Researchers at the University of Waterloo have developed a new technique to help doctors quickly and accurately detect autism spectrum disorder (ASD) in children.
Based on the findings of their study, the team of researchers was able to develop a technique that considers how a child with ASD transitions from looking at one part of a person’s face to another, and how they differ from children without ASD.
The use of this technique makes the diagnostic process of ASD less stressful for children, and if combined with existing manual methods, it could help doctors better avoid falsely diagnosing children with autism.
“The current approaches to determining if someone has autism are not really child-friendly. Our method allows for the diagnosis to be made more easily and with less possibility of mistakes,” said Mehrshad Sadria, a master’s student in Waterloo’s Department of Applied Mathematics.
In developing the new technique, the researchers evaluated 17 children with ASD at a mean age of 5.5, and 23 children without ASD at a mean age of 4.8. Each participant was shown 44 photographs of faces, while an eye-tracking system followed their eye movements. The system interpreted which areas of interest (AOIs) on the faces were being focused on by participants, such as under the right eye, the left eye, the nose, or the mouth. The researchers wanted to know how much time each participant spent looking at each AOI, and how participants moved their eyes when focusing on different AOIs. Currently, the most favoured method of assessing ASD involves a questionnaire or an evaluation from a psychologist.
“It is much easier for a child to just look at something, like the animated face of a dog, than to fill out a questionnaire or be evaluated by a psychologist,” said Anita Layton, a professor of Applied Mathematics, Pharmacy, and Biology at Waterloo.
“Our technique is not just about behavior or whether a child is focusing on the mouth or eyes. It’s about how a child looks at everything.”
The study, titled "Network Centrality Analysis of Eye-gaze Data in Autism Spectrum Disorder", was authored by Waterloo’s Faculty of Mathematics researchers Sadria, Layton, Shahid Behesthi, and graduate student Soroush Karimi in the Department of Physics. It was recently published in the journal Computers in Biology and Medicine.