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?

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

Guerbet, IBM Watson Health Partner on Artificial Intelligence for Liver Imaging
News | Clinical Decision Support | July 10, 2018
Guerbet announced it has signed an exclusive joint development agreement with IBM Watson Health to develop an...
FDA Clears Bay Labs' EchoMD AutoEF Software for AI Echo Analysis
Technology | Cardiovascular Ultrasound | June 19, 2018
Cardiovascular imaging artificial intelligence (AI) company Bay Labs announced its EchoMD AutoEF software received 510(...
News | Remote Viewing Systems | June 14, 2018
International Medical Solutions (IMS) recently announced that the American College of Radiology (ACR) added IMS'...
Wake Radiology Launches First Installation of EnvoyAI Platform
News | Artificial Intelligence | June 13, 2018
Artificial intelligence (AI) platform provider EnvoyAI recently completed their first successful customer installation...
How AI and Deep Learning Will Enable Cancer Diagnosis Via Ultrasound

The red outline shows the manually segmented boundary of a carcinoma, while the deep learning-predicted boundaries are shown in blue, green and cyan. Copyright 2018 Kumar et al. under Creative Commons Attribution License.

News | Ultrasound Imaging | June 12, 2018 | Tony Kontzer
June 12, 2018 — Viksit Kumar didn’t know his mother had...
Zebra Medical Vision Unveils AI-Based Chest X-ray Research
News | Artificial Intelligence | June 08, 2018
June 8, 2018 — Zebra Medical Vision unveiled its Textray chest X-ray research, which will form the basis for a future
Konica Minolta Launches AeroRemote Insights for Digital Radiography
Technology | Analytics Software | June 07, 2018
Konica Minolta Healthcare Americas Inc. announced the release of AeroRemote Insights, a cloud-based, business...
Vinay Vaidya, Chief Medical Information Officer at Phoenix Children’s Hospital

Vinay Vaidya, Chief Medical Information Officer at Phoenix Children’s Hospital

Sponsored Content | Case Study | Artificial Intelligence | June 05, 2018
The power to predict a cardiac arrest, support a clinical diagnosis or nudge a provider when it is time to issue medi
How image sharing through a health information exchange benefits patients while saving time and money is depicted in this slide shown at HIMSS 2018. Graphic courtesy of Karan Mansukhani.

How image sharing through a health information exchange benefits patients while saving time and money is depicted in this slide shown at HIMSS 2018. Graphic courtesy of Karan Mansukhani.

Feature | Information Technology | June 05, 2018 | By Greg Freiherr
A regional image exchange system is saving lives and reducing radiology costs in Maryland by improving the efficiency
Using Imaging Analytics for Radiology, VCU Health in Richmond, Va., has developed a dashboard to view turnaround time analysis. This functionality allows drill down for each technologist and radiologist and looks at the different steps of the imaging cycle.

Using Imaging Analytics for Radiology, VCU Health in Richmond, Va., has developed a dashboard to view turnaround time analysis. This functionality allows drill down for each technologist and radiologist and looks at the different steps of the imaging cycle.

Sponsored Content | Case Study | Information Technology | June 05, 2018
Sharon Gibbs, director of the radiology department at VCU Health in Richmond, Va., aims to provide quality, timely and...
Overlay Init