A new digital application created at Duke University has been found to successfully detect a common characteristic of autism in young children, providing hope for the idea that developmental disorders could be detected by technological early screening tools.
Developed by a research team at the university, the app focused on assessing the eye gaze patterns of children while watching short strategically created movies using tablets and iPhones, later applying vision and machine learning in order to discover if the child observed the human figures or objects in the video more.
Geraldine Dawson, Ph.D., director of the Duke Center for Autism and Brain Development and a co-author of the study that will appear in the academic journal JAMA Pediatrics, noted that “We know that babies who have autism pay attention to the environment differently and are not paying as much attention to people.”
“We can track eye gaze patterns in toddlers to assess risk for autism. This is the first time that we’ve been able to provide this type of assessment using only a smart phone or tablet. This study served as a proof-of-concept, and we’re very encouraged.”
The development of the app began several years ago, and was done in coordination with lead author Zhuoqing Chang, Ph.D., postdoctoral associate in Duke’s Department of Electrical and Computer Engineering.
In one of the movies featured on the app, a woman is seen playing with a top on on side of the screen, which then proceeds to spin toward the other side of the screen. when shown to children, it was found that those without autism focused more on the woman, while autistic children focused more on the spinning top.
Another movie following the same format repeated the test using a man blowing bubbles. In order to complete an assessment, the child needed to watch the video for 10 minutes, allowing the front-facing camera to record the child's behavior.
“This was the technical achievement many years in the making,” Chang said. “It required our research team to design the movies in a specific way to elicit and measure the gaze patterns of attention using only a hand-held device.
“It’s amazing how far we’ve come to achieve this ability to assess eye gaze without specialized equipment, using a common device many have in their pocket,” Chang said.
The app was tested on 993 children aged 16 to 38 months, and is expected to be further tested on children as a young as six-months-old.
“We hope that this technology will eventually provide greater access to autism screening, which is an essential first step to intervention. Our long-term goal is to have a well-validated, easy-to-use app that providers and caregivers can download and use, either in a regular clinic or home setting,” Dawson said.
“We have additional steps to go, but this study suggests it might one day be possible,” she added.