Nearly 3% of all children in the United States are diagnosed with autism, according to the Centers for Disease Control and Prevention. But a collaborative team of researchers at Indiana University and Purdue University are finding ways to make the correct diagnosis sooner.
The number of children requiring autism assessments exceeds the capacity of specialists trained to provide this service. Children and their families currently wait a year or more to access assessments. This is a problem because children miss opportunities for interventions at the optimal moment of impact.”
Rebecca McNally Keehn, PhD, assistant professor of pediatrics, IU School of Medicine
McNally Keehn is the senior author of a paper recently published in JAMA Network Open which describes the research team’s study of diagnosing autism using eye-tracking biomarkers in primary care clinics across Indiana. The team traveled to practices participating in the Indiana Early Autism Evaluation Hub system and conducted a blinded survey-level assessment of 146 children ages 14-48 months.
“Diagnostic biomarkers are characteristics that provide a distinct and objective indication of diagnosis. Eye-tracking biomarkers that measure social and nonsocial attention and brain function have been shown to differentiate young children diagnosed with autism from those with other neurodevelopmental disabilities ” McNally Keehn said. “However, despite huge investments in eye-tracking biomarker discovery, there has been a gap in the translation of eye-tracking biomarkers into clinical benefit.
To do the eye tracking, the children in the study sat in a high chair or on a caregiver’s lap and watched videos on a computer screen while the researchers recorded their eye movements and pupil size. When the primary care physician’s diagnosis and diagnostic certainty were combined with eye-tracking biomarker measurements, the model’s sensitivity was 91% and specificity was 87%, meaning they made a more accurate diagnosis of autism.
McNally Keehn said studies like these can help address delays in accessing autism assessments by better equipping primary care clinicians with a multi-method, diagnostic approach.
“This is a public health issue, and our approach has the potential to substantially improve access to timely, accurate diagnosis in local communities,” said McNally Keehn.
The team’s next step is to conduct a large-scale replication and validation study of its diagnostic model using artificial intelligence. Next, they hope to conduct a clinical trial studying the effectiveness of the diagnostic model in real-time primary care assessments.
Other study authors include IU’s Patrick Monahan, Brett Enneking, Tybytha Ryan and Nancy Swigonski, and Purdue’s Brandon Keehn.