Ultimately, this algorithm was pretty good at predicting from the six- and twelve-month brain scans of the same group of children if the child would be diagnosed with autism.
Over the last 12 years, more than 100 children were scanned at 6, 12 and 24 months old.
The scientists used MRI imaging on 106 high-risk infants (who had autistic older siblings) and 42 low-risk infants.
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.
On average, children aren't diagnosed with autism until they are four years old - once their brain has begun to expand, and once they begin behaving differently than neurotypical children - though some are diagnosed as early as their second birthday, Pletcher noted. Researchers say the findings from the study could help lead to early detection of autism in children with older siblings with autism well before a diagnosis is typically made.
The project included hundreds of children from across the U.S. and was led by researchers at the Carolina Institute for Developmental Disabilities (CIDD) at the University of North Carolina.
About 1 out of every 68 children in the United States has some form autism, according to the Centers for Disease Control and Prevention.
American Eagle jet hits deer on take- off, returns to airport
An American Airlines spokeswoman said in the statement that the aircraft was leaking fuel as a result of the incident. The passengers deplaned on the runway and were taken back to the terminal while fire trucks hosed the plane down.
But the diagnostic breakthrough addresses a key problem that has confounded efforts to effectively screen for autism as quickly as possible: Babies typically don't show clear outward signs of the disorder until almost the end of their second year of life. They found that the babies who developed autism experienced much more rapid growth of the brain's surface area from six to 12 months than babies who did not show evidence of autism at 24 months of age.
MRIs are very expensive, and it's hard to convince a 12 month old child to lay still long enough to get a good brain image.
"What we found was that cortical thickness didn't differ between the groups (of infants), but surface area increased at a higher rate than normal between 6 and 12 months of age" in the infants later diagnosed with autism, Piven said, referring to this as "hyper-expansion of cortical surface area". "The earlier an intervention is implemented, the better the outcome for kids with autism".
The researchers cautioned in their report that more research is needed, but that the results suggest machine learning could help doctors identify the disorder early, and perhaps develop therapies or treatments that could improve the well-being of patients, or, perhaps one day, even stop the progression of the disorder.
The findings could point to opportunities for new treatments and the potential to intervene before brain differences progress substantially, researchers said.
Other clinical sites included the University of Washington, Washington University in St. Louis, and The Children's Hospital of Philadelphia. The subsequent overgrowth was then linked to the emergence of autistic social deficits in the child's toddler years. "But if we did, parents of high-risk infants wouldn't need to wait for a diagnosis of ASD at 2, 3 or even 4 years and researchers could start developing interventions to prevent these children from falling behind in social and communication skills". Yet, for infants who have an autistic sibling, the risk of developing the disorder may be as high as one in five. "Now we have very promising leads that suggest this may in fact be possible".
The team also performed behavioral evaluations on the children at 24 months, when they were old enough to begin to exhibit the hallmark behaviors of autism, such as lack of social interest, delayed language, and repetitive body movements. Other key collaborators are McGill University, the University of Alberta, the College of Charleston, and New York University.