Using Big Data for Better Health Outcomes

The recent decision by the U.S. Supreme Court to uphold the Affordable Care Act’s federal subsidies for health insurance further entrenches the law, and continues the shift towards new ways of providing health care — including new kinds of delivery, financing, operations and leadership.

One striking aspect of the new landscape is the increasing use of data and analytics to improve outcomes, streamline processes and make purchasing more efficient. With careful use of data, health care providers can make significant strides in delivering better and more cost effective care.

MIT Sloan Management Review‘s recent case study of Intermountain Healthcare shows health care analytics at their best.

The case cites as an example Intermountain’s use of infection rate data to change the hospital and clinic group’s approach to operating room attire. The data showed chief of surgery Mark Ott that surgical infection rates at its flagship hospital, Intermountain Medical Center, were in line with national norms. He presented the findings to the surgeons there, saying, “You think you’re great, but compared to other hospitals in the country, you’re not above average.”

Intermountain uses a collaborative process to encourage behavioral change. On the infection question, a committee of clinicians spent a year developing a list of 30 possible causes, then whittled them down to five and made recommendations for changes that would address them. Ott sent out a note announcing the five recommendations, and got “a bunch of people complaining, the usual thing,” he says. In particular, doctors hated having to give up bringing personal items into the operating room, including fleece jackets they would wear to keep warm. “They literally hated that,” Ott says. “I would get calls all the time about how stupid that is.” Ott himself had to quit wearing his Boston Red Sox cap to cover his hair, in favor of disposable surgical caps.

The doctors argued that there was no hard evidence that the recommendations would actually help. Ott agreed, but told them that in six to nine months he would have data. If it didn’t show results, doctors could go back to their old ways.

In fact, infection rates fell to half the national standard. When the doctors got the data, they were delighted. But they also asked to relax the rules against personal items in operating rooms. Ott held firm, saying that since it was not clear how each of the five factors had impacted the data, the hospital needed to keep doing them all.

The infection control scenario, and Ott’s decision to stand firm, are the result of decades of work at Intermountain to build a data culture. Over the years, clinicians have learned to work together on a concerted effort to bring data-based insights to clinicians and managers across the Intermountain organization. All clinical programs have embedded analytics support teams, and procurement decisions are heavily influenced by data and analytics. Patient interactions are continuously enhanced by data, from the application of population health analytics to analyses of patient self-reports.

In 2016, Intermountain will launch a new insurance product that will make physicians and Intermountain jointly responsible for health care costs. Doctors who reduce costs will earn more income. As a result, providers will be even more focused on data. Intermountain will rely on the culture it has built and the systems it has developed to further improve care and manage costs.

For more on this topic, including the data on Intermountain’s improved health outcomes, read the case study “When Health Care Gets a Healthy Dose of Data.”