PDF version

Clinical Decision Support for Radiology Imaging in the United States

Location: Wisconsin and Illinois, USA
Sample: Approximately 3,500 providers affiliated with Aurora Health Care
2016 to 2017
Research Initiative: Health Care Delivery Initiative
Target Group: 
Health care providers
AEA RCT Registration Number: 

There is widespread concern that inappropriate medical imaging unnecessarily increases health care costs and exposes patients to avoidable radiation. In response, clinical decision support systems have been designed to notify providers when they have ordered a diagnostic scan that is inconsistent with current professional guidelines. Researchers are studying the impact of a clinical decision support system on the ordering of high-cost scans.

Policy Issue 

In 2012, Medicare spent US$10 billion on high-cost diagnostic scans, such as magnetic resonance imaging (MRI) and computed tomography (CT) scans, but research suggests that up to 30 percent of diagnostic imaging is unnecessary. These scans may also expose patients to potentially harmful radiation. With health care spending accounting for almost one-fifth of the U.S. economy and an even larger share of public sector budgets, policymakers are interested in reducing spending on health care that provides minimal value to patients. Reflecting concerns about inappropriate scanning, beginning in early 2018, Medicare will no longer reimburse providers for high-cost scans unless they are ordered using a qualifying clinical decision support system – an automated tool that provides guidance on the appropriateness of a scan. To date, there has been no randomized evaluation of the impact of clinical decision support systems for imaging.

Context of the Evaluation 

Aurora Health Care is a large, private, not-for-profit integrated health care provider serving communities in eastern Wisconsin and northern Illinois. Aurora encompasses 15 hospitals and more than 150 clinics in the region, and cares for more than 1.2 million unique patients. Aurora Health Care utilizes an industry-standard electronic medical record software that includes a radiology information and order entry system.

CT scan. Photo: Shutterstock.com

Details of the Intervention 

Researchers are conducting a randomized evaluation to study the impact of clinical decision support systems on the ordering of certain high-cost medical imaging scans. Approximately 3,500 Aurora providers with imaging order permissions were selected to participate in the study. Researchers randomly assigned about half of these providers to receive the clinical decision support intervention, with the other half serving as a control group. After a period where the clinical decision support system ran “in the background” to provide baseline measures of imaging-order behavior, the system was turned on for providers in the treatment group on December 15, 2016.

The clinical decision support system is integrated directly into Aurora’s electronic medical record and operates when a provider orders high-cost imaging, such as a CT scan or MRI. Based on the health condition that the provider enters as the reason for the scan and on characteristics of the patient, the system uses computerized guidelines developed by the American College of Radiology to determine the appropriateness of the scan. A pop-up window appears at physician sign-off if:   

(i) the scan is rated “usually not appropriate,” or
(ii) the scan is rated “may be appropriate,” or
(iii) the scan is rated “usually appropriate” and there is another higher-rated scan available.

The pop-up window provides the appropriateness rating of the selected scan, more appropriate scan options, and a link to the relevant medical documentation. The provider can choose to either cancel the initial order, order a substitute scan, or proceed with the initially selected scan. Prior to the introduction of the clinical decision support system, researchers estimated that approximately one-quarter of orders would trigger an alert.

Researchers will measure scan ordering through administrative data recorded by Aurora’s electronic medical records system and by the provider of the clinical decision support system. Researchers also hope to study the impact of the intervention on patients’ subsequent medical care through other administrative data sources.

Results and Policy Lessons 

Project ongoing; results forthcoming.