box10.gif (1299 bytes)

 

 

 

 

 

 

Long-term care

Intelligent systems will help elderly patients at home

TORONTO – Researchers at the Toronto Rehabilitation Institute (Toronto Rehab) have developed home-based computer systems that use artificial intelligence to promote independence and ensure the safety of older people living at home.

In many cases, older individuals might experience memory loss, confusion, or other cognitive problems as a result of Alzheimer’s disease or stroke, but intelligent, self-adaptive technologies have great potential for enabling adults with cognitive impairments to safely remain in their homes.

“Often when a person gets moderate to severe levels of impairment, they are taken out of their home and put into a care facility,” says lead scientist Dr. Alex Mihailidis, a mechanical and biomedical engineer and researcher at Toronto Rehab. “We are using artificial intelligence to support aging-in-place, so that people can remain in their homes for as long as possible.”

Dr. Mihailidis and his research team at the Intelligent Assistive Technology and Systems Lab, a Toronto Rehab and University of Toronto joint venture, have developed a personal emergency response system that can detect when a person has fallen and call for help. Using ceiling-mounted cameras in the house, pictures are fed to the computer system, which analyses the images to determine the position of the occupant and whether or not a fall has occurred. A voice recognition system will then ask the occupant if they need help.

“Often we hear of cases where an individual has fallen and is found three days later lying on the bathroom or kitchen floor. When this happens, their chances of survival and recovery are drastically reduced,” says Dr. Mihailidis. “Our emergency response system will ensure they get the help they need immediately.”

Alzheimer’s disease and other related dementias often affect a person’s ability to perform daily personal care activities, such as proper toileting. The Toronto Rehab team has developed a “talking” bathroom outfitted with a computer screen that gives video and verbal cues to assist with hand washing.

It is the ability of an intelligent system to monitor a person and situation, take into account probabilities and statistics, and come up with a course of action that distinguishes an intelligent home from a smart home, according to Dr. Mihailidis. “Smart homes respond to pre-programmed requests, but cannot learn and adapt. Our systems use computer algorithms that act more like a human in terms of rational thought and decision-making. They actually learn and adapt to a person’s needs.”

Toronto Rehab researchers are the first internationally to test home-based artificial intelligence systems in clinical trials. One study found that subjects’ ability to complete hand-washing steps without help from a caregiver increased by approximately 25% when the computer prompting system was employed. Another study showed that the team’s emergency response system detected 77% of falls staged in the lab.

“Our systems are not intended to replace professional or family caregivers. However, the results from our studies are encouraging and show that the use of artificial intelligence in a home setting can provide safety and security and enhance the quality of life for older adults who would like to remain in their homes as they age,” says Dr. Mihailidis.

About Toronto Rehabilitation Institute
The Toronto Rehabilitation Institute (Toronto Rehab) is at the forefront of one of the most important and emerging frontiers in healthcare today – rehabilitation science. As a fully affiliated teaching and research hospital of the University of Toronto, Toronto Rehab is Canada’s largest provider of adult rehabilitation services, complex continuing care, and long-term care. Toronto Rehab is advancing rehabilitation knowledge and practice through research, education and patient care. More information is available at: www.torontorehab.com.

 

HOME - CURRENT ISSUE - ABOUT US - SUBSCRIBE - ADVERTISE - ARCHIVES - CONTACT US - EVENTS - LINKS