For the first time, the autism researchers used MRIs of six-month infants to illustrate the brain region connection and their synchronization. This can further be used to predict the risk of developing autism in these babies by age 2. An earlier UNC-lead study used the MRIs to identify the differences in brain anatomy and predict which babies would develop autism as toddlers, published in the journal Nature.

The second type of brain biomarker was identified to determine the risks of autism in children, even before the symptoms appear. This could be used by the researchers and potentially clinicians as the part of a diagnostic toolkit for early detection, published in Science Translational Medicine.

Senior author Joseph Piven, MD said that The Nature paper focused on measuring anatomy at two-time points (six and 12 months) and the new paper focused on studying brain regions synchronization at one-time point (six months) to detect autism in infants to avoid it in toddlers. "The more we understand about the brain before symptoms appear the better prepared we will be to help children and their families," Piven added.

In the study, the sleeping infants were placed in an MRI machine and scanned for about 15 minutes and viewed for neural activity across 230 different brain regions and analyzed for synchronization i.e., the coordinated activity of brain regions.

The researchers further focused on brain region connections related to the core features of autism: language skills, repetitive behaviours, and social behaviour. The brain regions synchronization at six months related to behaviours at age two was determined.

This part of the study included 59 babies who had the risk of developing autism and eleven of the 59 babies went on to develop autism. The machine learning classifier was able to separate findings into two main groups: MRI data from children who developed autism and MRI data from those who did not; 81% were predicted to have autism in future.

"When the classifier determined a child which 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 obtained at six months of age," said Robert Emerson. "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."

More exciting work is yet to come which would include all predictions in one research and in future it could be used as biological diagnostics for autism during infancy, Emerson reported.