By Michelle Diament
February 15, 2017
For the first time, a new study suggests it’s possible to predict within the first year of life if a child will develop autism.
Researchers say they were able to identify with more than 90 percent accuracy which babies would go on to be diagnosed with the developmental disorder by age 2.
The findings published Wednesday could be a game changer, pointing to the possibility of identifying children on the spectrum at far younger ages and before behavioral symptoms become apparent, researchers said.
“The results of this study are a real breakthrough for early diagnosis of autism,” said Robert T. Schultz who directs the Center for Autism Research at the Children’s Hospital of Philadelphia and worked on the study published in the journal Nature.
“While we have known for some time that autism emerges in subtle, gradual ways over the first few years of life, this study offers the first firm evidence before a child’s first birthday predicting whether certain high-risk children are likely to be diagnosed with autism.”
Currently autism can reliably be diagnosed as early as age 2, but most kids aren’t flagged until after age 4, according to the U.S. Centers for Disease Control and Prevention.
Research suggests that autism intervention is most successful the earlier it begins, so scientists are eager to find reliable methods of spotting the disorder at younger ages.
The study looked at 106 infants considered to be at high risk for autism because they had an older sibling with the developmental disorder and 42 low-risk infants. Magnetic resonance imaging, or MRI, scans were conducted on each child at 6, 12 and 24 months of age.
In children who ultimately developed autism, growth of the brain’s surface area was significantly more rapid between ages 6 and 12 months as compared to other kids, the study found. What’s more, the overall size of affected children’s brains grew at a faster rate between ages 12 and 24 months.
Among babies at high risk, the brain differences between ages 6 and 12 months alone could predict whether a child would have autism with 80 percent accuracy, researchers said.
However, by considering other factors as well including additional brain measurements and the child’s sex, the researchers used a statistical approach known as machine learning to assess with near perfect accuracy who would develop autism.
“If we are able to replicate these results in further studies, these findings promise to change how we approach infant and toddler screening for autism, making it possible to identify infants who will later develop autism before the behavioral symptoms of autism become apparent,” Schultz said.
The findings could point to opportunities for new treatments and the potential to intervene before brain differences progress substantially, researchers said.
“We haven’t had a way to detect the biomarkers of autism before the condition sets in and symptoms develop,” said the study’s senior author, Joseph Piven of the Carolina Institute for Developmental Disabilities at the University of North Carolina. “Now we have very promising leads that suggest this may in fact be possible.”