Researchers have developed a technique using MRI scans and a machine learning algorithm to better predict a person's brain age to identify patients at risk of early death. Photo by Volt Collection/Shutterstock
April 25 (UPI) -- Researchers at the Imperial College London are predicting a person's brain age to determine if they are at risk of early death.
The team of neuroscientists at Imperial College London combined magnetic resonance imaging, or MRI, with a machine learning algorithm to train computers to give a predicted brain age for people based on their volume of brain tissue.
"We've come up with a way of predicting someone's brain age based on an MRI scan of their brain," Dr. James Cole, a research associate in the Department of Medicine at Imperial College London, said in a press release. "Our approach used the discrepancy between their chronological age and what we call their brain-predicted age as a marker of age-related atrophy in the brain. If your brain is predicted to be older than your real age than that reflects something negative may be happening."
The work was part of a worldwide effort by scientists to find reliable biomarkers that can be used to measure age.
The technique measures brain volume and uses machine learning to estimate the overall loss of white and grey matter, which is a key component in the aging process in the brain.
Cole and his team then tested the technique on publicly available datasets of MRI scans of more than 2,000 healthy people's brains, resulting in maps that could accurately predict a person's age.
Researchers tested the technique on a population of 669 older adults over age 70 or older in Scotland who were part of the Lothian Birth Cohort 1936.
The study found that the greater the difference between a person's brain age and their actual age, the higher their risk of poor mental and physical health and early death. Participants whose brain age was older than their chronological age performed worse on standard physical tests of healthy aging including lung capacity, walking speed and grip strength.
Participants with older brains were statistically more likely to die before age 80, and had an average discrepancy between brain age and chronological age of eight years for males and two years for females.
"In the long run it would be great if we could do this accurately enough so that we could do it at an individual level," Cole said. "Someone could go to their doctor, have a brain scan and the doctor could say 'your brain is 10 years older than it should be,' and potentially advise them to change their diet or lifestyle or to start a course of treatment. However, at the moment, it's not sufficiently accurate to be used at that sort of individual level."
The study was published in Molecular Psychiatry.