The unmet potential of clinical decision support tools in cardiology
Clinical decision support tools (CDS) are electronic systems that take information from patients’ electronic health records and make suggestions to clinicians on how to care for patients. These tools can, for example, see that a patient’s blood pressure is high, send a notification to the doctor to point this out, and suggest a response, such as prescribing medication. In an article published on May 25, 2022 in The BMJ.
Yuan Lu, ScD, epidemiologist and assistant professor at the Yale School of Medicine, and colleagues reviewed the literature on CDS tools for cardiovascular care. The tools can be improved, Lu and coauthors found, writing in their abstract, “To date, the promise of CDS to provide scalable and enduring value for patient care in clinical practice has not been realized.
“There is evidence to show that clinical decision support has a positive effect on process outcomes, such as prescribing a drug, ordering clinical trials,” Lu said. “But the effect on the clinical outcomes, such as blood pressure, reduction in cardiovascular events, those kinds of clinical outcomes, has been mixed,” she added.
The authors note that across medicine, CDS tools have had only small effects on patient care and that until now there have been no reviews of the literature examining how the tools CDS affect cardiovascular care and the barriers encountered when implementing CDS in particular. In their article, Lu, along with Ted Melnick, MD, MHS, associate professor of emergency medicine and biostatistics, and Harlan Krumholz, MD, SM, professor of medicine (cardiology) and director of the Center for Outcomes Research and Evaluation ( CORE), set out to fill this gap.
Lu and colleagues identified a total of 77 studies, including 19 observational studies and 58 randomized controlled trials, of how CDS tools affect cardiovascular disease care. The researchers analyzed the effects of CDS tools in two main areas: the outcomes of healthcare processes, such as whether doctors prescribe drugs or refer patients to specialists; and clinical outcomes, or whether the use of CDS tools was linked to improved heart health.
Of the randomized controlled trials, 45 examined the effects of CDS tools on health care process outcomes. Of these, 23 studies found that using CDS tools improved outcomes in healthcare processes, leading physicians to take the actions recommended by the tools more often. Process-related improvements don’t necessarily mean better patient outcomes, Lu noted.
Other studies included in the review looked at patient outcomes. Of the 41 studies that examined the effects of CDS tools on clinical outcomes, 10 reported that the tools were associated with improvements for patients. Seven studies reported that CDS use was correlated with reduced levels of heart risk factors, such as LDL (“bad”) cholesterol. Yet the other 31 studies reported no association or a mixed association between use of the CDS tool and heart health outcomes.
A major barrier to using these tools is that they are not well integrated into clinicians’ workflow, the authors found. For example, primary care physicians already have a lot to do in brief appointments. A CDS tool that demands attention in a way that is not helpful is “an added burden,” Lu said. “So, due to lack of time, many clinicians try to ignore the tool. CDS or ignore the alert.”
Clinicians often ignore alerts. For example, in one study reviewed by the authors, physicians received a total of 3,848 pop-up boxes with notifications. Of these, physicians only expanded 188 (5%) to reach the point where they could see the suggestion of the CDS tool.
Despite these mixed results, Lu still has faith in the potential of CDS tools. “I am convinced that if CDS is integrated into the electronic health record and clinical workflow, it holds great promise for delivering high quality care and impacting patient outcomes. It’s just that we’re not there yet,” Lu said.
To improve CDS tools, Lu said, tool developers and clinicians need to communicate back and forth during the development process to iteratively improve tools and ensure they meet clinicians’ needs. With more work, Lu is optimistic that the CDS tools will achieve their promise of improving patient care and outcomes “just as an enabler to help the clinician do their job faster and better.”