Researchers at the University of Buffalo have created a smartphone app that can detect autism spectrum disorder (ASD) in children with a 94 per cent accuracy rating.
The app is able to track eye movement so as to distinguish between those with ASD and those without, based on their viewing of images on the smartphone screen.
“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,” says Wenyao Xu, study co-author. “This can allow families to seek therapy sooner and improve the benefits of treatment.” The new technology was recently presented at the Institute of Electrical and Electronics Engineers (IEEE) Wireless Health Conference in Bethesda, Maryland.
The study involved 32 children between the ages of two and ten, half of whom had previously been diagnosed with autism and half who did not have autism. Participants were asked to watch 54 seconds of images of social scenes on a smartphone, all the while the app marked their eye movements. Researchers found significant differences in the eye movements of the two groups of children, with the eye movements of the children with ASD appearing more scattered and less focused than those by the children without ASD, something that the researchers believe is connected to the two groups’ differing abilities to pick up on social cues.
“We speculate that it is due to their lack of ability to interpret and understand the relationship depicted in the social scene,” says Kun Woo Cho, an undergraduate majoring in computer science and engineering at U Buffalo, and principal author of the new study.
Altogether, the app identified the eye movements of those with ASD to an accuracy rating of 93.96 per cent. The researchers are continuing to refine their app but they believe that easy-to-use detection methods such as theirs could help families detect autism at early stages of development, something which has been shown to be highly beneficial for treatment.
“The brain continues to grow and develop after birth. The earlier the diagnosis, the better,” says Michelle Hartley-McAndrew, clinical assistant professor of pediatrics and neurology in the Jacobs School of Medicine and Biomedical Sciences and study co-author. “Then we can inform families and begin therapies that will improve symptoms and outcome.”
According to Autism Canada, while detection of ASD can sometimes occur at 18 months or younger, more obvious signs of ASD typically being to express between the ages of two and three. Currently, however, the average age of diagnosis in both Canada and the United States is 4.5 years of age.
Studies have shown that intensive behavioural intervention training taken up at an early age can have significant benefit to the child with ASD. Such training usually focuses on developing social, language and communication skills, motor skills and daily living skills.
Diagnosing for autism spectrum disorder is a complex undertaking, involving overall assessment of a child’s development and progress, his or her behaviour patterns as well as tests for hearing and vision. Yet, other approaches to screening are on the horizon.
In a new study published in the journal Cell Reports, researchers from McMaster University in Hamilton have isolated a gene whose mutation affects people with ASD, potentially paving the way for genetic screening for ASD.