Big Data helps Courage Kenny connect with patients

Finding candidates for rehabilitation as soon as possible is critical to achieve the best possible results and avoid permanent injury.


Care providers at Courage Kenny Rehabilitation Institute knew there had to be a way they could be more proactive with patients.

The Minneapolis-based rehabilitation institute, now part of the 13-hospital, 61-clinic Allina Health system, annually treats more than 95,000 people trying to regain functionality after suffering strokes, spinal cord injuries and traumatic brain injuries, as well as other short and long-term disabilities. But too often, the institute found itself without the information it needed to take the initiative and connect with patients.

“The traditional way we see patients is through a referral from a physician after discharge from one of our hospitals,” explains Kyle Grunder, director of provider operations and program development at the institute. “But when we dug deep into the data, we found that didn’t happen as frequently as it should, and even when patients were referred, they didn’t always make an appointment in the timeframe they needed to. What we needed was a way to catch those patients farther upstream and intervene when their health data indicated they needed it most ”

According to Jill Henly, Courage Kenny’s manager for care coordination, timing is everything.

“There’s a window of opportunity after a traumatic injury to put a patient on the right path and avoid permanent injury, and we felt that too many patients were missing that window, which is typically around 12 weeks,” she says. “We decided we needed to start helping those patients navigate the Allina health system by enrolling them quickly in care coordination programs and actively monitoring their progress.”

To do so, the rehabilitation institute embarked on a big data effort that combines Allina Health’s enterprise electronic health records with information from long-term care facilities and primary care providers as well as Medicaid claims data from the state of Minnesota. The consolidated data and analytics efforts helped it identify at-risk patients who needed help managing post-acute care and medication therapies and keep them in line with Courage Kenny’s clinical pathways.

“After a traumatic injury, such as a stroke, there often is some cognitive impairment that makes it difficult for patients to navigate through the health system and keep track of their appointments and medications,” Henly says. “On top of that, health care has become increasingly complex—there are so many more specialties than there were in the past, and for patients who are often confused and simply tired after discharge, that’s a lot to ask.”

Courage Kenny’s analytics effort, in the last year, has allowed the institute to make huge strides in treating its high-risk populations. Among the achievements:

  • A 30 percent reduction in hospitalizations. The pre-enrollment baseline was .74 hospitalizations per patient per year. Post-enrollment, this was reduced to .52 hospitalizations per year per patient.
  • A 66 percent reduction in hospitalization days. The re-enrollment baseline was 10.2 hospital days per year. Post-enrollment, this was reduced to 3.5 hospital days per year.
  • A 79 percent reduction in 30-day readmissions days. The pre-enrollment baseline was 6.37 days in hospital associated with a 30-day readmission per member per year. That’s been reduced to 1.36 days in the hospital.
  • A significant improvement in access to care through nurse care coordinators. Care coordinators have contact with 55 percent of their patients each week, spending an average of 52 minutes per patient per issue.
  • A one-year savings of $4.5 million. Savings are based on comparison with a three-year baseline of medical services use, with reduced or eliminated need for services that would otherwise have been required—such as emergency department visits, hospital admissions and, when admitted, reduced length of stay.

The Courage Kenny Rehabilitation Institute was formed in 2013 through the merger of the independent Courage Center and Allina Health’s Sister Kenny Rehabilitation Institute. Prior to the merger, Courage Center invested heavily in creating a disability-specific primacy care model for treating its patient population. The model is designed to coordinate not only health care but also services for patients to address complex social needs like housing, access to community resources and transportation.

After the merger, the first order of business was to tie the center to Allina’s Epic EHR platform and then have Courage Center leaders work with Allina data architects to develop the data marts to feed into the health system’s big data analytics infrastructure.

Allina Health in January 2015 began a partnership with Health Catalyst under which the health system outsourced its data warehousing, analytics and performance improvement technology to the vendor. Allina Health under the incentive-laden agreement maps out specific clinical and financial performance improvement targets and gets access to Health Catalyst’s newest technologies.

Health Catalyst’s enterprise data warehouse architecture is based on what the company calls a “late-binding” approach to information, compared with the more commonly used “early-binding” strategy.

The late-binding approach at its heart is a strategy that enables organizations to move data from source systems into a warehouse without trying to transform the data up-front by changing its formatting to make it usable for specific purposes and committing it to a relationship. That transformation and binding happens later, when the specific data is needed for an analytics effort.

Health Catalyst moves data from source systems into source marts, which serve as a type of staging area for analytics. Minimal data transformation occurs until that data is then linked to a “data bus” comprising a small number of core data elements that are common to almost all analytics use cases in healthcare (patient ID, provider ID, date and time, facility ID and more).

Binding source mart data to these stable, core data elements enables organizations to query across disparate source system content in the data warehouse.

The next element of the architecture is subject-area marts that are created to address particular analytic use cases. An example of a subject area mart would be a diabetes registry, where data could be taken from a source mart and then associated across numerous, additional variables, such as eye exam history, A1c test results, medication history, age and other data points.

Courage Kenny aggregates the clinical and demographic EHR data from Allina’s inpatient facilities along with condition-specific data—in the case of stroke victims, for example, data from the Berg Balance scale, the Berg Fall risk and the Mann assessment of swallowing ability are fed into subject area marts.

After the data infrastructure was set up, the institute deployed dashboards to provide care coordinators and other clinicians with multiple views of the patient population. The dashboards enable team members to identify and target populations, evaluate clinical processes and business operations, manage care and support across the continuum, measure patient outcomes and evaluate return on investment for each sub-program and for the program as a whole.

The dashboards also deliver functional assessments such as patient mobility, stability, cognitive, and pain across the care continuum by location, encounter type and time-period. It also gives the Courage Kenny staff the ability to drill down into high-level data to discrete views at the patient and provider level.

A critical component of the big data effort is pulling in claims data from the state of Minnesota via an integrated health partnership that creates an accountable care model for patients in the state insured under Medicaid, a significant portion of Courage Kenny’s patient population.

“The claims data combined with our EHR and other information really gives us a new level of transparency,” says Grunder. “Our own data might indicate we are doing pretty well for a patient, but we didn’t know that they were going to an emergency department every month outside our health system. Now we can use that data to flag patients for care coordination instead of letting it slip through the cracks.”

Kenny Courage continues to refine its approach by modeling more efficient pathways in the system based on its quality, treatment and outcomes data, Henly says, as well as connecting with patients when the time is right. “When we identify patients through the system who are in need of help, we find that when we reach out to them they are completely ready for that extra help because they know they’re not on the right trajectory.”

More for you

Loading data for hdm_tax_topic #better-outcomes...