Embedding clinical decision support (CDS) into PACS significantly increases the likelihood that radiologists will use the software, but integration must occur at the time of implementation, otherwise physicians may become loath to change their workflows, concluded a study published in the July issue of the Journal of the American College of Radiology .
Despite vast efficiencies and improvements to care provided by the digital transformation of medicine, small technical inconveniences stand as notorious barriers to the adoption of new technologies, explained Matthew B. Morgan, MD, of the department of radiology at the University of Utah School of Medicine in Salt Lake City, and co-authors.
“Small technical factors can be significant deterrents to the use of decision support. Each step required to access a given support tool is a potential point of failure.” Such obstacles, the authors indicated, can pose substantial challenges to implementing applications, impacting potential benefits to patient care.
As a result, Morgan and colleagues divided 48 radiology residents into two equally sized groups, implementing a CDS program on the workstations of both groups. However, for the control group, the application had to be launched in a separate window from PACS, requiring the minimization of other ongoing computer applications. The experimental group was trained on the same decision support program, but was able to use the program within PACS.
After five months, the two groups switched, so that the integration group was required to use the separate application, and the non-integration group began using the PACS decision support tool.
The initial integration group showed significantly greater usage of clinical decision support than the group required to launch the separate application. At the fifth month, when both groups experienced peak usage, the integration group logged 604 sessions of the software, whereas the separate application group tallied 229 sessions.
Upon switching, the former PACS-integrated group experienced a drop in usage from 604 in the fifth month to an average of 289 sessions across the second five months of the study. Meanwhile, the new PACS group increased usage from 229 to 274 sessions per month. Both changes were statistically significant.
“Integration with PACS can increase the use of clinical decision support tools by embedding the tools in the clinical workflow. However, adding integration after users have learned an alternate means of access provides less benefit,” noted Morgan and coleagues, highlighting the three-fold higher usage of decision support in the initial PACS group.
The authors pointed out that because the crossover of applications occurred at the peak of each group’s usage, they could not be sure how the trends would have panned out over a longer time period, and whether this would have affected their findings.
Morgan and colleagues conjectured that the non-integrated system’s additional steps, unclear links, added logins and additional clicks all constituted points of failure, which hampered adoption. “Any risk for wasted time without successful payoff is a deterrent in a busy practice environment,” they maintained.
While concluding that decision support tools embedded in clinical workflow stand the best chance of improving the quality of care, Morgan and colleagues emphasized. “Integrated access is critical at the time of initial deployment, or acceptance of the decision support tools may be undermined.”