Where is the healthcare industry right now with regard to the successful use of data analytics? The answer to the question depends on a number of factors, but especially on two. It depends on the purpose or purposes for which the analytics solutions are being used—whether they be to support participation in value-based care delivery and purchasing regimens; participation in accountable care organization development; participation in population health management initiatives; participation in readmissions reduction work; or participation in other clinical or operational improvement initiatives, in hospitals, medical groups and health systems. The second factor has to do with how one defines “success,” and the robustness of analytics use.
That having been said, 2014 and 2015 have been a time of explosive growth in the use of data analytics for the above uses, and more. As Healthcare Informatics has been reporting, healthcare and healthcare IT leaders have indeed been moving forward quickly on the analytics front as the purchasers and payers of healthcare—federal, state, and private—have been demanding greater value for expenditure.
For example, on June 16 of this year, healthcare leaders participating in a panel discussion of predictive data analytics at the Health IT Summit in Washington, D.C., spoke of the long journey that provider organizations are embarking on right now across the U.S. healthcare system, one that they realize is both daunting and a long-term proposition. As Gabe Perna wrote, most patient care organizations are just beginning their analytics journey, and in that context, most are focusing initially on specific areas of endeavor.
In one instance referred to in that discussion, Cherie Pardue, deputy CIO of the Gaithersburg, Md.-based Adventist Health integrated system, noted that she and her colleagues have created an algorithm that alerts providers to patients at risk for sepsis. They’ve also developed a risk stratification score for readmissions within its accountable care organization. The lesson, Pardue told the Health IT Summit audience, is that “You never finish truly collecting or massaging the data. As you work through it, there are always things to tweak and refine. But the work that she and her colleagues have done has been successful so far, resulting in a drop of readmissions from 20 percent to 8 percent. Meanwhile, the organization is working on further reducing its readmissions rate by working specifically on readmissions of diabetic patients.
“One of the things we’ve worked on is educating people,” Pardue said. “The COO [has done] an amazing job of highlighting the data and how important everyone’s role is in contributing to the data and interpreting the data. That was the first step into turning our culture into an informational-driven one. Quite often, we get the reports and people don’t understand the role they play in the data that’s presented on the reports with the accuracy.”
The length of the journey ahead
The length of the journey ahead is only now beginning to be appreciated. In a discussion March 3 at the Health IT Summit in San Francisco, Shadaab Kanwal, executive director, Research & Quality, at the Oakland, Calif.-based Kaiser Permanente, led a panel discussion entitled “Driving Organizational Excellence with Analytics.” During that panel discussion, David Kaelber, M.D., Ph.D., CMIO, of the MetroHealth System, an integrated health system in Cleveland, Oh., summarized the current landscape when he said, “You have to have data, tools, people and processes, to make all this work. In healthcare, we’re just getting the data now, and maybe the tools. And in my own organization, we don’t have the people and processes to scale in place yet to really do this. So many people think of analytics as an end unto itself,” he added, “but analytics don’t deliver care, they only help people. We’re working on doubling our mammography rate, and to do that, we need the tools.”
What will be required, noted Jonathan Palma, M.D., medical director of IS analytics at Stanford Children’s Health in Palo Alto, Calif. Will be the development of solid partnerships between and among clinical informaticists, other informaticists, and clinician leaders, in order to create early “wins” with analytics-driven clinical performance improvement projects. “One important partner we have is our quality and safety department,” he noted. “When we partner with them around a defined set of goals, we can really make progress. We’re doing root cause analysis around hospital-acquired infections right now,” he reported. “Hopefully, that will lead to a change in the rates of infections.”
Moderator Shadaab noted that “In the past, we’ve dealt with databases that were originally created primarily for research. Meanwhile, healthcare is still grappling with core cultural problems” around achieving consensus for analytics-driven change. How do we move from proprietary infrastructure to disease-specific databases,” for more agile data use? he asked his fellow discussants.
“In San Mateo, we’re beginning to make that transition now,” noted Michael Aratow, M.D., CMIO of the San Mateo County Health System (San Mateo, Calif.). “The thing is that we all do use data in our daily lives, and even predictive analytics, like weather reports. And we always have our dashboards. Now we have to translate that” familiarity on the part of end-users in healthcare, with simple analytics in their daily lives, “into healthcare operations and clinical decision support.”
Stanford Children’s Health’s Palma opined that, “From where I sit in information services analytics, I see it as both an opportunity and a challenge; in terms of changing the culture around the use of data, that’s one of our responsibilities in informatics. I’d say we have a few pockets of reporting and analytics so far across Stanford Children’s Health,” he added. “And one opportunity is to help facilitate a data-driven culture.”
Industry experts agree that developing high-level strategies around analytics, prioritizing initiatives and projects, gathering together the right combination of leaders representing clinical informatics, clinical practice, IT, and administration, and gathering together the needed resources, are all key challenges in the leveraging of data analytics for value-based care delivery and purchasing, accountable care, population health, readmissions reduction, clinical and operational performance improvement, and virtually every other endeavor.
Industry experts: high hurdles remain
The deeper obstacles to rapid advancement in the analytics space remain considerable, say industry experts. Most patient care organizations have developed or are developing some sort of analytics strategy that involves an enterprise data warehouse, and combining claims, clinical and supply chain data, notes Judy Hanover, research director at research firm IDC Health Insights. “They are trying to assimilate that information. Most have a number of different repositories and different degrees of success combining that information,” she says, as noted in this issue’s feature, “Healthcare Analytics: Moving from Setup to Use Cases” (p. 58). But, Hanover notes, free-text notes in the electronic health record remain unstructured, and the approaches to unstructured data are much further behind approaches that look at structured data, she says. “The value in unstructured data is clearly there for organizations that choose to tackle it, whether through text analytics or natural language processing.”
Meanwhile, notes Larry Yuhasz, senior director of innovation and population health at Truven Health Analytics, “It is astounding how many organizations are creating enterprise-wide data warehouses and dumping in massive amounts of data without knowing about the stewardship of each data source. There are huge challenges around attribution, matching data to the right patient and the right physician, he adds. And, says Keith Figlioli, senior vice president of healthcare informatics at Premier Inc., the Charlotte-based healthcare alliance, data quality remains a key problem. “We just interviewed 50 to 75 people, ranging from executives down to analysts, and the No. 1 issue they mentioned by far is data quality,” he notes. “It was two standard deviations away from all the other issues. By far the No. 1 thing we talk about with members is data governance. We are seeing professionals come from other industries, such as consumer product goods and insurance, migrate to healthcare because they understand data governance.”
Tools for the path ahead
Right now, all industry experts and healthcare leaders agree, there remains some degree of fuzziness regarding the path ahead on data analytics. That is so not only because of the wide variety of goals, objectives, challenges, and opportunities involved, but also because of the fact that the leaders of even the most advanced patient care organizations readily admit that their organizations are just beginning the analytics-facilitated transformation of care delivery and operations in earnest. Looking ahead, experts and leaders say, the proof will be in the proverbial pudding, as the most advanced organizations blaze trails for their colleagues elsewhere to follow. Until then, the journey remains one fraught with challenges, but equally lined with opportunities for the genuine transformation of the U.S. healthcare system.