Organizations that put analytics to work effectively are gaining deep and broad insights about their customers — an approach that can transform health care.
Today’s health care environment presents challenges on many fronts, but somewhere at the intersection of cost, performance and outcomes is data. How health care organizations tap data to produce information, knowledge and insights increasingly determines whether they flourish or flounder.
To be sure, the right data can boost the quality of care, trim costs and deliver insights that allow health care providers to rethink and reinvent processes.
"Analytics is a key area for investment and it is one of the top spending priorities for health care organizations," says Bill Shea, vice president of the health care consulting practice at Cognizant. "But there are considerable barriers to getting maximum results."
How can leaders at a health care organization adopt a best-practice approach? How can it transform mountains of data into real-world insights? While there is no simple prescription for success, a well-conceived analytics strategy is an increasingly critical piece of the overall health care puzzle.
As Shea puts it: "Analytics is at the center of today's transition to an outcome-based pay-for-value model."
One organization putting analytics to work is Missouri-based Mercy, the fifth-largest Catholic health care system in the nation, with 44 acute care and specialty hospitals and more than 700 physician practices and outpatient facilities in the Midwest United States.
Since 2013, Mercy has parted with a collection of ad hoc tools and moved to a platform from a single vendor, SAP. This allowed Mercy to process massive amounts of data and achieve real-time insight seamlessly.
The solution — which connects to electronic health records and an array of other enterprise systems — has helped Mercy realize about $33 million in perioperative supply cost savings while helping nurses improve scheduling.
Analytics also has helped Mercy monitor the use of evidence-based pathways and treatment protocols, trimming costs by $800 a case for heart-failure patients while cutting the mortality rate to about half of the national average.
"Users can drill down and see how costs are defined on a per-case basis, they can view specific supply costs for a procedure and they can look at other factors and costs," says Jamie Oswald, Mercy’s manager of data analytics and engineering.
"The analytics platform provides insights immediately. In the past, legacy tools and processes resulted in wait times of three weeks or longer. The platform drives better decision-making but it also helps build credibility as we move forward."
Another facility tapping the power of analytics is the University of California at San Francisco Medical Center. In recent years, it has set its sights on migrating from a hypothesis-based framework to a data-driven approach. Researchers feed data volumes as large as 10 gigabytes — with up to 7,000 variables — into a machine learning and analytics system from Ayasdi. It spits out correlations and possible causalities within a few seconds.
Adam Ferguson, an associate professor and principal investigator at the medical center, says that the approach is leading to a much deeper understanding of symptoms and treatments for brain and spinal cord trauma, as well as helping researchers identify predictors for post-traumatic stress disorder and other problems. "By assembling the pieces of the puzzle, we will be able to diagnose and treat patients far more effectively," he explains.
A best-practice approach to analytics requires more than sophisticated information technology and software, Shea says. One problem health care organizations face is that analytics functions and users often are distributed and dispersed. As a result, it's essential to establish data standards, build a platform that connects diverse data sources, make data available in real time, and deploy tools that practitioners and staff can use at the point of decision-making — or patient contact.
"It's critical to create a data culture and focus on use cases,” he says. “When your entire organization understands the value of its data, and you know what you want to achieve, you can plug in the right data sources and data sets."
Todd Stewart, MD, vice president of clinical integrated solutions at Mercy, believes that it's important to identify key opportunities, build on the success and evolve from basic reporting and analytics to prescriptive and predictive approaches.
"When you have data at your fingertips you can better align performance with your metrics — and make adjustments quickly,” he says. “You can take performance to a level that wouldn't have been possible in the past."
Samuel Greengard is a freelance business and technology journalist based in Oregon.