Impact of a Commercially Available Clinical Decision Support Program on Provider Ordering Habits

Purpose: Clinical decision support (CDS) software designed around the ACR Appropriateness Criteria assists health care providers in choosing appropriate imaging studies at the time of order entry. The goal of this study was to determine the impact of commercially available CDS on the ordering habits of inpatient and emergency providers. Methods: In 2014, ACR Select was integrated into our electronic health record, though without displaying appropriateness scores in a “silent” mode for 6 months. Then, feedback regarding examination appropriateness was “turned on” at order entry for adult patients in the emergency and inpatient settings for 24 months. We retrospectively compared the appropriateness scores of imaging tests before and after displaying feedback at order entry and evaluated these data by modality and attending versus trainee status. Results: The commercially available CDS-generated scores for 34% and 20.4% of pre- and postintervention studies, respectively. After feedback, the relative frequency of low utility studies decreased to 5.4% from 11%, and the relative frequency of indicated studies increased to 82% from 64.5%. This was most pronounced in trainees for whom the percentage of low utility studies decreased from 10.8% (95% confidence interval [CI]: 10.0%, 11.7%) to 4.8% (95% CI: 4.4%, 5.2%) and the percentage of indicated studies increased from 65.6% (95% CI: 64.3%, 66.9%) to 83.7% (83.0%, 84.3%). Conclusions: After implementation of a commercially available decision support tool integrated into the electronic health record, there was a significant improvement in imaging study appropriateness scores, more pronounced in studies ordered by trainees.