Catching them before they fall: MU gait study aims to predict fall risk in elderly
About one in three people age 65 and older will fall every year according to the Centers for Disease Control and Prevention. Falls are a leading cause of injury and death for this age group.
With the baby boomer generation entering old age, safety issues that affect the elderly are becoming more important than ever. What if there was a way to pick out physical factors that predict a fall and stop it before it happens?
That’s the focus of MU research that studied gait patterns in order to assess a subject’s risk of falling. And the results are promising.
Marjorie Skubic, an MU electrical and computer engineering professor who worked on the study, said the study found that the speed of a person’s walk translated to how likely they are to fall. It was something many had assumed, she said, but with the study, they were able to definitively show the correlation.
The study, “Estimation of Human Walking Speed By Doppler Radar for Elderly Care,” was recently published in the Journal of Ambient Intelligence and Smart Environments. The researchers teamed up with GE Global Research Center and deployed Doppler radar technology in homes at the independent senior living community TigerPlace, studying subjects’ gait patterns over the long term in order to assess their fall risk.
Doppler radar measures velocity. It’s the same technology meteorologists use when tracking weather patterns and cops use when clocking the speed of cars. The radar devices were placed in non-intrusive boxes in the subjects’ homes, where they could pick up motion and collect the gait data needed. The study found that increased fall risk correlated with changes in gait such as gait speed decline, stride frequency increase and stride length decrease.
Dominic Ho, an MU electrical and computer engineering professor, said engineering is used to analyze the collected data. Since the radar picks up all motion, it also picks up a lot of useless data — the pacing of a pet Chihuahua, the abnormal gait of a person who’s vacuuming.
Ho’s job is to find the signal in the noise.
“Now you have to process the radar signal so you can separate the human walking from all these other motions,” Ho said. “This is our task. To analyze what’s being captured and pick out the information hidden.”
Once that information is plucked out, Skubic said the gait can be translated to a score that tells patients whether they are at a low, medium or high risk of falling. This frequently updated information is useful to patients who may not see doctors very often.
“Maybe some of these people will get an assessment from a doctor every six months, perhaps if they’re lucky,” Skubic said. “So being able to see something on a continuous basis so you can immediately tell when there’s a fall risk that’s occurring makes a really important impact on being able to address this fall risk, and being able to do something about it.”
For example, if a person is having knee problems, the walking pattern will change. The walking pattern will continue to change over time if the knees get worse, perhaps warning the person to the increased risk of falling.
“The sensors can predict more than just falls,” Ho said. “They can also predict early signs of health changes that occur before older subjects would have time to see a physician.”
Skubic said the ultimate goal for this technology would be able to introduce some sort of therapy or intervention as a preventative measure against a predicted fall.
“That’s what our end game is; we would like to be able to prevent the fall in the first place,” Skubic said.
This issue isn’t just an abstract project for those on the team. Almost everyone has someone older in his or her life, which makes this a personal issue, too.
For example, Skubic related the story of her mother-in-law, who once fell and broke her shoulder in the middle of the night and lay there for hours. She experienced pain for the rest of her life.
“Many on our research team have these personal stories that make it concrete to us,” Skubic said. “This is why we’re doing this work in the first place. It’s really personal to us.”
Skubic hopes the sensors can one day go into private homes and be able to help many elderly people live more freely, including her own parents.
“That’s my motivation for much of this,” Skubic said. “To help my mom and dad age in place, with a high quality of life. Being independent. Being as healthy as possible.”