For years, scientists have been looking for a way to diagnose autism earlier, while the children’s brains are still at their most flexible. A method of predicting autism at a very young age would mean earlier intervention and hopefully more success in helping children with autism learn to communicate.
Recently, a study published in the journal Science Translational Medicine attempted to find a new way of determining which babies would later show signs of autism and which ones wouldn’t using certain markers in their brains. Researchers conducted MRIs on 59 sleeping 6-month-olds, all of whom had a sibling with autism and were therefore at increased risk of developing the disorder. The 15-minute scans measured 230 neural regions in each child’s brain, and then researchers used a “machine learning classifier” to observe how the parts of the brain interacted. 974 connections between different parts of the brain were identified as predictors for autism.
Out of the 59 babies, 11 were later diagnosed with autism at the age of two. The MRI scan correctly predicted that outcome in nine of the cases.
“When the classifier determined a child had autism, it was always right,” says Robert Emerson, the postdoctoral fellow at the University of North Carolina who led the study. “But it missed two children. They developed autism but the computer program did not predict it correctly, according to the data we obtained at 6 months of age.”
This study was done on a relatively small scale, so its results will need to be replicated before the approach can be declared successful. However, it is the first study to show that a single brain scan can predict autism rather than a series of scans over time. And nine out of 11 accurate predictions (about 82%) is definitely a number worth investigating further. Even if an MRI cannot definitively diagnose autism, it could be added to the growing list of tools we have to recognize, diagnose, and understand this complex disorder.
“I think the most exciting work is yet to come, when instead of using one piece of information to make these predictions, we use all the information together,” says Emerson.
Emerson and his colleagues are now working on linking particular brain activity patterns to behaviors and abilities in people with autism.
Elizabeth Nelson is a wordsmith, an alumna of Aquinas College in Grand Rapids, a four-leaf-clover finder, and a grammar connoisseur. She has lived in west Michigan since age four but loves to travel to new (and old) places. In her free time, she. . . wait, what’s free time?