Autism is hard to diagnose before a child is 2 years old. Some symptoms can surface between 12 and 18 months, but often it can be difficult to achieve a full diagnosis until a child is older.

While a toddler’s behavior can show early signs of autism, there has been no technology to diagnose the disorder.

Until now.

Scientists at the University of Buffalo have created an app that can detect if your child has autism in less than 54 seconds.

The smartphone app has a 94% accuracy rate by tracking a child’s eye movement while they look at social scenes in a place they feel safe and comfortable – like at home.

The app is based on a study conducted by a team of researchers and Kun Woo Cho, an undergraduate student and the principal author of the study, monitored 32 children aged from 2 to 10. Half of the children had been previously diagnosed with autism based on the DSM-5 criteria and the app confirmed these results.

“The study found that photos of social scenes evoke the most dramatic differences in eye movement between children with and without ASD,” the study said. “The eye-tracking patterns of children with ASD looking at the photos are scattered, versus a more focused pattern of children without ASD.”

At this stage the app “is a prototype. We have to consider if other neurological conditions are included, like ADD, how that will affect the outcome,” Cho says.

Autism spectrum disorder affects one to two people per 1000 worldwide. There has been a strong push for a mechanism that can detect autism symptoms like this app. Early detection means parents are able to help their children get earlier treatment in life.