Man vs. machine: Human CDS reduces inappropriate imaging, cuts costs

As healthcare continues its hunt to reduce inappropriate imaging, one radiology practice has found human clinical decision support to be remarkably effective.

The approach allows radiologists to press a change-order button in the electronic medical record that alters the ordering provider’s CT or MRI request. It’s early success in limiting excess imaging, along with decreases in radiation exposure and costs, may be particularly important in light of CMS’ requirement that providers consult appropriate use criteria before ordering advanced imaging for Medicare patients.

A number of practices have been using such benchmarking tools in preparation for the CMS mandate that went into effect this January. Clinical decision support-recommendation acceptance rates, however, have been far from consistent, Sarvenaz Pourjabbar, MD, with Yale-New Haven Hospital, and colleagues wrote Jan. 17 in the Journal of the American College of Radiology.

Some figures suggest that 99% of these suggestions are ignored, but as many as 63% of those inappropriate exams are still carried out. In contrast, the authors noted, their human CDS intervention produced an 82% acceptance rate.

“These data suggest that direct radiologist involvement in modifying orders has greater impact than CDS tools,” Pourjabbar et al. wrote. “Radiologist review of imaging orders for appropriateness also addresses the need for patient-centric imaging initiatives.”

The researchers tested their tool on more than 79,000 outpatient CT and MRI requests at the author’s tertiary care center over a nearly one-year period. Requests to change a provider’s order were higher for MRI exams (5.2%) compared to CTs (2.9%). Clinicians accepted radiologists' requests for change at the same rate (82%) for both modalities.

Radiologists most commonly modified CT and MRI orders with and without contrast to ones with contrast only (39% and 26%, respectively).

What’s more, about half of the changes in CT orders led to an exam with less radiation, and another 76% resulted in a cheaper procedure, the authors found. In MRI, those alterations led to a 26% drop in gadolinium usage and nearly 50% less costly imaging.

All in all, these efficiencies can be done for about $50 each day to cover the staffing costs required to run the program. And the changes could have implications across healthcare.

“This system has potential to reduce inappropriate examinations, decrease unnecessary radiation exposure in CT, and reduce healthcare costs by optimizing imaging studies selection,” the researchers concluded.

""

Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.

Around the web

The new technology shows early potential to make a significant impact on imaging workflows and patient care. 

Richard Heller III, MD, RSNA board member and senior VP of policy at Radiology Partners, offers an overview of policies in Congress that are directly impacting imaging.
 

The two companies aim to improve patient access to high-quality MRI scans by combining their artificial intelligence capabilities.