Canadian researchers train AI algorithm to predict cognitive decline

8 October 2018 (Last Updated October 8th, 2018 10:40)

Researchers at McGill University in Canada have devised a new artificial intelligence (AI) based approach to predict cognitive decline that may lead to Alzheimer’s disease over the next five years.

Canadian researchers train AI algorithm to predict cognitive decline
Algorithm learns signatures from MRI, genetics and clinical data to predict cognitive decline leading to Alzheimer’s. Credit: Many Wonderful Artists via Flickr.

Researchers at McGill University in Canada have devised a new artificial intelligence (AI) based approach to predict cognitive decline that may lead to Alzheimer’s disease over the next five years.

Led by McGill University psychiatry department assistant professor Mallar Chakravarty, the team designed and trained an algorithm to learn signatures from MRI, genetics and clinical data.

The researchers used data from more than 800 people under the Alzheimer’s Disease NeuroImaging Initiative. Participants included healthy individuals, people with mild cognitive impairment, and Alzheimer’s patients.

“At present, the researchers are working towards validating the algorithm’s accuracy using new data in order to improve predictions and assess its extent of detection.”

Findings from the study were then replicated on a separately obtained sample from the Australian Imaging and Biomarkers Lifestyle Study of Ageing.

It is expected that by predicting an individual’s cognitive decline towards Alzheimer’s, the algorithm will help in potentially early prevention and the right treatment for the disease.

Chakravarty said: “At the moment, there are limited ways to treat Alzheimer’s and the best evidence we have is for prevention. Our AI methodology could have significant implications as a ‘doctor’s assistant’ that would help stream people onto the right pathway for treatment.

“For example, one could even initiate lifestyle changes that may delay the beginning stages of Alzheimer’s or even prevent it altogether.”

At present, the researchers are working towards validating the algorithm’s accuracy using new data in order to improve predictions and assess its extent of detection.

The team hopes that more data will aid in the better identification of those at greatest risk for cognitive decline leading to Alzheimer’s.

The Alzheimer Society of Canada report revealed 564,000 Canadians suffering from Alzheimer’s or another form of dementia in 2016. This is estimated to reach 937,000 within 15 years.