• Politics
  • Diversity, equity and inclusion
  • Financial Decision Making
  • Telehealth
  • Patient Experience
  • Leadership
  • Point of Care Tools
  • Product Solutions
  • Management
  • Technology
  • Healthcare Transformation
  • Data + Technology
  • Safer Hospitals
  • Business
  • Providers in Practice
  • Mergers and Acquisitions
  • AI & Data Analytics
  • Cybersecurity
  • Interoperability & EHRs
  • Medical Devices
  • Pop Health Tech
  • Precision Medicine
  • Virtual Care
  • Health equity

Clinical Decision Support Software Steers Providers to Better, Not Cheaper, Imaging Options

Article

But a new study suggests the tool can help eliminate waste.

clinical decision support,cds imaging,diagnostic decision

Clinical decision support software that aids providers in making diagnostic imaging choices appears to result in more appropriate decisions, but that doesn’t necessarily result in lower costs.

Those are the findings of a study out earlier this year which sought to put CDS software to the test in a category of medicine that is both expensive and has the potential to be inappropriately used.

Corresponding author Joseph Doyle, Ph.D., a professor of management and applied economics at the Massachusetts Institute of Technology’s Sloan School of Management, noted in the paper that some estimates suggest 30% of diagnostic imaging in the U.S. is unnecessary. He told Inside Digital Health™ that new tools such as CDS software benefit from solid scientific evaluation of their effectiveness.

“I think studies like these, where we roll out new tools in systematic ways, so we can study their impacts in credible ways, are essential for trust and adoption,” he said.

Doyle and colleagues designed a study to test whether giving “best practice alerts” to providers at the point of decision-making might help stop them from ordering unnecessary tests. Researchers worked with Milwaukee-based Aurora Health Care to track 3,511 of the health network’s providers for a year to see whether the alerts affected the rates at which the clinicians ordered a targeted group of high-cost tests, including CT scans and MRIs.

Providers — including medical doctors, nurse practitioners, physician assistants and other professionals who had previously ordered at least one imaging study — were randomly assigned to receive best practice alerts. The control group continued ordering in the same fashion they previously had.

The alert system, integrated into the CDS tool ACR Select, is in alignment with a new Centers for Medicare and Medicaid Services mandate requiring CDS integration no later than Jan. 1, 2020.

Over the 12-month observation period, the study found providers in the control group ordered an average of 17 high-cost scans in the targeted group. Providers receiving the alerts, however, averaged 1.1 fewer targeted scans over the course of the year, a 6% reduction. Moreover, the study found no evidence of “alert fatigue,” a concern that providers might begin to ignore the alerts over time.

The findings come with a significant caveat, however. While the CDS alerts led to a significant reduction in high-costs tests targeted by the study, they had less of an effect in terms of the overall number of high-cost tests. That’s because the system is designed to steer providers toward the most appropriate test, and the more appropriate test might not always be less expensive.

“Often the system recommends a more appropriate, but still high-cost, imaging order,” Doyle explained.

On average, the study found that in 69% of the alerts shown to physicians, at least one of the more appropriate options offered was classifiable as a “high-cost” scan.

One of Doyle’s concerns going into the study was whether providers would ignore the alert system. He said the goal of the study was to be narrowly tailored enough to evaluate the software itself, rather than other institutional initiatives.

Now that they have these data, health systems can use the insights to build supplemental initiatives to support the goal of ensuring high-cost imaging is used appropriately.

“We deliberately studied an intervention where only the software was used, as that is quite scalable,” Doyle said. “In the future, management could use the data from such a system to improve appropriateness even more.”

Get the best insights in digital health directly to your inbox.

Related

Reinventing Clinical Decision Support

Has Health IT Adoption Improved Patient Outcomes?

How to Go from Clinical Research to Practice in 4 Months

Recent Videos
Image: Ron Southwick, Chief Healthcare Executive
Image: Ron Southwick, Chief Healthcare Executive
Image: Ron Southwick, Chief Healthcare Executive
George Van Antwerp, MBA
Related Content
© 2024 MJH Life Sciences

All rights reserved.