Researchers develop a more accurate technique to detect ASD among children

A team of researchers from the University of Waterloo have created a new technique to diagnose autism spectrum disorder (ASD) in children. The new invention will help in identifying early and accurate signs of ASD.

According to experts children with ASD scan a person’s face in a different manner compared to neuro-typical children. The researchers thus based their study on the ASD gaze transitions from one person’s face to another. These findings were crucial in the diagnostic process of ASD through the new technique. Together with the manual methods, the technique could help doctors detect positive cases of ASD more accurately.

“Many people are suffering from autism, and we need early diagnosis especially in children,” commented Mehrshad Sadria, a master’s student in Waterloo’s Department of Applied Mathematics. “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. The new technique can be used in all ASD diagnosis, but we believe it’s particularly effective for children.”

In the developing process of the technique, 17 children with ASD were evaluated, along with 23 neuro-typical children. As per reports, the mean chronological age of the participants was 5.5 and 4.8 respectively.

In order to observe gaze transitions, participants were shown 44 faces, through the medium of photographs on a 19-inch screen. Furthermore, it was integrated into an eye-tracking system and thus the infrared device could interpret and identify locations on the stimuli, while the child was looking through an emission or reflection of wave from the iris.

Moreover, the images were distinguished into seven key areas of interest, also known as AOIs. Results confirmed that participants focused their gaze under the right eye, on the right eye, under the left eye, on the left eye, nose, mouth and on other parts of the screen.

For the study, experts also felt it was important to know how much time participants spent on looking at each AOI, in addition to the movement of their eyes and how they scanned the face photographs. In order to obtain satisfactory results through this medium, researchers used four concepts from the network analysis to examine the degree of importance every participant placed on the seven AOIs.

Current process of detecting ASD among children is through a questionnaire or through an expert evaluation from a psychologist. The new technique developed by researchers at the University of Waterloo focuses not only on the behavior of the child, but also focuses on the mouth or eyes and in general centers on how a child looks at everything.

The research study was published in the journal Computers in Biology and Medicine.