Thompson Center experts find Autism screening tool effective

When a family, doctor or teacher suspects a child has autism, they look to diagnostic experts to determine the diagnosis.

However, waiting for a diagnostic appointment can be agonizing – and long. Across the U.S., the average wait time for a diagnostic appointment for autism is 13 months. One solution for speeding up the process of diagnosing children with autism accurately is the use of highly effective screening tools. These tools, if effective, can identify children who are most likely to have an autism diagnosis onto shorter diagnostic waitlists, while those identified as having a lower risk of autism can be funneled into different clinics for more appropriate services, such as for learning disabilities or other disorders.

Now, experts at the Thompson Center for Autism & Neurodevelopmental Disorders have researched the effectiveness of one such autism screening tool, called Cognoa, and found that it is effective in

identifying children who are at higher risk for having autism.

In a study published in Autism Research, Dr. Stephen Kanne, executive director of the Thompson Center and an internationally recognized expert in autism diagnosis, found that the Cognoa tool maintains an equal level of sensitivity, or ability to detect a risk for autism, as other respected screening tools. However, he also found that Cognoa also has a much higher level of specificity than other screening tools. This means that the tool is better at identifying those children who do not have autism.

“The combination of Cognoa’s ability to accurately identify high autism risk while doing a better job of not falsely identifying children who are not at risk makes it a valuable tool,” Kanne said. “Being able to more accurately pick out those who truly do have a higher risk for autism makes Cognoa a valuable tool for parents and teachers who don’t necessarily have diagnostic expertise.”

Cognoa is a smartphone app which allows parents to upload videos of their children responding to predetermined prompts, as well as completing a questionnaire.

The app sends the uploaded videos to a group of technicians trained to look for behaviors and symptoms of autism and assign each a numerical code. This data is combined with the parent’s responses to the questionnaire, producing the child’s score. The higher score the score, the higher the risk the child has for autism.

For the study, Kanne tested Cognoa’s ability to accurately screen for children with a high-risk of autism through a complex machine-learning algorithm, which produces a score indicating the likelihood that the child has autism.

After first having completed the Cognoa screening process, a group of children ages 18 months to 6 years who were on the Thompson Center’s autism diagnostic clinic waitlist participated in the study during a weeklong “blitz” of diagnostic appointments.

With clinicians unaware of the Cognoa score from the screening, all 225 children were then given the ADOS-2, which is the gold-standard autism diagnostic test, by diagnostic experts.

The results of the study were promising: Cognoa accurately identified children with a risk for autism 71 percent of the time.

“I believe the app’s use of video as well as questionnaires is what allows it to be so specific,” Kanne said. “Putting tools such as this one in the hands of parents not only can speed up the time it takes to diagnose children and get them the services they need, but also it empowers families to be a part of the solution themselves.”