Live from iHT2-Cleveland: Geisinger’s Shift from an EDW-Dependent Data Strategy to a Big-Data Strategy

Oct. 5, 2016
John M. Kravitz, CIO of Geisinger Health System, shared with attendees at the Health IT Summit in Cleveland some of the developments taking place at his organization around the leveraging of data for care delivery improvement

What does it mean for an integrated health system to make a shift from an enterprise data warehouse (EDW)-driven strategy to a big data-driven strategy and architecture? Inevitably, there are many complexities involved. And John M. Kravitz, senior vice president and CIO of the Danville, Pa.-based Geisinger Health System, gave his audience a glimpse of some of those, when he delivered a presentation on Tuesday, Apr. 19, at the Health IT Summit in Cleveland, presented by the Institute for Health Technology Transformation (iHT2—a sister organization to Healthcare Informatics, under the Vendome Group, LLC corporate umbrella), being held this week at the Ritz-Carlton Cleveland.

The presentation, entitled "Geisinger's Transition from Enterprise Data Warehouse to Big Data Platforms,” gave Kravitz’s audience a broad sense of the shifts taking place at Geisinger these days, where many things are happening, including a merger last October with the N.J.-based AtlantiCare Health System. Not only has there been a lot of business activity in the integrated health system, which encompasses eight hospitals in Pennsylvania and two in New Jersey, as well as over 300 physician practices, and a range of outpatient care services; Geisinger continues to move forward in its population health management, care management, and evidence-based care delivery and payment innovations (including its flourishing ProvenCare program, which has married evidence-based clinical pathways with, in some cases, price guarantees for certain elective medical and surgical procedures).

With all the activities going on, Kravitz told his audience, it has become clear to senior Geisinger organization leaders that older ways of managing data and information were becoming unsustainable.

John M. Kravitz

“We had a lot of challenges with our EDW,” Kravitz told his audience on Tuesday, speaking of the organization’s enterprise-wide data warehouse. “We had pockets of data, but no data dictionaries, and purely structured data, and no unstructured data. We want to get closer to our patients, and use this data platform for that,” he said, of the broad big-data platform that he and his colleagues are currently building, a platform that he says will better be able to ingest social media-based and other data as well as traditional, structured healthcare data.”

One area in which the building of a more robust big-data architecture will be very helpful is in Geisinger’s intensive, ongoing effort to identify gaps in care for patients with chronic illnesses, and to leverage information technology to help providers provide better care to those patients, Kravitz said.
“We've been known as an innovator with regard to addressing care gaps; we use ProvenHealth Navigator in that area,” he noted. “And we’ve built our protocols and evidence into our EDW. And we work with patients with CHF [congestive heart failure], COPD [chronic obstructive pulmonary disease], diabetes, and on and on. And on a daily basis, we look for gaps in care. So we look to see if you've had your a1c done recently, for example. And if we find gaps, we'll fire order sets back into Epic, which we've had since 1995. That's been a valuable component.”

Kravitz went on to say that, “In our existing data warehouse, we look for gaps in care every night,” through automation-driven clinical intelligence. What that means is that the next time a patient has exceptional care orders, we will confirm that the patient hasn't had things treated elsewhere. We are bringing in data on services done in our community, into the EHR, too.” All this activity is connected to ongoing advances in data architecture, he said, noting that Geisinger’s existing EDW, which went live in 2008, and is called its “Clinical Data Intelligence System,” began without any unstructured data. But he and his colleagues are preparing to begin to work, through the EDW, with large amounts of unstructured data as well.

“We're gradually moving away from our current platform to a Hadoop platform,” Kravitz reported. “We are an Epic platform, but we've chosen Cerner Healthy Intent for population health. We signed that around HIMSS last year, 2015. It really brings things forward. We're seeing where the value will come in for us,” he added. “Before we started going down this path, we decided we needed a good strategy. We wanted to do a primarily in-house data platform, but also utilize the Cerner Healthy Intent. Covito with Epic was kind of new at the time, and HealthyPlanet wasn't in existence yet,” so he and his colleagues chose to partner with Cerner in that area instead. One of the big goals is to be able to leverage IT to create as much real-time alerting as possible, particularly with regard to rapidly evolving situations like sepsis. “We want to establish real-time data,” he noted. “Our EHR and analytics development. Cerner has a sepsis dashboard, Epic's working on it. We want to be able to do that in our systems real-time. We do that with Visicu. And it's that same type of algorithms and analytics that we want to bring to the acute workflow, to make sure we provide high-quality care and lightning-fast speeds.”

All of this development will also be manifested in what Kravitz referred to as an important initiative called “Geisinger’s Digital Front Door,” which will be entry points for patients/consumers, to enhance the patient experience with Geisinger care delivery. “We want a higher level of satisfaction and to personalize the experience. Patients want real-time scheduling, content delivery, etc.,” he said. “So that's our Digital Front Door. We're going to use our Hadoop platform to ingest this data, whether structured or unstructured, and to achieve the ability to mine that data right away and look at logs and identify what would have had to be identified in a manual process, including complaints or problems from patients. In other words, real-time monitoring rather than a patient contacting us. And to personalize our processes for our patients. That was the first use-case scenario.”

In fact, going forward, the use-case scenarios will simply evolve forward, Kravitz said. And he offered that the future looks bright with regard to the ability of technology to support Geisinger’s continually evolving work in population health, care management, evidence-based care delivery, and other important clinical and operational areas.

Sponsored Recommendations

How to Build Trust in AI: The Data Leaders’ Playbook

This eBook strives to provide data leaders like you with a comprehensive understanding of the urgent need to deliver high-quality data to your business. It also reviews key strategies...

Quantifying the Value of a 360-Degree view of Healthcare Consumers

To create consistency in how consumers are viewed and treated no matter where they transact, healthcare organizations must have a 360° view based on a trusted consumer profile...

Elevating Clinical Performance and Financial Outcomes with Virtual Care Management

Transform healthcare delivery with Virtual Care Management (VCM) solutions, enabling proactive, continuous patient engagement to close care gaps, improve outcomes, and boost operational...

Examining AI Adoption + ROI in Healthcare Payments

Maximize healthcare payments with AI - today + tomorrow