Effect of a Computer-Based Decision Support Intervention on Autism Spectrum Disorder Screening in Pediatric Primary Care Clinics: A Cluster Randomized Clinical Trial

Abstract

Importance: Universal early screening for autism spectrum disorder (ASD) is recommended but not routinely performed.

Objective: To determine whether computer-automated screening and clinical decision support can improve ASD screening rates in pediatric primary care practices.

Design, setting, and participants: This cluster randomized clinical trial, conducted between November 16, 2010, and November 21, 2012, compared ASD screening rates among a random sample of 274 children aged 18 to 24 months in urban pediatric clinics of an inner-city county hospital system with or without an ASD screening module built into an existing decision support software system. Statistical analyses were conducted from February 6, 2017, to June 1, 2018.

Interventions: Four clinics were matched in pairs based on patient volume and race/ethnicity, then randomized within pairs. Decision support with the Child Health Improvement Through Computer Automation system (CHICA) was integrated with workflow and with the electronic health record in intervention clinics.

Main outcomes and measures: The main outcome was screening rates among children aged 18 to 24 months. Because the intervention was discontinued among children aged 18 months at the request of the participating clinics, only results for those aged 24 months were collected and analyzed. Rates of positive screening results, clinicians' response rates to screening results in the computer system, and new cases of ASD identified were also measured. Main results were controlled for race/ethnicity and intracluster correlation.

Results: Two clinics were randomized to receive the intervention, and 2 served as controls. Records from 274 children (101 girls, 162 boys, and 11 missing information on sex; age range, 23-30 months) were reviewed (138 in the intervention clinics and 136 in the control clinics). Of 263 children, 242 (92.0%) were enrolled in Medicaid, 138 (52.5%) were African American, and 96 (36.5%) were Hispanic. Screening rates in the intervention clinics increased from 0% (95% CI, 0%-5.5%) at baseline to 68.4% (13 of 19) (95% CI, 43.4%-87.4%) in 6 months and to 100% (18 of 18) (95% CI, 81.5%-100%) in 24 months. Control clinics had no significant increase in screening rates (baseline, 7 of 64 children [10.9%]; 6-24 months after the intervention, 11 of 72 children [15.3%]; P = .46). Screening results were positive for 265 of 980 children (27.0%) screened by CHICA during the study period. Among the 265 patients with positive screening results, physicians indicated any response in CHICA in 151 (57.0%). Two children in the intervention group received a new diagnosis of ASD within the time frame of the study.

Conclusions and relevance: The findings suggest that computer automation, when integrated with clinical workflow and the electronic health record, increases screening of children for ASD, but follow-up by physicians is still flawed. Automation of the subsequent workup is still needed.

Trial registration: ClinicalTrials.gov identifier: NCT01612897.

Conflict of interest statement

Conflict of Interest Disclosures: Dr Downs reported being a cocreator of the Child Health Improvement Through Computer Automation (CHICA) system; being the founder and CEO of Digital Health Solutions, a company created to license the CHICA software (this study was completed prior to the formation of the company); and receiving grants from the Agency for Healthcare Research and Quality during the conduct of the study. Dr Saha reported receiving grants from the National Institutes of Health during the conduct of the study. Dr Carroll reported being a cocreator of the CHICA system; and receiving grants from the Agency for Healthcare Research and Quality during the conduct of the study. No other disclosures were reported.

Figures

Figure 1.. CONSORT Diagram for Cluster Randomized Trial Showing Randomization Allocation, Follow-up, and Analysis

Figure 2.. Run Chart Showing the Rates of Autism Spectrum Disorder Screening in Eligible Children During the Study Period

The screening rate at each time point for each group was estimated using the binomial distribution, and the 95% CIs (error bars) were from Clopper-Pearson (exact)–type intervals.

Figure 3.. Physician Responses to Alerts Indicating Child Had a Concerning Modified Checklist for Autism in Toddlers Result

Total percentages exceed 100% because physicians could check more than 1 response per child. ASD indicates autism spectrum disorder; and CHICA, Child Health Improvement Through Computer Automation system.