Researchers at Imperial College London have developed an algorithm that is able to predict a person’s ‘brain age’ based on their volume of brain tissue.
They found that having a brain age that is older than your actual age correlates with a higher risk of poor physical and mental health, as well as an increased likelihood of early death.
The researchers, writing in the journal Molecular Psychiatry, said that their model could eventually be used to identify those at the greatest risk of cognitive decline.
Dr James Cole, the study’s lead author, said: ‘We’ve come up with a way of predicting someone’s brain age based on an MRI scan of their brain. Our approach uses the discrepancy between their chronological age and what we call their brain-predicted age.
‘If your brain is predicted to be older than your real age then that reflects [that] something negative may be happening.
‘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.
‘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.’
The researchers are now working to refine the technique further by incorporating a more detailed MRI scanner.
The high cost of the equipment currently limits widespread use of the system, but the study’s authors say that the economies of scale could lower costs in the future.
Brain scans are undertaken for multiple medical reasons and are now considered routine, but this interesting study suggests it may be possible in the future to predict whether someone may be at future risk of poor health or dying early by using MRI brain scans. This is linked to the development of algorithms that can predict ‘brain age’ based on brain tissue volume and could have a significant benefit in terms of altering a patient’s lifestyle early in order to try to prevent future health problems.
However, there are significant caveats here. There is a large margin of error currently in the technique with the absolute error in determining brain age being up to five years. The technique remains a long way off from being used in clinical practice and is currently expensive, although economies of scale may reduce cost in the future.