Access to autism evaluations in the United States is often delayed, with families in Missouri sometimes waiting up to a year for diagnostic appointments. Researchers from the University of Missouri School of Medicine have explored how artificial intelligence (AI) might help reduce these wait times.
Kristin Sohl, lead author of the study, and her team collaborated with Cognoa, Inc. to assess CanvasDx, an FDA-approved medical device designed for use by primary care clinicians in areas lacking autism care specialists. The device uses AI algorithms to analyze patient data and predict whether a child is likely to have autism or not. If the information provided is insufficient for a clear decision, it returns an 'indeterminate' result.
The study found that children living in rural parts of Missouri typically had to travel an average of 97 miles to reach specialty care centers for autism evaluations. By enabling local diagnoses through devices like CanvasDx, families were able to save on travel costs and receive diagnoses five to seven months sooner than if they had waited for specialty appointments.
"Devices like CanvasDx, especially when used by autism-experienced clinicians, can help accelerate diagnosis, so children have faster access to services that support them," Sohl said. "It can also provide support for the clinician and streamline processes of the evaluation."
The research involved 80 children and showed that CanvasDx provided determinate results for 52% of patients without producing any false positives or negatives. The device's assessments did not contradict clinicians’ diagnoses at any point. Sohl noted this outcome points to the importance of further education for clinicians on autism evaluation and diagnosis.
"Identifying autism and starting individualized support for a child with autism are critical for optimizing their outcomes," Sohl said. "Autistic children and their families deserve high-quality and timely access to local care and expertise. Using AI-integrated devices like CanvasDx can expedite diagnostic processes and add additional, objective data to support primary care clinicians in making diagnoses."
Kristin Sohl is a pediatrician at MU Health Care as well as a professor at the Mizzou School of Medicine. She also leads several programs related to telehealth and continuing education in health professions.
