AI-assisted evaluations can speed up the diagnosis of autism

AI-assisted evaluations can speed up the diagnosis of autism

Access to autism evaluations through specialized health care is notorious for long wait times throughout the United States. In Missouri, many families wait nearly a year for a diagnostic appointment. According to researchers at the University of Missouri School of Medicine, AI could be a solution to reduce waiting time.

Lead author Kristin Sohl and her team worked with Cognoa, Inc. to test their FDA-cleared medical device, CanvasDx, for primary care physicians in areas without autism care. It integrates AI algorithms with patient data and makes a prediction about a positive or negative autism diagnosis depending on the information provided. If it cannot make a clear prediction, it returns an “indeterminate” result.

Our mission is to increase access to best practices for autism care in rural and underserved communities. To explore CanvasDx as a potential best practices tool, we leveraged the ECHO Autism community, which trains primary care physicians across Missouri and beyond in autism care.”

Kristin Sohl, lead author

Children in rural Missouri often wait longer to access autism evaluations, and this provides families an opportunity to receive the care they need. According to the study, traveling to specialty centers meant an average distance of 97 miles. On-site care helped families save on gas and receive a diagnosis five to seven months earlier than if they had waited.

“Devices like CanvasDx, especially when used by clinicians with autism experience, can help speed diagnosis so children can more quickly access services that support them,” Sohl said. “It can also assist the clinician and streamline assessment processes.”

In the study, which used data from 80 children, the device gave clear results in 52% of patients, but did not produce false positive or negative diagnoses and never contradicted a doctor's diagnosis. Sohl says this highlights the need for physicians to be educated about the assessment, diagnosis and care of autism.

“Recognizing autism and beginning individualized support for a child with autism are critical to optimizing their outcomes,” Sohl said. "Autistic children and their families deserve high-quality, timely access to local care and expertise. Using AI-integrated devices like CanvasDx can accelerate diagnostic processes and add additional, objective data to help primary care physicians make diagnoses."

Kristin Sohl, MD, is a pediatrician at MU Health Care and professor of pediatrics at Mizzou School of Medicine. She is the founder and executive director of the ECHO Autism Program and the medical director of the Missouri Telehealth Network (MTN) and the Office of Continuing Education for Health Professionals.

Sources: