Researchers study use of AED-carrying drones to avoid wasting lives
By DRONELIFE Feature Editor Jim Magill
In responding to medical emergencies, corresponding to when an individual is suffering a heart attack, seconds count. Shortening the length of time between when a call is placed to a 911 operator and when medical assistance is delivered to the scene could mean the difference between life and death.
To satisfy this challenge, researchers within the U.S. and Canada are studying the event of systems that use drones to deliver automatic electronic defibrillators (AEDs), portable and straightforward to operate devices that abnormal people on the scene can use to maintain the patient alive while waiting for the emergency medical technicians to reach by ambulance.
A recent study by scientists on the University of Southern California used artificial intelligence (AI) and machine learning (ML) technology to look at the optimal strategies for siting locations for drone bases or depots, to be certain that the AED-equipped UAVs provide the perfect time savings for his or her emergency response.
“Drone depots, like many other things, have a bit little bit of NIMBYism attached to them,” Vishal Gupta, lead creator of the USC study said in an interview. The USC scientists based their research largely on an earlier study of using drones as first responders, performed by scientists on the University of Toronto.
Unlike the UT research, which focused largely on the variety of bases and drones needed to attain the perfect time savings across a large geographic area, the USC scientists examined strategies for determining the perfect places to site the drone depots, based on limited or “noisy” data sets.
“The query that we wanted to have a look at was not what number of drones, because we could at all times buy a couple of more, but reasonably, where should we locate the drone depots?” Gupta, associate professor of knowledge sciences and operations on the Marshall School of Business said.
“Everyone likes the thought of this pilot program, and of using drones to avoid wasting lives. No one actually wants a drone depot of their backyard. So, the positioning of those drone depots and the variety of drone depots needed to make this method work gave the impression of a more first-order query in our mind,” said Gupta.
The choice on where to site a drone depot in an urban area is a comparatively easy one: place the depot in a centralized location where the drone carrying the lifesaving equipment is most apt to serve the best number of individuals within the shortest time-frame. The tricky part lies in easy methods to best site drone depots in rural areas, where ambulances may need to travel long distances over gravel or dirt roads to get to distant areas and reach the patient.
Decision makers deciding where to locate drone depots in such areas often must operate on incomplete data as to the common time it takes for an ambulance to travel to such distant locations. The information they do have are further subjected to “noise” corresponding to how the condition of rural roads might affect an ambulance’s travel time.
“Are these dirt roads still maintained? Will they find a way to seek out this location on this rural place?” Gupta said “Because we’re tailored to take care of that, we do a significantly better job of predicting travel time for rural locations, and so consequently propose drone depot locations that higher serve rural communities.”
To construct their model, the USC researchers used the UT research data concerning the frequency and placement of where cardiac arrest events were happening in the encompassing Toronto area. Using that historic data and other relevant data for a given area — corresponding to population density, the population’s median age and income level — Gupta’s team built machine learning (ML) models to predict the frequency and placement of where cardiac arrest events were almost certainly to occur.
“I believe the large contribution is the optimization algorithm. We developed an AI method that optimizes the location of the depots and on condition that information, we attempt to ensure that that we will serve essentially the most people effectively with these drones,” he said.
The UT study had determined that for specific large region of eastern Canada, a drone-as-first-responder system would require 81 bases and 100 AED-delivery drones to scale back the common 911 response time for a cardiac emergency by three minutes.
“Cardiac arrest is one in all the leading causes of death. Heart disease kills somewhere between 300,000 and 400,000 people in North America yearly,” Justin Boutilier, the lead creator of the UT study, said in an interview. “On the whole, we discover that drones can, after all, improve response times and also you don’t need a lot of them to do it.”
Boutilier, who co-authored the study as a PhD student on the University of Toronto and is now an assistant professor on the University of Wisconsin Madison, said there are a variety of pilot programs for using drones to deliver AEDs to cardiac patients underway within the Toronto area and in Salt Spring Island, British Columbia on the west coast area of Canada.
“There have been some tests within the U.S. as well. There’s a bunch at Duke that’s doing research on this topic, and has been collaborating with the EMS [emergency medical service] folks.” Several cities in Sweden have already implemented such drone response programs and in January officials there for the primary time credited a drone-delivered AED with saving someone’s life.
“I believe something like this must occur within the cardiac arrest space, especially with out-of-hospital cardiac arrest, in order that we will actually see improvement in outcomes here,” Boutilier said. “I’m enthusiastic about it.
Read more: