A team of researchers from McGill University has taken steps toward using artificial intelligence to help doctors determine if a patient is likely to develop dementia years before symptoms develop.
Scientists from Douglas Mental Health University Institute's Translational Neuroimaging Laboratory at McGill used AI techniques and big data to develop an algorithm capable of recognizing signs of dementia two years before its onset. They employed a single amyloid PET scan of the brain of patients who are at risk of developing Alzheimer’s disease.
Dr. Pedro Rosa-Neto, the co-lead author of the study and Associate Professor in McGill’s departments of Neurology & Neurosurgery and Psychiatry, believes that this technology could change the way physicians manage patients and accelerate treatment research into Alzheimer’s.
"By using this tool, clinical trials could focus only on individuals with a higher likelihood of progressing to dementia within the time frame of the study. This will greatly reduce the cost and the time necessary to conduct these studies," adds Dr. Serge Gauthier, co-lead author, and Professor of Neurology & Neurosurgery and Psychiatry at McGill.
Scientists have known for some time that a protein called amyloid accumulates in the brains of patients with mild cognitive impairment (MCI), which often leads to dementia. The accumulation of amyloid begins decades before the symptoms of dementia show, but this protein could not be used reliably as a predictive biomarker because not all MCI patients develop Alzheimer’s.
To conduct the study, the McGill researchers gathered data already available through the Alzheimer’s Disease Neuroimaging Initiative (ADNI), a global research effort in which participating patients agree to complete a variety of imaging and clinical tests.
Sulantha Mathotaarachchi, a computer scientist from the research team, used hundreds of amyloid PET scans of MCI patients from the ADNI database to train the team’s algorithm to identify which patients would develop dementia before symptoms develop, with an accuracy of 84 percent. The team is still trying to find other biomarkers for dementia that could be incorporated into the algorithm to improve the software’s prediction capabilities.
“This is an example how big data and open science brings tangible benefits to patient care," said Dr. Rosa-Neto, who is also director of the McGill University Research Centre for Studies in Aging.
This new software is available online to scientists and students, but physicians won’t be able to use it in clinical practice before it is certified by health authorities. The McGill team is conducting further testing to validate the algorithm in different patient cohorts, like those with concurrent conditions such as small strokes.
The findings were published in the journal Neurobiology of Aging.