Researchers at the University of Waterloo have developed a system that utilises Artificial Intelligence (AI) to non-invasively monitor older adults in their homes, enabling the early detection of potential health issues.
This system tracks an individual’s daily activities in real-time, collects critical information without the use of wearable devices, and promptly notifies medical professionals when intervention is required.
It operates by transmitting low-power waveforms through a space, such as a room in a long-term care facility or a private residence, using a wireless transmitter. The receiver captures and processes the reflected waves, which are then analysed by an AI engine for monitoring and detection purposes.
This system utilises low-power radar technology and can be easily installed on a wall or ceiling, eliminating the need for uncomfortable wearable devices that require frequent battery charging.
“After more than five years of working on this technology, we’ve demonstrated that very low-power, millimetre-wave radio systems enabled by machine learning and artificial intelligence can be reliably used in homes, hospitals and long-term care facilities,” Dr. George Shaker, an adjunct associate professor of electrical and computer engineering said.
“An added bonus is that the system can alert healthcare workers to sudden falls, without the need for privacy-intrusive devices such as cameras.”
Shaker and his colleagues’ research is particularly important as healthcare systems struggle to cope with the increasing demands of a growing elderly population.
The new system has already been rolled out in a number of long-term care homes.
“Using our wireless technology in homes and long-term care homes can effectively monitor various activities such as sleeping, watching TV, eating and the frequency of bathroom use,” Shaker said.
“Currently, the system can alert care workers to a general decline in mobility, increased likelihood of falls, possibility of a urinary tract infection, and the onset of several other medical conditions.”
In addition to the new AI system from the University of Waterloo, experts at Nottingham Trent University have developed a new smart sock that can alert older individuals to the increased risk of falls.
The prototype over-sock can detect near-falls with over 94 per cent accuracy, providing crucial information to caregivers and professionals who can take action to prevent an actual fall from occurring.
The over-sock contains a small motion sensor embedded at the ankle and can be linked to an internet-enabled device such as a phone via a detachable microcontroller that uses Bluetooth. Despite containing an electronic circuit, the over-sock is comfortable to wear as the technology is too small to be felt by the wearer. Additionally, the motion sensor is protected by a resin coating, ensuring the sock can still be washed as normal.
Innovators at @TrentUni have been working on a project which helps predict and detect when the elderly might be at more risk of falls with up to 94% accuracy!
— Marketing Nottingham (@MarketingNottm_) March 21, 2023
By analysing the data collected by the sensor, an algorithm can identify any unusual movements and distinguish between a fall and a near-fall. The aim is for the technology to notify emergency responders in the event of an actual fall, potentially saving lives.
Human trials of the device found that the over-sock is highly effective, accurately detecting falls 99.4 per cent of the time and near-falls 94.2 per cent of the time. The findings of this research have been published in the academic journal Electronic Textile Materials.
As we age, our risk of falls increases significantly. Falls can lead to serious injuries, including hip fractures, head injuries, and even death.
Nearly one in three older Australians have experienced a fall in the past 12 months, with one in five required hospitalisations. Although not all falls result in injury, the incident can often result in a person losing confidence in their own abilities and withdrawing from life to avoid the risk of suffering a fall again.