Emerging theme of the University of North Carolina at Chapel Hill Health Informatics Symposium — getting the right data to the right person at the right time

In 2015, US national health expenditures totaled $3.2 trillion, or almost $10,000 per person. The Centers for Medicare and Medicaid Services project that these expenditures will continue to increase through the year 2025. How do we stop or reverse this trajectory without compromising access to healthcare or the quality of that care?

One answer to this conundrum is getting the right data to the right person at the right time, which was a refrain heard throughout the University of North Carolina at Chapel Hill Health Informatics Symposium held in April 2017. The symposium brought together a diverse group of over 100 attendees, including faculty and staff from UNC-Chapel Hill, Duke University, NC State University, NC Central University, East Carolina University, as well as industry partners from across North Carolina, to discuss the use of data in healthcare systems.

In his keynote, Using Big Data to Improve Outcomes Under Accountable Care, Dr. David Bates reinforced the health expenditure problem that we are grappling with as a nation. "We spend a lot more per capita than any other country on health and if you look at the percentage of our total expenditures as a percent of GDP, that's really high," he explained. "We're about twice as high as the next leading competitor. This has been a real issue for us. And I would submit that this is the burning platform in healthcare in the US today and something that we've got to do something about." Dr. Bates is an internationally renowned expert in patient safety, using information technology to improve care, quality-of-care, cost-effectiveness, and outcomes assessment in medical practice. He is the Chief of the Division of General Internal Medicine and Primary Care at Brigham and Women's Hospital, a Professor of Medicine at Harvard Medical School, and a Professor of Health Policy and Management at the Harvard School of Public Health.

One way to lower health expenditures while improving the quality of health care is by utilizing big data to create "learning health systems." Dr. Sam Cykert, Professor of Medicine at UNC School of Medicine and Director of the Program on Health and Clinical Informatics, characterized big data with an example from a national health insurer: "They were using data from grocery carts…in regions that had poor health outcomes but an uptick in the purchase of multi-grain products [that was where] they were focusing their health care improvement programs because…the use of the multi-grain products showed a willingness to change." This concept of big data incorporates data beyond what we typically associate with health care data, such as the information found in the electronic medical record.

In a recent NEJM Catalyst article, Why Every Health Care Organization Needs a Data Science Strategy, Dr. Bates defined a learning health system as a system that uses data to help predict patient outcomes and to identify specific, actionable areas for improvement. Dr. Bates expanded upon this idea in his keynote address, offering a snapshot of how Partners HealthCare and Brigham and Women's Hospital in Boston are using big data to move toward a learning health system. They have focused their initial efforts in six areas of the hospital inpatient setting — high-cost patients, readmissions, triage, decompensation, adverse events, and treatment optimization for diseases affecting multiple organ systems — that they believe will yield high value care along with a reduction in health expenditures.

UNC-Chapel Hill and UNC Health Care sees the value in big data, and is busy fostering a learning health system and training the next generation of clinical informaticians to transform health care.

Brent Lamm, Deputy CIO for the UNC Health Care System and one of the panelists at the symposium, noted how far the university and its affiliated hospitals have already come: "I started here in January 2009 and none of this [clinical data warehouse and informatics research capabilities] existed. It's really exciting for me to sit here and see this — it's awesome."

The pace of growth in research and clinical informatics at UNC-Chapel Hill continues to expand, from the development of the Carolina Data Warehouse for Health (CDW-H) to the development of new tools for researchers to utilize the data in news ways to foster translational research. Also, the Biomedical Informatics Service at the North Carolina Translational and Clinical Sciences (NC TraCS) Institute provides tools and experts to catalyze collaborations, expand the research portfolio, and create and sustain partnerships in clinical data research networks. Similarly, clinical and biomedical informatics programs on campus continue to grow with the addition of new faculty dedicated specifically to informatics. This process is leveraged by the Carolina Health Informatics Program (CHIP) and its certificate and master's degree programs with emphasis on translational and applied informatics. A PhD program in Clinical Informatics is in its first year.

The symposium was sponsored by the Carolina Health Informatics Program, the Program on Health and Clinical Informatics, and the North Carolina Translational and Clinical Sciences (NC TraCS) Institute, home to the NIH Clinical and Translational Science Awards (CTSA) Program at UNC- Chapel Hill.

To see all speakers at the symposium or peruse the topics covered, you can find the program at phci.tracs.unc.edu.