Researchers develop technique for early, accurate detection of autism in children

A new study sheds light on a recent accomplishment by researchers who have developed a technique to detect autism spectrum disorder (ASD) in children quickly and more accurately.

The findings were published in the journal 'Computers in Biology and Medicine.' "Many people are suffering from autism, and we need early diagnosis especially in children," said Mehrshad Sadria, a master's student in Waterloo's Department of Applied Mathematics.

"Our method allows for the diagnosis to be made more easily and with less possibility of mistakes. The new technique can be used in all ASD diagnosis, but we believe it's particularly effective for children," Sadria added. Researchers evaluated 17 children with ASD and 23 neuro-typical children. The mean chronological ages of the ASD and neuro-typical groups were 5.5 and 4.8, respectively.

Each participant was shown 44 photographs of faces on a 19-inch screen, integrated into an eye-tracking system. The infrared device interpreted and identified the locations on the stimuli at which each child was looking via emission and reflection of waves from the iris. The images were separated into seven key areas of interest (AOIs) in which participants focussed their gaze- under the right eye, right eye, under the left eye, left eye, nose, mouth and other parts of the screen.

The researchers wanted to know how much time the participants spent looking at each AOI, and also how they moved their eyes and scanned the faces. To gather information, researchers used four different concepts from network analysis to evaluate the varying degree of importance the children placed on the seven AOIs when exploring the facial features.

The first concept determined the number of other AOIs that the participant directly moves their eyes to and from a particular AOI. The second concept looked at how often a particular AOI is involved when the participant moves their eyes between two other AOIs as quickly as possible.

The third concept is related to how quickly one can move their eyes from a particular AOI to other AOIs. The fourth concept measured the importance of an AOI, in the context of eye movement and face scanning, by the number of important AOIs that it shares direct transitions with.

"It is much easier for children 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, professor of Applied Mathematics, Pharmacy and Biology at Waterloo. "Also, the challenge many psychologists face is that sometimes behaviours deteriorate over time, so the child might not display signs of autism, but then a few years later, something starts showing up. Our technique is about how a child looks at everything," Layton added.