An early detection of autism is key because it gives clinicians and parents ample time to formulate a treatment plan. But unfortunately autism is difficult to identify in infants and young children because many of its symptoms aren’t noticeable until the child is walking, talking and regularly interacting with his environment.
But work by Children’s Hospital Boston researchers suggests that a noninvasive test to evaluate an infant’s autism risk could one day be available for children under a year of age.
The test combines electroencephalograms (EEGs), which record electrical activity in the brain, with machine-learning algorithms, and seeks to identify patterns in brain activity that are unique to children who are considered to be at a high risk for developing autism. (In this case, high-risk meant the child had an older sibling with a confirmed diagnosis of an autism spectrum disorder). In this pilot study, the researchers’ system had 80 percent accuracy in distinguishing between 9-month-old infants known to be at high risk for autism from controls of the same age.
“Electrical activity produced by the brain has a lot more information than we realized,” says William Bosl, PhD, a neuroinformatics researcher in the Children’s Informatics Program, and lead author in the study. “Computer algorithms can pick out patterns in those squiggly EEG lines that the eye can’t see.”
If proven successful, EEG testing for autism risk would be a welcome detection tool because it’s inexpensive, can be performed in a matter of minutes in a doctor’s office and, unlike MRI scans, does not require sedation.
Like many of its subjects, EEG testing for an increased risk of autism is still in its infancy. For a start, Bosl needs to follow the group of “at risk” infants into early childhood to see if they actually develop autism. But initial findings are promising and researchers remain optimistic that continued study will provide more data that will improve their ability to recognize signs of autism earlier than they can now. “With enough data, I’d like to follow each child’s whole trajectory from 6 to 24 months,” Bosl says. “The trend over time may be more important than a value at any particular age.”
For more information, watch this segment from Good Morning America, which commented on Bosl’s study: