Va. first responders test AI assistant for emergency scenes
CognitiveEMS, developed by University of Virginia researchers, provides prompts to support responders' decision-making
By Laura French
CHARLOTTESVILLE, Va. — First responders in Virginia are testing an AI assistant developed by researchers that is designed to aid decision-making at emergency scenes.
CognitiveEMS was developed at the University of Virginia (UVA) School of Engineering and is being tested by first responders from the North Garden Volunteer Fire Company and Richmond Ambulance Authority in simulated emergency scenes to help evaluate and improve the tool, according to a UVA news release.
The tool uses artificial intelligence that listens to first responders' conversations at the scene and provides prompts meant to improve responders' situational awareness and support decision-making. The system listens for information such as vitals, symptoms and other facts involved in the incident, then analyzes the information to provide the most helpful prompt for the situation.
For example, if the assistant hears that a patient is having difficulty breathing, it may prompt the responder by asking if they have taken the patient's temperature to potentially distinguish between infection and chronic disease, according to the university. However, the technology is not meant to direct or command first responders' actions, researchers said.
"We were not looking to tell a responder what to do. We always want to leave the decision-making with the responders, so that they are always in control," said Ronald D. Williams, associate professor of electrical and computer engineering at UVA, in a statement. "The objective is to reduce the cognitive load on the responders, helping them focus on the highest-priority tasks throughout the process."
CognitiveEMS also has an automatic forms feature that extracts and records timestamped information to generate real-time incident reports that can be edited if needed.
"Documentation is difficult to do in the field when you are focusing on keeping your patient alive. The only practical means for filling out the forms is after the patient is in the hands of hospital staff," stated Williams, who is also a 25-year veteran and life member of the Charlottesville-Albermarle Rescue Squad. "I remember having to go down the hall to another room and fill out a form that documented everything you did, everything you saw, and the times these things happened. That's just tough."
UVA engineers, the North Garden Volunteer Fire Company and Richmond Ambulance Authority have been working on the prototype for CognitiveEMS since 2017, when UVA received a $1.1 million grant from the U.S. Department of Commerce's National Institute of Standards and Technology (NIST), as part of the Public Safety Innovation Accelerator Program. The project is led by Homa Alemzadeh, assistant professor in the Charles L. Brown Department of Electrical and Computer Engineering at UVA. Alemzadeh and her team shared their progress on the technology in a demonstration at the virtual 2020 NIST Annual Public Safety Broadband Stakeholder Meeting in July.
"I enjoy thinking about the real-world implications of research," Alemzadeh said in a statement. "A device that assists responders while they are delivering medical care at the scene could reduce stress and cognitive overload and improve outcomes for both the patients and responders."
North Garden Volunteer Fire Company Chief George Stephens said firefighters have been responding to an increasing number of medical calls over his more than 20 years in the fire service, and that he was happy to contribute to a project that could potentially revolutionize their work.
"It's hard to simulate a real-world environment in the lab and even harder to account for factors that come into play and in public-facing situations," stated Stephens, who also leads a team of engineers as an employee at Northrop Grumman. "I am glad we can lend our front-line expertise to the project."