New AI safety system tracks seniors in care homes while giving them more privacy, researchers find

There's a new, non-invasive technology that monitors seniors in long-term care facilities without the need for cameras, fobs or other traditional wearable gadgets.

Researchers at the University of Waterloo in Ontario use a wall-hung, low-power radio system and artificial intelligence (AI) to take note of habits like how often residents go to the washroom, when they eat, or how long they usually watch TV. It can also alert care providers in the event of a fall.

Hajar Abedi is a PhD candidate in systems design engineering at the university and lead author of the study, which was published in the journal the Institute of Electrical and Electronics Engineers (IEEE) Internet of Things.

"We use artificial intelligence to actually make our lives easier because we can train them and they can do our job, and basically, our main purpose is to save lives using this AI technology," Abedi told CBC Kitchener-Waterloo.

Monitoring seniors as they go about their daily lives allows care providers to keep on top of any changes, she said.

"For example, we know your gait speed right now and in the next month. So based on what we see, we have a baseline of each individual," Abedi said.

When the monitor notes something abnormal, such as a recurring change in stride length while walking, "we can identify or send notification to caregivers. If [the seniors] walk slower over a period of time, [caregivers] can tell."

The monitoring system, called ElephasCare, works via a radio wave device similar in size to an internet modem and can be mounted on the wall. No cameras are installed.

This helps protect a person's privacy and is more beneficial than wearable devices, which can be cumbersome or sometimes require the person to interact with them to ensure they're working properly, Abedi said.

LISTEN | New wall-mounted AI sensor can monitor seniors and send security or health alerts:

'Interest levels are high'

Waterloo-based company Gold Sentintel has just started a pilot using the system, called ElephasCare, in a local long-term care facility.

Greg Dalton, chief executive officer of Gold Sentintel, said the initial safety concern focused on people having falls.

They "quickly realized that to make a meaningful impact, fall prevention had to become the core of our efforts."

According to the Public Health Agency of Canada, falls are a leading cause of injury-related hospitalization for Canadians 65 and older.

Dalton said staff in long-term care homes cannot watch residents 100 per cent of the time. If a resident falls at night when staffing levels tend to be lower, that person may remain on the floor for longer periods of time.

The longer it takes for staff to respond, the higher the chance of a bad health outcome, so being able to instantly alert staff about a fall will "prevent needless suffering," he said.

"The beauty of AI is that as the data set collected by ElphasCare grows, we'll be able to identify [other] trends and develop predictive models to better improve outcomes for seniors in care and the front-line staff caring for these elders.

"Interest levels are high," Dalton said. The company recently attended a long-term care conference in Toronto, where they spoke to people in the long-term care industry.

"They are all very interested in our unique approach that is both resident-centred and clinically informed as well. Our AI provides entirely new data to front-line caregivers to allow them to provide better, more focused personalized care to residents," he said.

Need to 'find the right balance'

Using this type of research and AI technology in long-term care homes across Canada is worth exploring, said Jodi Hall, chief executive officer of the Canadian Association for Long Term Care (CALTC).

Hall said the research out of the University of Waterloo "sounds like it could be an additional tool for teams to support residents' safety," but noted "no piece of technology is a replacement for a skilled care provider."

"At a time when long-term care is currently grappling with staffing shortages and burnout, we should not view technology as a solution by itself, as a multi-faceted recruitment and retention strategy is needed," Hall said in a statement to CBC News.

As well, Hall said, it would be important to engage people who live in long-term care facilities, their families, staff and government "to find the right balance" before moving ahead.

"For all of society, it is important that we continue to balance the advancement of technology with concerns that privacy is respected," Hall said.

"In particular, in long-term care, many of the residents are vulnerable and have complex care needs. It's of paramount importance that we maintain their dignity and privacy at all times."