This article is more than 5 years old. Information may no longer be current.
Neuroimaging technique accurately predicts autism in some infants
Functional connectivity MRI accurately predicted which 6-month-old infants at high familial risk for autism spectrum disorder would be clinically diagnosed with the disorder at 2 years of age, according to findings recently published in Science Translational Medicine.
CDC data indicate that one in 68 children was diagnosed with autism in 2012 — the last year for which such data are available — up from one in 150 children in 2002.
“Recent research using [functional connectivity MRI] has linked the functional organization of the human brain to individual cognitive profiles. These measures of brain functional connectivity are reliable ... [and have] provided predictions of brain maturation and diagnostic category at the single-subject level,” Robert W. Emerson, PhD, Carolina Institute for Developmental Disabilities, University of North Carolina, and colleagues wrote. “However, there have been no infant functional neuroimaging studies that have used these techniques to develop early diagnostic predictions in ASD.”
To gather more data, researchers used a computer-based technology called machine learning to scan 59 infants aged 6 months who had older siblings with autism, thus putting them at high risk for autism. As the infants slept naturally, the technology looked for differences that can separate the neuroimaging results into two groups, autism or non-autism, and predict future diagnoses.
Researchers found that 11 of the 59 infants were diagnosed with autism at 2 years of age, and one analysis predicted each infant's future diagnosis by using the other 58 infants' data to train the computer program. This method identified 82% of the infants later diagnosed with autism and it correctly determined all of the infants who did not develop autism. In another analysis that tested how well the results could apply to other cases, the computer program predicted diagnoses for groups of 10 infants, at an accuracy rate of 93%. Overall, the team found 974 functional connections in the brains of 6-month-olds that were associated with autism-related behaviors.
“This study represents an initial, but critical, first step toward developing the earliest diagnostic methods available, and may yield the clues necessary to build efficacious early interventions based on individual risk profiles,” Emerson and colleagues wrote. “If these findings could be generalized to more cost-effective and mobile neuroimaging technologies, it would greatly increase the accessibility of early screening.” – by Janel Miller
Disclosure: The researchers report no relevant financial disclosures.