Augmented Expertise
Machine learning could improve autism outcomes.
Photo: Adobe Stock
An interdisciplinary team of researchers is developing ways for non-expert clinicians to identify children at risk for autism spectrum disorder (ASD), which affects 1 in 54 children in the U.S.
Led by Gondy Leroy, professor in the Eller College of Management, the team combines expertise in information science, pediatric medicine and public health. The researchers are using machine learning to mark the electronic health records of children at high risk for autism based on observed behaviors that align with a medical diagnosis of ASD.
Early diagnosis and treatment drive the best long-term outcomes for children ultimately diagnosed with ASD, a condition that today is often identified late or missed entirely in childhood.
Tools from the research, funded by a $1.5 million health information technology grant from the National Institute of Mental Health, will encourage earlier referrals for expert evaluation and will be particularly valuable in smaller towns and rural areas, which are home to fewer physicians, especially those with specialized training for early detection of ASD.
Data Connects Us
The Data Connects Us series is published in partnership with the university's Office of Research, Innovation & Impact (RII) and the Institute for Computation & Data-Enabled Insight. RII content was written by Eric Van Meter and originally published in the RII Magazine in December 2023 based on reporting by Rosemary Brandt, Logan Burtch-Buus, Anna Christensen, Emily Dieckman, Mikayla Mace Kelley, Susan McGinley, Kimberly Nichols and Niranjana Rajalakshmi.
