Please ensure Javascript is enabled for purposes of website accessibility
Alzheimers.net
Menu

Researchers Use Algorithm to Predict Alzheimer's Years Before Symptoms

Alissa Sauer
By Alissa SauerOctober 25, 2017

Researchers know that people with mild cognitive impairment (MCI) are at an increased risk for Alzheimer’s. Unfortunately, there is no way to tell which people with MCI will go on to develop the disease.

However, a research team from McGill University recently developed an algorithm that can predict Alzheimer’s in people with MCI two years before symptoms occur, with 84% accuracy. Learn more about the algorithm and how it could impact the development of the disease.

The Link Between Alzheimer’s and Mild Cognitive Impairment

A new study published in the Neurobiology of Aging journal reveals how researchers from McGill University in Canada used imaging and machine-learning techniques to develop an algorithm to predict Alzheimer’s in people with mild cognitive impairment (MCI).

MCI affects 15-20% of adults over the age of 65 and is largely characterized by a decline in cognitive skills and memory. In people with MCI, the memory loss is noticeable but does not affect their ability to complete activities of daily living. However, people with MCI are more likely to develop Alzheimer’s than people who do not have the condition.

There is no way to predict which people with mild cognitive impairment will go on to develop Alzheimer’s, but researchers hope their algorithm will be able to help identify those individuals.

Researchers Use Algorithm to Predict Alzheimer’s with 84% Accuracy

The study used data from over 270 people with mild cognitive impairment who were part of the Alzheimer’s Disease Neuroimaging Initiative. Researchers looked at two years of PET brain scan data, noting beta-amyloid accumulation, if the individual had any Alzheimer’s risk genes and if that person ever received an Alzheimer’s diagnosis.

Then, the team programmed a computer to calculate each person’s risk of Alzheimer’s based on the first PET brain scan. The algorithm was successfully able to predict which participants with MCI went on to develop Alzheimer’s with 84% accuracy and up to two years before symptoms occurred.

Researchers hope that by identifying other biomarkers for Alzheimer’s, the algorithm can become even more accurate.

Have you seen a loved one progress from mild cognitive impairment to Alzheimer’s? We’d like to hear your stories in the comments below. 

Related Articles:

Alissa Sauer
Author

Alissa Sauer

Alzheimer’s Newsletter

Get the latest tips, news, and advice on Alzheimer’s prevention, treatment, stages and resources.

Contact UsatA Place for Mom

6330 Sprint Parkway, Suite 450

Overland Park, KS 66211

(866) 567-4049
Copyright © 2022 A Place for Mom, Inc. All Rights Reserved.Alzheimers.net complies with the Can-Spam Act of 2003.