How analytics is helping lower risk for UPMC

Many healthcare providers use analytics to improve financial performance by boosting revenue and streamlining administrative processes.

But the deployment of analytics on the clinical side also can help providers control costs. Healthcare Finance News features an interesting article about how the nation’s second-largest provider/payer system is using analytics to identify high-risk patients.

With nearly 2.9 million members, UPMC Insurance Services Division (which includes UPMC Health Plan) trails only Kaiser Permanente in patient base among provider/payers in the U.S. Since spending $1.6 billion eight years ago to upgrade its data analytics and IT infrastructure, UPMC has “positioned the 125 hospitals in the UPMC system to not only survive, but thrive in the era of pay-for-quality and population health,” writes HFN Associate Editor Susan Morse.

The power of analytics resides in its ability to find connections and patterns in seemingly unrelated data. For example, as UPMC chief analytics officer Pamela Peele says, data shows that people who subscribe to magazines about cooking are far more likely to end up in a UPMC emergency room. This kind of information hinting at potential lifestyle-based health problems can help providers target certain populations with proactive outreach and education to head off serious and expensive medical conditions related to obesity.

"We model on a lot of different kinds of data," Peele tells Morse. "We model on household data, we use everything we can lay our hands on."

But it’s the claims process that provides the largest trove of useful information. "The backbone of data is claims data,” Peele says. “We get that and other data from the pharmacy, census … we bring all of that data together."

In addition, clinical notes within electronic health records can contain subtle clues that may foretell return visits to the hospital for individual patients. Morse explains:

“When the clinician writes the word ‘mother’ somewhere in the notes, those patients usually do very well, but when the clinician writes the abbreviation, ‘ww,’ which means the patient has a wheeled walker, there's cause for concern.”

The tipoff that the patient is at higher risk is “not that the patient has a wheeled walker,” Morse writes, “but that the clinician has included it in the notes.”

Those are the kinds of connections that clinicians wouldn’t be able to make without analytics. As Peele tells Morse, "Data are our eyes and ears. It's how to be smarter about what we're doing and manage the financial risk."

Latest News

Claims Life Cycle
Thirty-three percent of the American public supports a single-payer system, up from 21 percent in 2014.
Claims Life Cycle
Senate Majority Leader abandons plan to force a vote before the July 4 recess.

Stay Up To Date!

Get the latest revenue cycle insights delivered right to your inbox.