An estimated one in 68 children globally are affected with ASD - a wide-ranging group of neurodevelopmental disorders that often cause ongoing problems with communication, repetitive behaviors, and other symptoms that impair an individual's ability to function socially.

Early detection and behavioral interventions could significantly improve quality of life for people with ASD, but the full range of behavioral symptoms typically don't appear until children are two years old or later.

Previous study used MRIs to determine differences in brain anatomy that predict which babies would develop autism as toddlers.

Published in Science Translational Medicine, this paper describes a second type of brain biomarker that researchers and potentially clinicians could use as part of a diagnostic toolkit to help identify children as early as possible, before autism symptoms even appear.

According to the results of a new study, a brain scan can detect functional changes in babies as young as six months of age that predicts later diagnosis with autism spectrum disorder (ASD). The scientists scanned the brains of 59 infants with high familial risk for ASD while they were sleeping using an imaging technique called functional connectivity magnetic resonance imaging (fcMRI), and collected data on 26,335 pairs of functional connections between 230 different brain regions. This synchrony reflects the coordinated activity of brain regions, which is crucial for cognition, memory, and behavior, and may be observed during sleep.

The researchers then focused on brain region connections related to the core features of autism: language skills, repetitive behaviors, and social behavior. For instance, the researchers determined which brain regions - synchronized at six months - were related to behaviors at age two. This helped the researchers create a machine learning classifier - a computer program - to sort through the differences in synchronization among those key brain regions. Once the computer learned these different patterns, the researchers applied the machine learning classifier to a separate set of infants.

Of the 59 infants, 11 went on to be diagnosed with ASD at 24 months of age, which enabled the researchers to apply machine-learning algorithms to parse out specific brain patterns that correctly predicted nine of the 11 diagnoses without any false positives.

The first author of the study, said, "When the classifier determined a child had autism, it was always right. But it missed two children. They developed autism but the computer program did not predict it correctly, according to the data we obtained at six months of age."

First author added, "No one has done this kind of study in six-month olds before, and so it needs to be replicated. We hope to conduct a larger study soon with different study participants."

Although future work is needed to determine if the signature applies to infants without high genetic risk, the authors say their findings may be first step towards much-needed early detection measures for ASD.

http://news.unchealthcare.org/news/2017/june/predicting-autism-study-links-infant-brain-connections-to-diagnoses-at-age-2

http://stm.sciencemag.org/content/9/393/eaag2882