also needed to operate in real time, using mobile computing platforms with limited processing power and memory. In addition, the system had to accommodate missing and inconsistent sensor data because patient vital sign information such as heart rate and blood pressure collected during transport to a hospital are notoriously unreliable.

Key contributors to Reifman’s APPRAISE team included Maxim Khitrov and Jianbo Liu as well as Andrew Reisner, an investigator with the Army’s Biotechnology High Performance Computing Software Applications Institute and an emergency room doctor at Massachusetts General Hospital.

The Army has received two U.S. patents for the APPRAISE system and is now pursuing Food and Drug Administration clearance and a licensing agreement with a commercial partner.

Gary Gilbert, program manager for the Army’s Medical Intelligent Systems, said Reifman “argued for years that we measure many vital signs, but that we don’t know if the data we are collecting is actually information we need to be sure someone is in critical condition.”

“He had a vision,” Gilbert said. “He addressed the need for expediency to help medical personnel in combat.”

Reifman said the APPRAISE system offers “an opportunity to save lives on the battlefield” and eventually could be of great assistance to emergency medical personnel throughout the country.

“Not too often do scientists have an idea or a dream, and then over time advance the science to take the concept to deployment and show that it works,” Reifman said. “I’m thankful that I’m here at the Army, which provides longevity in funding and support over time.”