The device, deemed WiGait, measures the walking speed of people with 95 to 99% accuracy using wireless signals while hanging on the wall of a person’s home. The signals emit nearly one-hundredth the amount of radiation that a standard cellphone emits.
“By using in-home sensors, we can see trends in how walking speed changes over longer periods of time,” said lead author and Ph.D. student Chen-Yu Hsu in a press release. “This can provide insight into whether someone should adjust their health regimen, whether that’s doing physical therapy or altering their medications.”
WiGait is 85 to 99% accurate when measuring stride length, which could help researchers better understand diseases that are characterized by reduced step size including Parkinson’s disease.
Typically, walking speed is measured by a physical therapist or clinician using a stopwatch. Consumer wearable devices use step count to estimate speed, and smartphones use GPS. Both are inaccurate and limited.
The WiGait doesn’t require a sensor to measure walking speeds with high details. It works by analyzing surrounding wireless signals and how it reflects off of a person’s body. The algorithms created by the CSAIL researchers are able to determine whether someone is walking, cleaning or brushing their teeth.
Dina Katabi, an MIT professor and leader of the research group, suggests that using WiGait could help uncover important health information for elderly users. Changes in walking speed could mean someone has suffered an injury and could be at risk of falling.
“Many avoidable hospitalizations are related to issues like falls, congestive heart disease or chronic obstructive pulmonary disease, which have all been shown to be correlated to gait speed,” said Katabi. “Reducing the number of hospitalizations, even by a small amount, could vastly improve healthcare costs.”
The WiGait differs from a camera because it only shows a moving dot on a screen.
Researchers hope they will be able to modify the system to work for people who have walking impairments from Alzheimer’s, Parkinson’s and multiple sclerosis.
“The true novelty of this device is that it can map major metrics of health and behavior without nay active engagement from the user, which is especially helpful for the cognitively impaired,” said Ipsit Vahia, a geriatric clinician at McLean Hospital and Harvard Medical School. “Gait speed is a proxy indicator of many clinically important conditions, and down the line, this could extend to measuring sleep patterns, respiratory rates and other vital human behaviors.”
The research will be presented in May at ACM’s CHI Conference on Human Factors in Computing Systems in Colorado. The research paper was published online on the MIT CSAIL website.
[Want to stay more on top of MDO content? Subscribe to our weekly e-newsletter.]