Autism Detectable In Infants, Study Suggests
Long before an official diagnosis, a single brain scan at 6 months of age may be able to predict with near perfect accuracy which babies will develop autism.
By using a technique known as machine learning to look at brain patterns in infants, researchers say they were able to successfully flag most children on the spectrum well before symptoms appeared.
The findings published Wednesday in the journal Science Translational Medicine may offer a first step to developing an early detection method for autism, researchers said.
Advertisement - Continue Reading Below
For the study, 59 sleeping babies spent 15 minutes each in an MRI machine so brain activity in 230 neural regions could be observed. Researchers then analyzed how different regions worked with each other, using a machine learning classifier — essentially a computer program — to distinguish patterns.
All of the children studied were considered to be at high risk for autism because they had an older sibling with the disorder.
Ultimately, 11 of the babies were diagnosed with autism at age 2, nine of whom were identified by the machine learning classifier as babies.
“When the classifier determined a child had autism, it was always right. 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,” said Robert Emerson, who led the study as a postdoctoral fellow at the University of North Carolina.
The findings come after the same group of researchers reported earlier this year that a slightly different approach, also using MRI scans, could identify children with the developmental disorder before symptoms appeared. In that research, however, children received brain scans multiple times so that changes over time could be observed.
Those behind the research say they are looking to replicate the findings in a larger study group.
“Although the findings are early-stage, the study suggests that in the future, neuroimaging may be a useful tool to diagnose autism or help health care providers evaluate a child’s risk of developing the disorder,” said Joshua Gordon, director of the National Institute of Mental Health, which helped fund the work.