Brain scans can detect autism in children long before they display symptoms, a new study says, giving hope for the development of early testing and intervention methods. 

MRI scans of of 148 children at six, 12 and 24 months allowed scientists to detect brain surface differences in children who were eventually diagnosed with autism. Researchers used artificial intelligence to analyze the brain scan results and were able to predict an autism diagnosis with 80 percent accuracy. The study, led by researchers from the University of North Carolina, was published Wednesday in Nature.

Currently, the earliest age doctors can diagnose autism in a child is at two years old. But researchers were able to identify brain differences in the cerebral cortex -- the part of the brain responsible for high-level functions -- in children less than a year old. 

"That allows us to consider intervening before the behaviors of autism appear," Dr. Joseph Piven, one of the study's authors, told the BBC. "I think there's wide consensus that that's likely to have more impact at a time when the brain is most malleable and before the symptoms have consolidated... So we find it very promising."

One out of every 68 children receives an autism diagnosis, the Scientific American said. That rate increases to as high as one in five for children with an older sibling with the disorder. Researchers were able to compile valid data on 104 children with older siblings on the autism spectrum, making the study's sample size too small to be definitive, the Scientific American reported. 

Scientists are using a variety of methods to try and devise a way to detect autism earlier, Wired notes. Duke University researchers have developed an app that analyzes children's reactions to videos in order to detect abnormal reactions, and a University of Buffalo team created another app that tracks eye movement to identify signs of autism in children.