Many people who rely on power wheelchairs to get around will soon let onboard AI negotiate obstacles, adjust speeds and avoid collisions. The algorithmic assistance will pair with millimeter-wave radar and continuous camera data for additional functionality.
That’s all thanks to clinical researchers at Northwestern University’s Feinberg School of Medicine and their commercial collaborators in the assistive technology industry.
The advance is one of four healthcare AI innovations under development at the Chicago institution and described in the winter edition of Northwestern Magazine.
Here’s a summary of each.
1. Building a better means of assistive mobility. Joystick controls are effectively out of reach for more than 15% of the 500,000 Americans using power wheelchairs. It’s mainly for them that Brenna Argall, PhD, is working with LUCI Mobility Inc. to smarten up power wheelchairs with AI. Make that mainly but not exclusively, says Argall, an engineer and roboticist at Northwestern’s McCormick School of Engineering and an associate professor of physical medicine and rehabilitation at Feinberg. In her words:
“A lot of this technology would be helpful for any wheelchair user, just as driver-assist technologies on today’s cars are helpful even if you already know how to drive. Even for wheelchair users who don’t have severe motor impairments, this technology could still increase their access to the world.”
2. Reducing stress during pregnancy. Pointing out that, in the absence of concerted support, prenatal anxiety can bring on complications for mother as well as child, the magazine spotlights a Northwestern team led by Feinberg associate professor of preventive medicine Nabil Alshurafa, PhD. The team is combining an AI algorithm with wearables and digital surveys to gauge and alleviate stress in mothers-to-be. Team member Maia Jacobs, PhD, an assistant professor of preventive medicine at Feinberg and of computer science at McCormick, says:
“We have the tools to address stress in the moment. This new algorithm gives us a way to not only provide an intervention when a person is in the throes of stress but also to look for ways to reduce stress across the pregnancy.”
3. Personalizing precision care for heart patients. Northwestern cardiologist Sanjiv J. Shah, MD, and colleagues are using machine learning to uncover patterns in diagnostic data that are indicative of heart muscle stiffening due to heart failure with preserved ejection fraction (HFpEF). “What we’ve done in HFpEF is applicable to so many medical conditions: diabetes, schizophrenia, depression, hypertension, you name it,” says Shah. More:
“There are a lot of skeptics of precision medicine—the right treatment for the right patient at the right time. But I’m a believer. With the AI technologies we have today, we can identify subtypes within broad constructs of diseases, and that knowledge can be harnessed to create tailored treatments.”
4. Improving autism diagnostics. Molly Losh, PhD, professor of learning disabilities and associate dean for research:
“Across prosodic speech features, some people with autism show sing-songy patterns while others might be monotone, and others might have completely different speech patterns. Machine learning has the potential to pull out those fine-tuned differences and really help us understand them.”
The feature article was reported by Clare Milliken, a senior writer at the magazine. It includes input from Abel Kho, MD, director of Northwestern’s Institute for Artificial Intelligence in Medicine. Read the full piece.
