We have completed maintenance on DiscoverMagazine.com and action may be required on your account. Learn More

You're (Brain Is) So Immature

Neuroskeptic iconNeuroskeptic
By Neuroskeptic
Sep 12, 2010 10:30 PMNov 5, 2019 12:17 AM


Sign up for our email newsletter for the latest science news

How mature are you? Have you ever wanted to find out, with a 5 minute brain scan? Of course you have. And now you can, thanks to a new Science paper, Prediction of Individual Brain Maturity Using fMRI.

This is another clever application of the support vector machine (SVM) method, which I've written about previously, most recently regarding "the brain scan to diagnose autism". An SVM is a machine learning algorithm: give it a bunch of data, and it'll find patterns in it.

In this case, the input data was brain scans from children, teenagers and adults, and the corresponding ages of each brain. The pattern the SVM was asked to find was the relationship between age and some complex set of parameters about the brain.

The scan was resting state functional connectivity fMRI. This measures the degree to which different areas of the brain tend to activate or deactivate together while you're just lying there (hence "resting"). A high connectivity between two regions means that they're probably "talking to each other", although not necessarily directly.

It worked fairly well:

Out of 238 people aged 7 to 30, the SVM was able to "predict" age pretty nicely on the basis of the resting state scan. This graph shows chronological age against predicted brain age (or "fcMI" as they call it). The correlation is strong: r2=0.55.

The authors then tested it on two other large datasets: one was resting state, but conducted on a less powerful scanner (1.5T vs 3.0T) (n=195), and the other was not designed as a resting state scan at all, but did happen to include some resting state-like data (n=186). Despite the fact that these data were, therefore, very different to the original dataset, the SVM was able to predict age with r2 over 0.5 as well.


What use would this be? Well, good question. It would be all too easy to, say, find a scan of your colleague's brain, run it through the Mature-O-Meter, and announce with glee that they have a neurological age of 12, which explains a lot. For example.

However, while this would be funny, it wouldn't necessarily tell you anything about them. We already know everyone's neurological age. It's... their age. Your brain is an old as you are. These data raise the interesting possibility that people with a higher Maturity Index, for their age, are actually more "mature" people, whatever that means. But that might not be true at all. We'll have to wait and see.

How does this help us to understand the brain? An SVM is an incredibly powerful mathematical tool for detecting non-linear correlations in complex data. But just running an SVM on some data doesn't mean we've learned anything: only the SVM has. It's a machine learning algorithm, that's what it does. There's a risk that we'll get "science without understanding" as I've written a while back.

In fact the authors did make a start on this and the results were pretty neat. They found that as the brain matures, long-range functional connections within the brain become stronger, but short-range interactions between neighbours get weaker and this local disconnection with age is the most reliable change.

You can see this on the pic above: long connections get stronger (orange) while short ones get weaker (green), in general. This is true all across the brain.

It's like how when you're a kid, you play with the kids next door, but when you grow up you spend all your time on the internet talking to people thousands of miles away, and never speak to your neighbours. Kind of.

Link: Also blogged about here.

Dosenbach NU, Nardos B, Cohen AL, Fair DA, Power JD, Church JA, Nelson SM, Wig GS, Vogel AC, Lessov-Schlaggar CN, Barnes KA, Dubis JW, Feczko E, Coalson RS, Pruett JR Jr, Barch DM, Petersen SE, & Schlaggar BL (2010). Prediction of individual brain maturity using fMRI. Science (New York, N.Y.), 329 (5997), 1358-61 PMID: 20829489

1 free article left
Want More? Get unlimited access for as low as $1.99/month

Already a subscriber?

Register or Log In

1 free articleSubscribe
Discover Magazine Logo
Want more?

Keep reading for as low as $1.99!


Already a subscriber?

Register or Log In

More From Discover
Recommendations From Our Store
Shop Now
Stay Curious
Our List

Sign up for our weekly science updates.

To The Magazine

Save up to 40% off the cover price when you subscribe to Discover magazine.

Copyright © 2024 Kalmbach Media Co.