Related Experiment Video
Updated: Aug 6, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Evaluating the implementation of a clinical decision support system for substance use disorder screening in maternal
Melanie Besculides1, Nicklas Klepser1, Roland C Merchant2
1Institute for Healthcare Delivery Science, Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, 1 Gustave L Levy Pl, New York, NY 10029, United States.
Purpose:
Screening for substance use disorders (SUDs) during pregnancy is essential but is hindered by barriers, including limited leadership engagement, financial sustainability concerns, and insufficient infrastructure. This study evaluated the implementation in a maternal health clinic of an electronic health record (EHR)-integrated Screening, Brief Intervention, and Referral to Treatment clinical decision support system (SBIRT-CDSS) that incorporated the 5Ps screening tool. We aimed to assess social workers' perceptions of usability and integration, and to compare screening rates, missed referrals, and revenue generation of the SBIRT-CDSS to SBIRT without CDSS.
Methods:
Our mixed-methods assessments encompassed four phases: (1) pre-implementation acceptability assessment using Technology Acceptance Model (TAM) surveys and qualitative input from social workers; (2) cognitive walkthroughs with mock patients; (3) systems modeling comparing SBIRT-CDSS to SBIRT without CDSS; (4a) post-implementation feedback from social workers at 1 month and (4b) quantitative analysis of SBIRT-CDSS usage, CPT billing, and screen-positive rates after 18 months of deployment.
Results:
Social workers rated SBIRT-CDSS as easy to use and useful. Systems modeling projected SBIRT-CDSS adoption would increase screening rates, referral rates, and revenue-depending upon extent of CDSS usage. Among 1967 patients with an initial prenatal visit during the 18-month post-implementation period, 1721 (87.5%) had SBIRT screenings documented at that encounter. Among screened patients, 1331 (77.3%) had CPT codes entered and 422 (24.5%) screened positive.
Conclusions:
SBIRT-CDSS implementation facilitated screening, billing code entry, and substance use identification. Social workers reported high usability and workflow integration. Utilization is expected to enhance referral rates and financial sustainability.
