New eye-tracking tool may help diagnose autism much earlier in toddlers

A new tool that tracks toddlers’ eye movements as they watch a video of children playing together could help clinicians diagnose autism in children as young as 16 months, according to researchers.

Families currently face years-long waits for an autism diagnosis. This new device — developed by researchers at the Marcus Autism Center, a subsidiary of Children’s Healthcare of Atlanta — would enable critical earlier interventional therapies and support services by speeding up a diagnosis.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder caused by brain differences. People with autism may behave, interact, and learn in ways that are different from other people. They may have trouble with social interactions and with interpreting and using nonverbal and verbal communication. There is no cure for autism but there are many therapies that can reduce symptoms and improve quality of life.

Autism affects 1 in 36 children, meaning that each year, in the U.S. alone, more than 90,000 children are born with autism.

During the early years of a child’s life, the brain is still developing — which makes early intervention key to a child’s development and functioning.

Two new studies published Tuesday in JAMA and JAMA Network Open suggest that eye-tracking technology could help clinicians identify autism in children at a younger age with a high degree of accuracy.

Currently, the average age of diagnosis for a child with autism is a little under 4.5 years, according to the Centers for Disease Control and Prevention. Only 1 in 5 children in the U.S. is diagnosed before they turn 3 years of age. Use of the eye-tracking tool could mean a diagnosis in a child as young as 16 months and, with more testingof the technology, possibly as young as 9 months of age.

“We can help individuals with autism at any stage of their lives. But because of the brain plasticity early on, this is the window of opportunity when we have to have the greatest impact on their lives,” said Ami Klin, director of the Marcus Autism Center and one of the developers of this diagnostic technology. He is also a co-author of both studies.

“If we wait until later, what we are treating really are the results of autism and the results of autism are significant,” he said. “They can be intellectual disabilities, language disabilities, and severe behavior challenges.”

Here’s how the tool works: A child being evaluated simply watches a video on a portable tablet showing children playing in a daycare. They watch toddlers in different play settings: a kitchen, a theater, and an inflatable boat. The toddlers being watched show a range of emotions, sometimes smiling and laughing and sometimes looking concerned or crying. All the while, the tool monitors the child’s eye movements at a rate of 120 times a second.

While earlier research focused on simplified measures of attention to eyes versus objects, this sophisticated tool measures not just looking at the eyes but at whose eyes, when, for how long, and what part of the face at each moment. Children with autism often miss social interaction and look instead at toys or brightly colored or high-contrast objects in the background. Children typically watch between eight and 12 minutes of video.

The results can be available in 30 minutes.

The device, EarliPoint Evaluation, received Food and Drug Administration (FDA) clearance in July to be used as a diagnostic tool for specialists evauating children between the ages of 16 and 30 months . Researchers say they are working on developing this method to diagnose children as young as 9 months.

Results of clinical studies are published simultaneously in the Journal of the American Medical Association (JAMA) and in JAMA Network Open. The research published in JAMA Network Open describes the initial testing of the device on 1,089 children whose average age was 22 months. The JAMA paper reported on a trial performed at six of the country’s leading autism centers, including the Marcus Autism Center. During that trial, 499 children ages 16 to 30 months were first tested with the device and then evaluated by specialists.

Overall, the data shows the technology could accurately diagnose autism in about 84% of the subjects. That is comparable to expert clinicians trained to diagnose autism, according to researchers.

Warren Jones, director of research at the Marcus Autism Center, said the tool he helped Klin develop can also diagnose a range of autism severity. He emphasized the tool is not meant to replace expert clinicians. The goal of the eye-tracking technology is to provide clinicians with an objective tool that can be used to evaluate children within a matter of minutes.

Since there are no blood tests or imaging tests for diagnosing autism, the process has involved a battery of observations and listening to parents. Currently, autism is diagnosed by a highly trained expert over multiple hours of testing, and there is a shortage of these experts. General pediatricians can screen for autism but they often don’t have the time to do a full evaluation and will often refer families to specialists such as a developmental pediatrician for more tests.

The American Academy of Pediatrics recommends screening children for autism at 18 months and 24 months.

Since the FDA authorized the tool, it has been used for about 30 children at the Marcus Autism Center.

In early trials of the device, researchers often referred to it as “the Marcus Test,” acknowledging Atlanta philanthropist Bernie Marcus, founder of Marcus Autism Center. Researchers credit Marcus for making the breakthrough possible with his generous support of autism research.

Home Depot co-founder Bernie Marcus founded the Marcus Autism Center in 1991, donating about $120 million over the years to the Center, which is now a leading autism center in the U.S.

About the Author