Robot Monitors in Homes of the Elderly
Robotic movement sensing systems in the homes of elderly people can predict with a high level of accuracy when a person is at high risk of having a fall and send warnings to support workers or relatives, say researchers
The US study, carried out in a senior housing centre in Missouri, found that telltale signs, including a sudden decline in walking speed, were linked to an 86% chance of having a fall within the next three weeks.
Elderly residents who were monitored by the system, which allowed clinicians to intervene before injuries occurred, were able to live independently for 1.8 years longer than those without the technology.
The scientists are now working to create benevolent Big Brother-style systems in which AI software would automatically interpret movement data and send text messages to relatives or support staff when a person was at risk or had suffered a fall.
Marjorie Skubic, a professor of electrical and computer engineering who is pioneering the approach at a residence linked to the University of Missouri, said: “Our goal is to help people age in the home of their choice, which in many cases will be their existing home. People say ‘I want to stay in my own home’.”
Speaking recently at the American Association for the Advancement of Science (AAAS) conference in Boston, Skubic challenged the common assumption that the later years of life are accompanied by a depressing but inevitable downward trajectory in mental and physical abilities.
With consistent monitoring and interventions, she said, it is possible to “square the life curve”, keeping people fit, healthy and living independently until they die.
With this goal in mind, Skubic has even installed the system in the home of her own parents, Lou and Mary Ann, and gets daily readouts of any sudden changes in their physical activity.
In one study, the scientists monitored 23 residents of an independent-living facility for elderly people, called Tiger Place, for between three months and four years each. They collected continual data on a Kinect-style system, which provided silhouette images that could be used to track a person’s daily movements.
The study found that when a person’s gait-speed dropped by 5cm/second within a week, this was a sign that they were at increased risk of a fall, in fact, 86% had a fall within three weeks when such a drop in walking speed was observed. By contrast, the elderly residents who had no change in walking speed had a background probability of falling of 19.5%.
The system could also pick up health issues such as urinary tract infections, which can cause rapid physical and mental declines in elderly people if untreated, by spotting when someone started going to the bathroom more frequently.
According to Skubic, participants in the scheme tend to find the idea of monitors watching their every movement reassuring rather than sinister or intrusive. “Some people talk about how they feel more secure,” she said.
