Greg Freiherr, Industry Consultant
Greg Freiherr, Industry Consultant

Greg Freiherr has reported on developments in radiology since 1983. He runs the consulting service, The Freiherr Group.

Blog | Greg Freiherr, Industry Consultant | Clinical Decision Support| October 23, 2015

Does Clinical Decision Support Software Work?

 human-skeleton STOCK

Image courtesy of Pixabay 

The idea behind clinical decision support (CDS) is simple — ensure that tests or procedures ordered by referring physicians are best suited to benefit the patient. But does CDS software really work? And how well?

Among the companies likely to highlight CDS on the RSNA exhibit floor are:

  • National Decision Support Company, which provides the technical platform, supports and licenses CDS. It is the exclusive distributor of national standards CDS imaging guidelines, providing ACR Select, the Web service version of American College of Radiology (ACR) Appropriateness Criteria;
  • Sage Health Management Solutions provides tools including RadWise for imaging CDS. Compliant with ICD-10, RadWise offers hyperlinked references, tracks patient radiation exposure, and reports patient outcomes; and
  • Stanson Health, a first-time RSNA exhibitor, combines point-of-care CDS with “actionable insights for analyzing and adjusting provider ordering behavior.”

Radiology-oriented CDS software is available from other vendors, including Nuance and Medicalis.

When CDS software is layered on top of a RIS/PACS, radiologists can access it directly. CDS for referring physicians typically is integrated into e-prescribing and computerized patient order entry systems.

The Feds are pushing the medical community to put CDS in place, although there’s plenty of time to do so. The Centers for Medicare and Medicaid plan to begin tracking the way advanced imaging exams are chosen, but not until 2017. After that, outliers could be paid less for not using CDS.

Regulatory pressure aside, CDS appears to hold value for providers and patients. Evidence has begun to accumulate that its use by radiologists can reduce the number of unnecessary studies.

Last spring researchers from NYU Langone Medical Center reported at the Society for Imaging Informatics in Medicine (SIIM) meeting that radiology exams were in-line with clinical guidelines 50-80 percent more of the time, after a CMS tool was integrated into the center’s dictation software. One of the researchers, Ankur Doshi, M.D., concluded that integrated decision support available to the radiologist at the point of care “may encourage use and help improve adherence to follow-up recommendations.”

Similarly evidence is accruing that CDS positively affects patient welfare when used by referring docs.  Research reported in the April issue of the Journal of the American College of Radiology (JACC), also available online, found that the integration of this software into inpatient computerized order entry system increased the overall use of ACR Appropriateness Criteria (AC) when ordering advanced imaging.  It also led them to provide the structured data needed to automatically generate AC scores.

Just as the value of CDS is beginning to bubble to the surface, so are the pros and cons of the software behind it. In another article published in the April JACC, researchers from the Cleveland Clinic reported on the use of two CDS products — Medicalis SmartReq and Nuance RadPort. Both used the ACR’s criteria.

The researchers examined how each handled the appropriateness and insurance dispositions of MRI and CT orders, concluding after several months’ experience and 2000 consecutive outpatient MRI and CT orders that the chief difference — and the strongest influence on outcomes — was how the software handled exams without relevant guidelines or with insufficient information.

“Nuance augmented published guidelines with clinical best practice; Medicalis requested additional information utilizing pop-up windows,” the researchers wrote.

Radiologists became frustrated, however, by the need for supplemental information. More than half of the exams scored by the Nuance system, for example, were scored as lacking sufficient information or having no guidelines to support the order. Similarly, radiologists express frustration from having to plow through the multiple windows that popped up in the Medicalis software.

Clearly more needs to be done before CDS is an efficient part of a radiologist’s workflow.  It appears, however, that CDS will play an important role in future of radiology.

Editor’s note: This is the third blog in a series of four by industry consultant Greg Freiherr on Clinical Decision Support. The first, “How Clinical Decision Support Can Help Radiologists,” can be found here. The second, "Clinical Decision Support or: How I Learned to Stop Worrying and Love Evidence-based," can be found here.

Related Content

Selecting an AI Marketplace for Radiology: Key Considerations for Healthcare Providers
Feature | Artificial Intelligence | October 18, 2019
October 18, 2019 — As the nascent market for...
Surgical Institute of Reading Chooses RamSoft's PowerServer Lite PACS
News | PACS | October 18, 2019
Surgical Institute of Reading recently selected RamSoft’s PowerServer Lite PACS (picture archiving and communication...
While electronic medical record systems have helped consolidate most patient data into one location, medical imaging IT systems has proved to be more difficult to replicate by large EMR vendors. This has made room in the market for third-party radiology IT vendors that allow easy integration with the larger EMRs like Epic and Cerner. This image shows Agfa's enterprise imaging system, leveraging its ability to be accessed anywhere with internet connection and pull images from radiology and surgery.

While electronic medical record systems have helped consolidate most patient data into one location, medical imaging IT systems has proved to be more difficult to replicate by large EMR vendors. This has made room in the market for third-party radiology information system vendors that allow easy integration with the larger EMRs like Epic and Cerner. This image shows Agfa's enterprise imaging system, leveraging its ability to be accessed anywhere with an internet connection and able to pull in images from both radiology and surgery. 

Feature | Enterprise Imaging | October 17, 2019 | Steve Holloway
October 17, 2019 — The growing influence and uptake of electronic medical records (EMRs) in healthcare has driven deb
USF Health Expands Digisonics System With Vascular Reporting
News | Cardiac PACS | October 17, 2019
University of South Florida (USF) Health in Tampa, Fla., has enhanced their use of the Digisonics Cardiovascular...
Intelerad's nuage Patient Portal

Intelerad's nuage Patient Portal. Image courtesy of Intelerad.

News | Enterprise Imaging | October 17, 2019
Intelerad Medical Systems announced that OneWelbeck, a London operator of specialist facilities for minimally-invasive...
An illustration of radiology department analytics data showing GE Healthcare’s business analytics software.

An illustration of radiology department analytics data showing GE Healthcare’s business analytics software.

Feature | Radiology Business | October 17, 2019 | By April Wilson
According to IBM, the world creates 2.5 quintillion bytes of data daily.
Feature | Artificial Intelligence | October 16, 2019 | By Siddharth (Sid) Shah
The period between November through February is pretty interesting for the field of medical imaging — two major confe
Sponsored Content | Webinar | Analytics Software | October 11, 2019
Today’s healthcare providers understand that becoming “data-driven’ is imperative to continued success. In this webinar...
Fujifilm Upgrades Next-Generation Synapse Cardiology PACS
News | Cardiac PACS | October 10, 2019
Fujifilm Medical Systems U.S.A. Inc. recently launched Synapse Cardiology PACS 5.6.1, the company’s next-generation...
As the role of artificial intelligence continues to expand, many companies are making significant investments in this technology to offer solutions
Feature | Artificial Intelligence | October 09, 2019 | By Sharmistha Sarkar
Artificial intelligence (AI) is a technology