What you need to know about the forces reshaping our industry.


February 15, 2017

How hospitals are using predictive analytics

Daily Briefing

Data and predictive analytics can help hospitals and health systems avoid a "reactive" approach to medicine, Rebecca Vesely writes for Hospitals & Health Networks.

According to a 2016 Health Catalyst survey, 80 percent of hospital executives say predictive analytics could significantly improve health care. The survey found that about 31 percent of hospitals have used such tools for more than a year, and 38 percent said they were planning to adopt the technology within the next three years.

Predictive tools in action

At Indiana University Health's (IU Health) University Hospital, staff use predictive analytics to prevent central line-associated bloodstream infections. According to CDC, about 250,000 central line-associated bloodstream infections occur in the United States annually, and mortality rates for the infections range from 12 to 25 percent. The cost of treating such infections ranges from $3,700 to $36,000 per case.

IU Health since 2008 has used an e-surveillance program for hospital-acquired infections (HAIs) that is integrated with its EHR system. However, the combination only allows IU Health to monitor central line-associated bloodstream infections after patients had been diagnosed.

In 2016, IU Health launched a data visualization project at University Hospital that allows providers to see data in real time. With the dashboard, nurse unit managers and bedside nurses now can determine which units have missed central line maintenance activities and or did not complete prevention bundles for central line-associated bloodstream infections. Providers also can use the tool to track how long a patient has had a central line, which is a key predictor of infection.

According to H&HN, smaller hospitals also are testing predictive analytics tools.

For instance, Northwestern Medical Center in Vermont is launching a program this year that will use the LACE index scoring tool to identify patients at risk for readmission or death within 30 days of discharge. The index accounts for patients' acuity, comorbidities, length of stay, and number of ED visits. Research has shown that using the LACE index can result in moderate to high reductions in 30-day readmissions.

Chris Giroux, manager of data management and integration services at Northwestern, said, "I believe in the next five to 10 years, predictive analytics will be a necessary component in health care. It is going to help contain costs and produce better patient outcomes" (Vesely, Hospitals & Health Networks, 2/7; Minemyer, FierceHealthcare, 2/7; Vesely, Hospitals & Health Networks, 2/8).

Is ‘big data’ right for your organization?

Big data technologies bring new capabilities and IT economics to the problems of acquiring, storing, analyzing, and acting on data of unprecedented volume and variety. But is it right for you?

In our primer, we examine what big data is, the problems big data technologies attempt to solve, and the vendor landscape. We also provide guidance on when and if it makes sense to deploy big data approaches in health care settings.

Download the primer

Have a Question?


Ask our experts a question on any topic in health care by visiting our member portal, AskAdvisory.