Skip to main content

USC Studies Potential for AI-Enabled Drones in Emergency Care

Analysis  |  By Eric Wicklund  
   May 18, 2023

Researchers are studying a Toronto-based program that deploys drones equipped with AED devices alongside ambulances to emergencies involving cardiac arrest cases.

Researchers at the University of California are studying whether AI-powered drones can be used to deliver emergency care in rural and remote areas.

As detailed in a study recently published in Operations Research and partially financed by the National Science Foundation, AI technology could be used to determine the quickest means of getting emergency care to a specific location. The study focused on a Toronto-based program in which drones equipped with automated external defibrillators (AEDs) were deployed along with ambulances to cardiac arrest events.

“Our methods have the potential to revolutionize the way we design and optimize systems in data-scarce settings that extend beyond emergency response," Michael Huang, a doctoral candidate in the data science and operations department at the USC Marshall School of Business and corresponding author of the study, said in a press release. "It can help us make more informed and efficient decisions across a range of fields where data is limited.”

Drones have been used in the past to ferry supplies and tests between hospitals and to residents in hard-to-reach areas. Among the health systems using drones are Intermountain Health, which launched a drone delivery service in October 2022, the University of Michigan's Michigan Medicine, which uses drones to deliver prescription medications, WakeMed Health & Hospitals in North Carolina, Kaiser Permanente (which is using drones to deliver prescriptions to a retirement community in Florida) and the Rady Children’s Institute for Genomic Medicine in San Diego.

[See also: Alabama Project Tests Drones for Rural Healthcare Delivery.]

At USC, the focus is on having drones available as a resource for emergencies when an EMS vehicle might take a long time to reach the scene.

“We initially thought that the main question was where to deploy the drone, but in reality, the first-order question is where to put the drone depots,” Vishal Gupta, an associate professor of data sciences and operations at USC Marshall, said in the press release. “We want to strategically place them in locations that are both close to where cardiac arrests occur, but also in areas that are difficult to reach by ambulance. The challenge here is that data on ambulance travel times to remote locations is scarce, making it difficult to estimate. Ambulances rarely go to these remote locations, so we don’t have a lot of data on travel times."

“We often hear about big data and its potential, but in many cases, data is still scarce, especially in settings where data collection is expensive or limited by privacy concerns,” he added. “There are also cases where collection events are rare, which can make it challenging to design systems and make informed decisions. With AI tools, we can address these challenges and make better decisions even in data-limited settings.”

Eric Wicklund is the associate content manager and senior editor for Innovation, Technology, and Pharma for HealthLeaders.


Several health systems have been using or studying the use of drones to deliver medical supplies and tests between hospitals or to remote patients.

Researchers at the University of California are studying whether AI technology can be used to dispatch drones with medical equipment to an emergency site that can't be quickly accessed by EMS vehicles.

The study is focused on how to determine when a drone would be dispatched and how and where to locate drones for easy access and deployment by healthcare providers.

Get the latest on healthcare leadership in your inbox.