In this post, Brandon Keehn, an associate professor in the College of Health and Human Sciences and a member of the Purdue Institute to Integrative Neuroscience, discusses his recently published research “Eye-Tracking Biomarkers and Autism Diagnosis in Primary Care” which appears in JAMA Network with the support of the NIH and the Riley Children’s Foundation.
What did you want to know?
In this research we wanted to understand whether a battery of eye-tracking measures accurately identify young children with autism, and whether integrating biomarkers with primary care practitioner (PCP) diagnosis provide a method for improving diagnostic accuracy.
What did you achieve?
Diagnostic biomarkers are characteristics that provide discrete 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. However, despite enormous investment in eye-tracking biomarker discovery, there has been a gap in the translation of eye-tracking biomarkers into clinical benefit. In this Journal of American Medical Association (JAMA) Network publication our team showed that integrating eye-tracking metrics with primary care clinician diagnosis and diagnostic certainty improved autism diagnostic accuracy. Primary care clinicians across Indiana’s Early Autism Evaluation Hub system referred children they evaluated for autism. Our research team traveled to the primary care practices to conduct a blinded research-grade evaluation, including eye-tracking biomarkers. For eye tracking, the child sits in a high chair or their parents lap and views videos on a computer screen while their eye movements and pupil size are recorded. When a machine learning approach is used to combine primary care clinician diagnosis and diagnostic certainty and eye-tracking biomarker metrics, the sensitivity and specificity of this integrated model was 91% and 87%, respectively.
What is the impact of this research?
According to the Centers for Disease Control and Prevention, nearly 3% of children in the United States are diagnosed with autism. The number of children needing autism evaluations exceeds the capacity of specialists trained to provide this service. Children and their families are currently waiting a year or more to access evaluations. This is a problem because children miss opportunities for interventions at the time of optimal impact. Finding effective and scalable solutions to address the autism bottleneck is a public health imperative. Our study findings suggest that equipping primary care clinicians with a multi-method diagnostic approach, including use of eye-tracking biomarkers, has the potential to substantially improve access to timely, accurate diagnosis in local communities.