Artificial intelligence predicts dementia before onset of symptoms

August 22, 2017, McGill University
Credit: McGill University

Imagine if doctors could determine, many years in advance, who is likely to develop dementia. Such prognostic capabilities would give patients and their families time to plan and manage treatment and care. Thanks to artificial intelligence research conducted at McGill University, this kind of predictive power could soon be available to clinicians everywhere.

Scientists from the Douglas Mental Health University Institute's Translational Neuroimaging Laboratory at McGill used techniques and to develop an algorithm capable of recognizing the signatures of dementia two years before its onset, using a single amyloid PET scan of the brain of patients at risk of developing Alzheimer's disease. Their findings appear in a new study published in the journal Neurobiology of Aging.

Dr. Pedro Rosa-Neto, co-lead author of the study and Associate Professor in McGill's departments of Neurology & Neurosurgery and Psychiatry, expects that this technology will change the way physicians manage patients and greatly accelerate treatment research into Alzheimer's disease.

"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.

Amyloid as a biomarker of dementia

Scientists have long known that a protein known as amyloid accumulates in the brain of patients with mild cognitive impairment (MCI), a condition that often leads to dementia. Though the accumulation of amyloid begins decades before the symptoms of dementia occur, this protein couldn't be used reliably as a predictive biomarker because not all MCI patients develop Alzheimer's disease.

To conduct their study, the McGill researchers drew on data 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 assessments.

Sulantha Mathotaarachchi, a computer scientist from Rosa-Neto's and Gauthier's 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, with an accuracy of 84%, before symptom onset. Research is ongoing to find other biomarkers for that could be incorporated into the algorithm in order to improve the software's prediction capabilities.

"This is an example how big data and open science brings tangible benefits to patient care," says Dr. Rosa-Neto, who is also director of the McGill University Research Centre for Studies in Aging.

While new software has been made available online to scientists and students, physicians won't be able to use this tool in clinical practice before certification by health authorities. To that end, the McGill team is currently conducting further testing to validate the algorithm in different patient cohorts, particularly those with concurrent conditions such as small strokes.

Explore further: Early abnormalities of Alzheimer's disease: It takes two (proteins) to tango

More information: Sulantha Mathotaarachchi et al. Identifying incipient dementia individuals using machine learning and amyloid imaging, Neurobiology of Aging (2017). DOI: 10.1016/j.neurobiolaging.2017.06.027

Related Stories

Early abnormalities of Alzheimer's disease: It takes two (proteins) to tango

April 20, 2016
For years, neuroscientists have puzzled over how two abnormal proteins, called amyloid and tau, accumulate in the brain and damage it to cause Alzheimer's disease (AD). Which one is the driving force behind dementia? The ...

Brain amyloid PET scans enhance the diagnosis of Alzheimer's

July 17, 2017
The build-up of amyloid protein in the brain is a hallmark feature of Alzheimer's disease, and its detection often relies on the testing of brain and spinal fluid samples. More recently, PET brain scans have been able to ...

Machine learning can predict rate of memory change

July 31, 2017
In new research published today, researchers have created a machine learning algorithm that is able to form two distinct groups of people who have early memory problems known as mild cognitive impairment. The algorithm was ...

Single dual time-point PET scan identifies dual Alzheimer's biomarkers

June 14, 2017
More people die of Alzheimer's disease than prostate and breast cancer combined. Identifying the disease before major symptoms arise is critical to preserving brain function and helping patients maintain quality of life. ...

Can poor sleep boost odds for Alzheimer's?

July 18, 2017
(HealthDay)— Breathing problems during sleep may signal an increased risk for Alzheimer's disease, a trio of studies suggests.

Unique structure of brain blood vessel amyloid latest clue to Alzheimer's development?

November 22, 2016
Accumulating amounts of amyloid, which is a fragment of a larger protein, in the brain have been associated with the development of dementia, including Alzheimer's disease. Now a team of neuroscience and biochemistry researchers ...

Recommended for you

Pregnancy history may be tied to Alzheimer's disease

July 18, 2018
A woman's history of pregnancy may affect her risk of Alzheimer's disease decades later, according to a study published in the July 18, 2018, online issue of Neurology, the medical journal of the American Academy of Neurology. ...

Molecular tracer, seen with PET scan, shows concentrations of abnormal proteins

July 17, 2018
In a small study of military personnel who had suffered head trauma and had reported memory and mood problems, UCLA researchers found brain changes similar to those seen in retired football players with suspected chronic ...

Yale-developed test for Alzheimer's disease directly measures synaptic loss

July 16, 2018
Yale researchers have tested a new method for directly measuring synaptic loss in individuals with Alzheimer's disease. The method, which uses PET imaging technology to scan for a specific protein in the brain linked to synapses, ...

New study highlights Alzheimer's herpes link, experts say

July 12, 2018
A new commentary by scientists at the Universities of Manchester and Edinburgh on a study by Taiwanese epidemiologists supports the viability of a potential way to reduce the risk of Alzheimer's disease.

Practice imperfect—repeated cognitive testing can obscure early signs of dementia

July 12, 2018
Alzheimer's disease (AD) is a progressive, neurodegenerative condition that often begins with mild cognitive impairment or MCI, making early and repeated assessments of cognitive change crucial to diagnosis and treatment.

The 'Big Bang' of Alzheimer's: Scientists ID genesis of disease, focus efforts on shape-shifting tau

July 10, 2018
Scientists have discovered a "Big Bang" of Alzheimer's disease – the precise point at which a healthy protein becomes toxic but has not yet formed deadly tangles in the brain.

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.