A quarterly publication of the Autism Research Institute

The Autism Research Review International is quarterly publication of the Autism Research Institute

Fall, 2016 | Number 4, Volume 30

Smartphone app identifies autism with high accuracy

Recently (see ARRI 2016, No. 3), researchers at the University of Rochester announced that they could diagnose autism spectrum disorders (ASD) with up to 93% accuracy using iPad games that measured children’s movement patterns. Now a separate team of researchers at the University at Buffalo are reporting that they have developed a smartphone app that can diagnose ASD with equal accuracy. 

Kun Woo Cho and colleagues created an app that tracks the eye movements of children as they look at pictures of social scenes. The researchers tested their app on 32 children ranging from two to 10 years of age, half of whom had an autism diagnosis. While the app is only a prototype, the researchers say that it detected ASD in under one minute with an accuracy of 93.96%. 

The researchers say that the eye-tracking patterns of children with ASD were more scattered and less focused than those of controls when they viewed the social scenes. Cho says, “We speculate that it is due to their lack of ability to interpret and understand the relationship depicted in the social scene.” 

Study coauthor Wenyao Xu says, “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. This can allow families to seek therapy sooner, and improve the benefits of treatment.”


Cho and colleagues presented their findings at the IEEE Wireless Health Conference in October 2016. Address: wenyaoxu@ buffalo.edu.