When most of us stumble and fall, we’re likely to end up with bruises, a chipped tooth, or maybe scraped knees and elbows. But as we age, various factors can contribute to increasing the risk of falling and how badly we’ll be injured when we do.
In the United States, the Centers for Disease Control and Prevention reports, falls are the leading cause of injury-related death among adults aged 65 and older; and the rate of falls for people in this age group increased by 30% between 2009 and 2018, costing the nation’s healthcare system an estimated $50 million a year.
While there are things older adults can do to improve balance and strength, a Stanford researcher Karen LiuPhD, leads a project to create a wearable robotic device to help predict and prevent such falls.
Solve problems with AI
Liu, a computer science professor, is one of many researchers who recently received funding under the new Stanford Institute for Human-Centered Artificial Intelligence Hoffman-Yee Fellowship Program.
The program, supported by philanthropists Reid Hoffman and Michelle Yee, is a multi-year, multidisciplinary initiative to use artificial intelligence to solve real-world problems. Six projects received funding under the inaugural program.
“These projects will initiate and support exciting new collaborations across the university,” said Jean Etchemendy, PhD, Denning Co-Director of HAI and Patrick Suppes Family Professor in the School of Humanities and Sciences. Grant recipients represent Stanford’s schools of humanities and sciences, medicine, business, education, engineering, and law.
Anticipating falls, stabilizing balance
With their project, Liu and his team – which includes VJ PeriyakoilMD, a geriatrics specialist and associate professor of medicine and neurology – are looking to develop wearable robotic devices to aid in human locomotion.
They plan to develop a semi-rigid exoskeletal device that would be placed around a user’s hip area to provide additional control and power to the muscles in that area. It could later spread to more of the leg, Liu said.
With a built-in computer, the device would use AI to predict falls by monitoring the user’s movements. If the device detects a possibility of a fall, it would help stabilize the user’s balance and timing to avoid the fall. “It might help the user move to the next step a bit faster or make it longer or shorter,” Liu said.
Robots to diagnose developmental disabilities
Another of the six health outcomes projects aims to create playful, socially interactive robots that can more effectively diagnose people with developmental disabilities, including autism.
Dan YaminsPhD, Assistant Professor of Psychology and Computer Science, leads the team, which includes Denis WallPhD, autism expert and Stanford Medicine associate professor in pediatrics, psychiatry, and biomedical data science.
“By studying the human brain, we can learn about the underlying algorithms that the brain runs, and then use those algorithms to improve the performance and human-likeness of machines,” Yamins said. “The most amazing learning machines on the planet are human children.”
Photo by Christophe Wu, depicting previous research by Karen Liu, PhD