A study conducted at Duke University shows a mobile app successfully identified the telltale characteristics of autism in children. The comprehensive technology has the potential to become an inexpensive and universal early autism screening tool.
Researchers designed the app to strategically assess the eye gaze patterns of children while they watch short movies on a smartphone or tablet. They applied computer vision and machine learning to the clips to identify whether the child was looking more often at the objects in the video, or the human. Eye-tracking has been used previously to assess gaze patterns in people with autism, but it requires special equipment and expert analysis. The intuitive app uses the front-facing camera of any smartphone or tablet to record the child’s behavior in less than 10 minutes, making it readily accessible to parents and pediatricians alike.
"We hope 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," said Geraldine Dawson, director of the Duke Center for Autism and Brain Development, and co-senior author of the study published in JAMA Pediatrics. "We have additional steps to go, but this study suggests it might one day be possible."
Dawson says that ongoing validation studies are underway. Further studies with infants as young as 6 months are investigating whether the digital app assessment could identify differences in children diagnosed later with autism and neurodevelopmental disorders during the first year of life.
Photo Credit: Duke University