Fifteen of the babies were diagnosed with ASD by their second birthday.
Researchers from the University of Washington were part of a North American effort led by the University of North Carolina to use MRI to measure the brains of "low-risk" infants, with no family history of autism, and "high-risk" infants who had at least one autistic older sibling.
Researchers found that, among infants with an older ASD sibling, the brain differences at 6 and 12 months of age successfully identified 80 percent of those infants who would be clinically diagnosed with autism at 24 months of age.
Despite the limitations of the new study, Pletcher marvels at the findings.
Hazlett and her colleagues discovered an overgrowth of cortical surface area in infants later diagnosed with autism, compared with the typically developing infants.
Most of the time, it takes a few years for parents and doctors to notice the behavior changes in a child 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.
Right now the earliest a child can receive a reliable diagnosis of autism is generally thought to be age 2, at which point certain hallmark behaviors and communication problems have emerged, like an inability to string several words together or avoiding eye contact. "So, detecting autism before it really appears".
Certain rare mutations are linked to ASD, but the vast majority of cases can not be pinned to a single or even a handful of genetic risk factors. But Piven and colleague Heather Cody Hazlett, a psychologist at UNC-Chapel Hill, say it had not been clear when overgrowth occurred.
Sonos raising their United Kingdom prices as of February 23
Sonos is jacking up prices on a slew of its high-ticket speakers, and says the UK's Brexit-linked currency woes are to blame. Apple has already added as much as £300 to the cost of an iMac, and a wallet-busting £500 to the top of the line Mac Pro.
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.
For this study, researchers from around the country conducted MRI scans of infants at six, 12, and 24 months of age.
Babies who are most at risk of developing autism as toddlers have been identified from brain scans in the first year of life.
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.
A study published today in the journal Nature is the first to show that it is possible to predict within the first year of life, whether some infants will go on to develop autism.
Coloured regions indicate areas of the cortex that grew significantly faster in infants who were later diagnosed with autism. Though it is about the size of a pizza, it has been crumpled to fit inside your skull, and the result is the brain's most distinctive feature: the many folds and wrinkles.
The researchers used magnetic resonance imaging (MRI) to scan the brains of 148 infants, 106 of whom have an older sibling with autism. The algorithm correctly predicted 30 out of the 37 autism diagnoses (81%), while producing false-positives in 4 out of the 142 infants who were not later diagnosed. Each was at a higher risk for the disorder.
To find enough children to make their study useful, the research team followed more than 500 infants, scanning many of them in the middle of the night so they would be in a deep sleep. "They have been willing to travel long distances to our research site and then stay up until late at night so we can collect brain imaging data on their sleeping children". "The key thing is going to be replicating this". But the method might benefit at-risk populations, such as the younger siblings of those diagnosed with autism. Also participating was Jason Wolff, a U assistant professor of educational psychology, who said the study "offers the unprecedented possibility of predicting whether or not a child will develop autism based on neurobiological data".