Like 40-year-old Khloe Kardashian, you may have been tempted to test for your biological age in the hopes that it will tell you that you’re only 28 on the inside, at least. But what these tests have so far been unable to reveal is how old your brain is. Now, a study may have found a new way to calculate how fast your grey matter is ageing – a finding which could help to predict and prevent dementia.
Unlike your chronological age, which counts the number of years since you were born, your biological age depends on how well your body is functioning and how worn down your cells and tissues are. Two people can be the same age chronologically, but have different biological ages.
Most of the time, biological age is measured via DNA methylation – a chemical process that changes how your genes look at the cellular level. But the researchers behind the new study, published in journal Proceedings of the National Academy of Sciences, say this method doesn’t work for our brains.
That’s because the brain’s protective fortress, known as the blood-brain barrier, doesn’t allow blood cells to cross into the brain. So a blood sample from, say, your arm won’t contain any information about how much your brain has aged. And forget getting a blood sample directly from the brain – the risk of damage is too high.
To overcome these obstacles, the researchers from the University of Southern California, in the US, created a non-invasive method combining MRI scans and artificial intelligence (AI). In the future, they say it could help to prevent and treat dementia.
“This is a novel measurement that could change the way we track brain health both in the research lab and in the clinic,” said Prof Andrei Irimia, senior author of the study. “Knowing how fast one’s brain is ageing can be powerful.”
First, Irimia and his team used AI to study thousands of MRI brain scans of people of different ages and brain health conditions. This helped them create a baseline for comparison, allowing the scientists to estimate the biological age of an individual’s brain. However, while this method could show how old a brain appeared, it couldn’t predict how fast it was ageing or what might happen in the future.
Next, the team built a model called a three-dimensional convolutional neural network (3D-CNN). The 3D-CNN essentially compares an individual’s original and follow-up MRI scans for more precise results. Crucially, the model also identified brain zones which were showing faster brain ageing.
The team tested this model on 104 adults with healthy brains and 140 Alzheimer’s patients, and found that brain ageing speed was closely linked to cognitive function. In other words, people with faster brain ageing were more likely to experience degraded memory and processing speed.
Not only do the researchers think the AI could track down early signs of cognitive decline, but – given it can make accurate predictions about disease trajectories – it could also help doctors choose the best treatments.
The other thing the researchers are excited about is how the model could provide insights into how genetics, environment and lifestyle affect brain ageing.
Irimia said: “One thing that my lab is very interested in is estimating risk for Alzheimer’s; we’d like to one day be able to say, ‘Right now, it looks like this person has a 30 per cent risk for Alzheimer's.’ We're not there yet, but we're working on it.”
He added: “I think this kind of measure will be very helpful to produce variables that are prognostic and can help to forecast Alzheimer's risk. That would be really powerful, especially as we start developing potential drugs for prevention.”
Read more: