Early detection for autism may soon be possible through a smartphone app that tracks eye movements to detect autism spectrum disorder (ASD) in children as young as two years old.

Affecting one in 68 children in America, ASD can be a devastating disease, especially if gone untreated. Kun Woo Cho, an undergraduate majoring in computer science and engineering at the University of Buffalo (UB), was lead on the study of the smartphone app along with Wenyao Xu, PhD, assistant professor in UB's Department of Computer Science and Engineering. The team hopes to develop the app as a fast and efficient way to diagnose children with ASD.

"The beauty of the mobile app is that it can be used by parents at home to assess the risk of whether a child may have ASD," said Xu. "This can allow families to seek therapy sooner, and improve the benefits of treatment. This technology fills the gap between someone suffering from autism to diagnosis and treatment.”

When developing the app, researchers noticed that the eye movements in pictures with multiple people were more pronounced between children with ASD and those without. For this reason, the application uses these social scene picture to track eye movements and differ between the focused pattern of ASD children and the scattered movements of children without ASD.

In a study of 32 children ages two to 10, half which had been diagnosed with ASD, the application was found to be 94 percent accurate in diagnosing children accordingly. The application was able to finish the diagnoses process in about 54 seconds, making the platform accurate and quick as well as portable.

"Right now it is a prototype. We have to consider if other neurological conditions are included, like ADD, how that will affect the outcome," Cho said. The team hopes to continue to test and develop the application on children.