Though screen time is typically a no-no for toddlers, a new smartphone app supported by the National Institutes of Health could actually have a positive impact on childhood brain development.
The app, which is still in the prototype phase, was shown in an NIH-funded study to be able to accurately distinguish between toddlers with and without autism by analyzing their eye movements while viewing social stimuli.
The study, published in JAMA Pediatrics, was funded by the NIH’s National Institute of Child Health and Human Development and National Institute of Mental Health.
Past research has found that individuals with autism spectrum disorder are less responsive to social signals. Visual eye tracking is one way to monitor those responses, but much of the required equipment is expensive and must be used by trained lab personnel.
The NIH app uses a smartphone or tablet’s front-facing camera to record children’s eye movements as they watch videos of people smiling, making eye contact and having conversations. Toys like spinning tops and bubbles are also included in the videos to determine whether a child focuses more on humans and social stimuli or objects.
The recorded gaze patterns are then analyzed with computer vision and machine learning algorithms that have been trained to identify how well each child focuses on and tracks the social interactions.
Researchers had 993 toddlers between 16 and 38 months old use the app during normally scheduled primary care check-ups. Forty of those toddlers were later diagnosed with autism, and the study data showed that those children had been significantly less likely to focus on the social cues and visually track the conversations in the app’s videos.
With that proof of concept, the researchers will now pursue larger studies that include children as young as 6 months. They hope to confirm the ability of their app-based solution to offer an inexpensive way to screen for autism at an early age, when treatment is typically most effective.
“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,” Geraldine Dawson, co-senior author of the study and director of the Duke Center for Autism and Brain Development, said in a release. “We have additional steps to go, but this study suggests it might one day be possible.”
Though this study represents the first time a smartphone or tablet has been deployed to use visual tracking to screen for autism, the NIH’s app isn’t the only one in development for autism diagnosis.
Pediatric digital health company Cognoa has created an artificial intelligence-powered app that analyzes videos of children and input from their parents and healthcare providers to spot the signs of autism spectrum disorder. With the app recently proven successful in a clinical trial of 400 children aged 1 1/2 to 6 years old, Cognoa is now seeking FDA clearance for its use in autism diagnosis.