In a new study, autism researchers used MRIs of six-month olds to show how brain regions are connected and synchronized and then correctly predicted 81 percent of high-risk babies who would later meet the criteria for autism at age two.
“There are no behavioral features to help us identify autism prior to the development of symptoms, which emerge during the second year of life,” said co-senior author John R. Pruett Jr., MD, Ph.D., associate professor of psychiatry at Washington University School of Medicine in St. Louis.
“But early intervention improves outcomes, so if in the future we could use MRI to identify children at ultra-high risk before they develop symptoms, we could begin treatments sooner.”
In a previous study published in the journal Nature, researchers at the University of North Carolina (UNC) used MRIs to determine differences in brain anatomy that could predict which babies would develop autism as toddlers.
In the new paper, published in Science Translational Medicine, researchers describe a second type of brain biomarker that could be used as part of a diagnostic toolkit to help identify children as early as possible, before autism symptoms even appear.
“The Nature paper focused on measuring anatomy at two time points (six and 12 months), but this new paper focused on how brain regions are synchronized with each other at one time point (six months) to predict at an even younger age which babies would develop autism as toddlers,” said senior author Joseph Piven, M.D., the Thomas E. Castelloe Distinguished Professor of Psychiatry at the UNC School of Medicine, and director of the Carolina Institute for Developmental Disabilities.
“The more we understand about the brain before symptoms appear, the better prepared we will be to help children and their families.”
For the study, sleeping infants were placed in an MRI machine and scanned for about 15 minutes to record neural activity across 230 different brain regions. Researchers were then able to observe the synchronized brain activity, crucial for cognition, memory, and behavior.
The researchers then focused on brain region connections related to the core features of autism: language skills, repetitive behaviors, and social behavior. For example, they determined which brain regions — synchronized at six months — were related to behaviors at age two.
This information helped Piven’s co-investigators create a computer program, called a machine learning classifier, that was able to sort through the differences in synchronization among key brain regions. Once the computer learned these different patterns, the researchers applied the information to a separate set of infants.
This part of the study involved 59 high-risk infants. Each had an older sibling with autism, meaning that each baby had about a one-in-five chance of developing autism, as opposed to one in 68, which is the approximate risk for the general population. 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. Using only this information, the computer program correctly predicted 81 percent of babies who would later meet the criteria for autism at two years of age.
“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,” said Robert Emerson, Ph.D., a former UNC postdoctoral fellow and first author of the study.
“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.”