December 26, 2019
1 min read

Computer-automated decision support improves early screening rates for ASD

You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact

Stephen M. Downs

The use of computer automation in a clinical setting increased screening rates of children for autism spectrum disorder, according to findings of a cluster-randomized clinical trial published in JAMA Network Open.

“We found that automating the autism screening process with a computer decision support system can dramatically increase the number of children screened at recommended ages,” Stephen M. Downs, MD, MS, research scientist at Regenstrief Institute in Indiana and the Jean and Jerry Bepko Professor of pediatrics at Indiana University School of Medicine, told Healio Psychiatry. “I was surprised at the magnitude of the effect. Early screening essentially never happened without the Child Health Improvement Through Computer Automation (CHICA) system but happened almost universally with it.”

Downs and colleagues evaluated four clinics that use CHICA — a computer-based clinical decision support system that communicates with a patient’s underlying electronic health record — in the Eskenazi Health System in Indianapolis, Indiana. The researchers randomly assigned two clinics to use CHICA with ASD decision support, and two other clinics served as controls. They included children aged 3 years or younger who were seen in the study clinics within one month of their 18- or 24-month birthday.

A total of 274 children (101 female, 162 male and 11 without information on sex) ranging from 23 to 30 months old were evaluated. The researchers found that screening rates increased from 0% at baseline to 68.4% in 6 months and to 100% after 24 months. Control groups had no significant increase in screening rates.

Despite the increase in ASD screening, clinics and physicians were not effective in follow-up with patients with positive screening results. Among the 265 patients with a positive M-CHAT result, physicians responded to only 151 children (57%).

“I think that automating the referral process could improve the early identification of children with autism even more,” Downs said. “Getting children with autism identified, evaluated and enrolled in early intervention programs can profoundly improve outcomes and save money. –by Erin T. Welsh

Disclosure: Downs reports being a co-creator of the Child Health Improvement Through Computer Automation (CHICA) system, being founder and CEO of Digital Health Solutions and receiving grants from the Agency for Healthcare Research and Quality during the study. Please see the study for all other authors’ relevant financial disclosures.