OR WAIT null SECS
The University of Virginia Health System is making a concerted effort to find out how they can integrate clinical decision tools into their health network.
The premise of clinical decision support (CDS) software is clear: Use technology to leverage the power of big data to improve patient care and, theoretically, drive down costs. But the technology is, in many ways, still at the starting gate, in part due to technical and bureaucratic hurdles and a lack of scientific data surrounding its use.
Now, a major academic medical center, the University of Virginia Health System, is launching a concerted effort to find ways to integrate CDS into its organization. The evaluation is part of a larger effort at the health system to boost value-based care. It could prove to be a model to help other medical centers take the leap.
Joseph Wiencek, Ph.D., an assistant professor of pathology at UVA, said the health system is looking at products developed in house and elsewhere.
“We have several rules built from our internal analytics/informatics teams but would like to see if there is any value in external support that is becoming more widely available,” he told Inside Digital Health™. “These decision support tools would likely target high-volume, low-cost tests as well as high cost, low volume.”
The team remains in the evaluation and “data-crunching” phase, but he said one important element of the evaluation will be to get buy-in from the health system stakeholders.
“Since we are an academic teaching hospital, it is important to research and strategically partner with service lines and department leads to make sure we achieve lateral buy-in from our colleagues,” he said.
He and teammate Andrew Parsons, M.D., MPH, an assistant professor of medicine at UVA, recently wrote about how reduce laboratory costs, noting that “low-value care” — care that could be eliminated without harming patient safety — costs the U.S. healthcare system an estimated $800 billion each year.
They wrote that integrating decision support tools into electronic health record software could help reduce unnecessary costs. However, given the relative novelty of these types of products, health systems should evaluate them carefully before integration.
Wiencek told Inside Digital Health™ that there simply isn’t much in the way of scientific literature when it comes to the effects of CDS.
“I think the lack of peer-reviewed literature is an enormous impact,” he said.
While the technical work that’s required to implement the systems can be difficult, Wiencek said scientific evaluation will also be key.
“It truly is a multi-modal approach, and support from your colleagues and evidence-based literature will really be the only way these tools will succeed,” he said.
Ultimately, the success of any decision support technology will be about more than just cost. For some institutions, that could be the benchmark. But for others, victory might resemble patients receiving the right test at the right time, he said.
In fact, a recent study by researchers at the Massachusetts Institute of Technology found that CDS helped providers make more appropriate decisions but didn’t result in cost savings, in part because sometimes the most appropriate decision was a high-cost test.
Wiencek said while cost is a major issue in healthcare generally, he doesn’t think people should overemphasize its importance. Besides, he said, the cost implications of better decisions might not appear in the short term.
“Doing the right test for the right patient will lead to better clinical decisions, and patients will get the care that they need or be diagnosed faster,” he said. “If this happens, costs will fall, too. I’d like to see these types of tools lead us in that direction.”
Wiencek offered no timeline as to when UVA will complete its evaluations, though he said the team is proceeding at a “steady pace.” The health system is currently working with a single external vendor, though he said they have been approached by several others.
Get the best insights in digital health directly to your inbox.