Clinical Decision Support (CDS) for Outpatient Radiology Imaging

Summary

The goal of the study is to determine whether clinical decision support (CDS) affects the number, type, or appropriateness of targeted high-cost radiology images (i.e. MR and CT) ordered. The CDS will be delivered in Epic through ACRSelect software, which is a leading decision support tool based on the American College of Radiology (ACR) Appropriateness Criteria (see http://www.acr.org/Quality-Safety/Appropriateness-Criteria), and presents the ACR appropriateness scores for each image on a scale of 1-9 with 1-3 labelled as 'usually not appropriate', 4-6 'May be appropriate', and 7-9 'usually appropriate'.

Conditions

• CT and MR Image Orders

Interventions

OTHER

Clinical Decision Support (CDS)

A best practices alert (BPA) pop-up screen providing CDS will appear at physician sign-off for all scans scored 1-3, and scans scored 4-6 for which an alternative scan scored 7-9 exists. This screen will show the appropriateness score of the original scan order, and will display any alternative scans that are scored 7-9 for the same indications and patient characteristics. It will also display a link to relevant ACR documentation relevant to the selected scan and indication. Any time the pop-up alert appears, a checkbox removing the selected scan from unsigned orders will be checked by default.

Sponsors & Collaborators

• Icahn School of Medicine at Mount Sinai

  collaborator OTHER

• Abdul Latif Jameel Poverty Action Lab

  lead OTHER

Principal Investigators

• Amy Finkelstein, PhD · Massachusetts Institute of Technology

• Madhu Mazumdar, Mazumdar · The Mount Sinai Health System

• Bruce Darrow, MD, PhD · The Mount Sinai Health System

• Joseph Kannry, MD · The Mount Sinai Health System

• David S Mendelson, MD FACR · The Mount Sinai Health System

• Joseph Doyle, PhD · Massachusetts Institute of Technology

• Jesse Shapiro, PhD · Massachusetts Institute of Technology

• Laura Feeney, MA · Massachusetts Institute of Technology

Study Design

Allocation

RANDOMIZED

Purpose

HEALTH_SERVICES_RESEARCH

Masking

NONE

Model

PARALLEL

Eligibility

Sex

ALL

Healthy Volunteers

Yes

Timeline & Regulatory

Start

2015-10-31

Primary Completion

2016-05-31

Completion

2016-05-31

Countries

• United States

Study Locations