While working on an article about the state of healthcare analytics for an upcoming issue of Healthcare Informatics, I had a chance the other day to speak with Shaun Grannis, M.D., the associate director of the Center for Biomedical Informatics at the Regenstrief Institute in Indiana, about the increasingly important role health information exchanges can play. Dr. Grannis has spent several years studying the cross-section of HIEs and analytics with the Indiana HIE. His research has shown that patients do not receive care in one health enterprise. For instance, his research found that 40 percent of visits to emergency departments in Indiana are by patients who come from different healthcare systems.
“So If I want to understand healthcare utilization patterns, I need to integrate data from multiple sources,” Grannis said. “If I am an ACO and want to have complete picture of the patients I am responsible for, I need integrated data from people who are sometimes my competitors. We have agreed that integrating data to improve outcomes makes sense. So our HIE in Indiana actually provides ACOs data for analytics purposes.”
Analytics is a promising avenue for HIEs looking for valued services they can offer health system members. In January, in an interview with Healthcare Informatics’ Gabriel Perna, the State of Maine HIE CEO Dev Culver described how HealthInfoNet was rolling out a predictive analytics service option for members. The analytics service, created in partnership with the Palo Alto, Calif.-based HBI Solutions, uses real-time clinical data to determine and identify the potential costly patients that are in the middle range. They’re not yet the high-cost, frequent users of the system, but they very well could be.
“The analytics platform can tell you within the year, who will be admitted to inpatient, who will be in the emergency room, who will be among the top 10 percent of most expensive patients, who is going to be returning for admission within 30 days, and who will return to the ER within 30 days,” Culver said.
The conversation with Dr. Grannis and the Maine effort reminded me that I recently saw an announcement that Delaware's Health Information Network (DHIN) is set to play a central role in supporting the State Healthcare Innovation Plan (SHIP). With a grant through the CMMI State Innovation Model (SIM) initiative, SHIP’s major goal is to improve health system performance. Participants will use analytics to create a positive feedback loop of analysis, change, and review, according to DHIN, which was launched in 2007, and today serves all of Delaware's acute care hospitals and is approaching 100 percent of the state's medical providers.
According to DHIN, SHIP will include the development of a scorecard used by payers and providers to indicate the performance of primary care providers in three areas: adherence to accepted standards of care for a set of specific conditions; patient experience; and healthcare cost. Adoption of this set of core metrics by payers and providers will allow them to focus attention on a manageable set of key performance indicators with the highest potential to move the state in the direction of better health and lower costs, according to DHIN.
DHIN is working with a company called IMAT Solutions. The IMAT Enterprise Data Foundation, Medical Research and Query Builder, and Clinical Analytics and Reporting modules will be integrated as core components of the overall solution.
The IMAT system will aggregate, validate, and analyze data from payers and providers and present the results in a common scorecard user interface. DHIN will capture these key metrics and will also use the IMAT Enterprise Data Foundation module to leverage all of the data inside its Medicity HIE platform to provide value added data services to its stakeholders.
"DHIN has become the indispensable tool for healthcare providers in Delaware to receive clinical results and reports and look up historical information on patients under their care," said Jan Lee, CEO of DHIN, in a prepared statement. "Just as they appreciate having only one place to go to access all the key clinical data, they now look forward to having only one place to go to view the results of their performance measures. Having one set of measures generated by IMAT and used by all payers and one place to go to view those measures will create workflow efficiencies and a unifying focus for performance improvement efforts across an entire practice, regardless of which payer a given patient may be insured with."
Data quality is always an issue with HIE data. But as Dr. Grannis put it: “There is substantial value in this aggregate data today and it will improve over time. The game now is finding those bright spots in current data where it shows real value. It will get better, and the value of analytics will continue to grow.”