Big Data is rapidly transforming patient care at Long Island’s North Shore-LIJ Health System, one of the nation’s largest healthcare providers.
“For many years, we’ve created very sophisticated analytical work in what today would be called ‘big data,’” says Jeff Kraut, North Shore’s senior vice president for strategy and business informatics. More recently, though, the health system’s shift from a traditional fee-for-service model to one based on shared risk and pay for performance “has forced us to take another look at how we’re organized for analytics and what we need to do to support value-based medicine,” Kraut explains.
During the past 20 years, although data and analytics have helped inform decision making at the 19-hospital, 6,400-plus bed provider, the process has taken place in what Kraut refers to as “cooperative silos.” But value-based purchasing and risk-based contracting—whereby the health network gets paid for agreed-upon patient outcomes in lieu of services rendered—have created a need to collect, collate and harness data across the North Shore system instead of department by department.
To integrate the data generated by different hospital functions and buttress its over-arching strategy of providing managed patient care, in 2013 North Shore launched a big-data analytics initiative known as Care Solutions. The two-year-old business unit has three primary responsibilities:
- To monitor North Shore’s value-based outcome performance goals as stipulated in contracts with private insurers and government programs like Medicaid and continuously compare those outcomes against cost and resource utilization levels to ensure that the health system remains profitable.
- To provide the performance-based metrics needed to demonstrate to payers that those goals have been met.
- To provide feedback to doctors and other practitioners about their performance with respect to their patient-outcome objectives.
The core objective within all this, Kraut says, is using insurance claims and electronic health record (EHR) data to identify and better manage those patients at greatest risk. Among the some 200,000 North Shore patients covered under value-based contracts, “10 percent represent 60 to 70 percent of our spend and resource utilization,” he says. So improving outcomes and lowering treatment costs among this pivotal group is the key to meeting performance goals and maintaining profitability.
For example, in the greater Long Island area that North Shore serves, 30 percent of all emergency room visits are for non-emergencies and 30-day hospital readmission rates range from the high-teens to the low-twenties.
By reducing both types of occurrences among the hospital network’s high-risk population through close patient monitoring and timely support, Kraut expects the healthcare provider to be able to substantially reduce unnecessary resource utilization and its total cost of patient care.
in order to accomplish these paired goals, North Shore’s Care Solutions team has developed what it refers to as “the analytics life cycle,” which draws on many millions of data points to better comprehend the disease burdens facing its patient population and the demands these place on hospital resources. Capturing patient data is at the heart of the effort.
“It’s very difficult to manage what you don’t have data about,” says Joe Schulman, Care Solutions’ executive director.
At the start of the cycle, North Shore receives claims data from any public or private insurer with which it has entered into a risk-sharing agreement. As part of the contract negotiations, an understanding is reached on what data the payer will provide, the structure of the data, how it will be delivered and the frequency of that delivery.
“No two data sets are ever alike,” notes Greg Bennett, a program manager, although he and the rest of the Care Solutions team are working to develop a more standardized approach that consistently includes patient identification and classification, health network membership and eligibility, medical claims history and pharmacy information among the data elements.
The data resides in an SQL Server Data Warehouse. Once it has been sorted and structured, it’s fed into one of two analytics engines—the web-based Optum Impact Suite from Optum Inc. and Explorys, a cloud and Hadoop-based big data platform that was developed by the Cleveland Clinic and acquired last month by IBM.
The Optum analytics tool suite includes Impact Intelligence, which allows the Care Solutions team to dissect and present data using a variety of measures including utilization trends and patient outcomes; Impact Provider, which provides clinical informatics and longitudinal care information that can be used to improve patient outcomes, and Impact Pro, which makes use of episode-based predictive modeling to help care managers target services at the highest-risk groups within North Shore’s population.
The Explorys platform provides similar functions, according to Bennett, that enable North Shore to collect, link, and combine “many millions” of data points from hundreds of disparate sources.
The engines synthesize claims and socio-economic data with “transactional” or clinical data drawn from North Shore’s electronic medical record systems and includes data points such as physicians seen, services received and medicines prescribed. Pharmacy data from Allscripts is also part of the feed. The combined data is used to analyze or “stratify” the patient population by age, diagnosis, location, risk factors and other demographics, Bennett explains.
These breakdowns are provided in reports that are used to optimize hospital resource allocations, plan future investments in facilities and new services and to provide comprehensive pay-for-performance reporting.
Once these reports have been generated, they are submitted for multiple rounds of user-acceptance testing (UAT). This ensures that they meet the expectations of North Shore’s practitioners and administrators, and the feedback allows the Care Solutions team to better align the analytics engines with North Shore’s evidence-based medicine strategy.
Kraut says one example of how big data analytics are used in practice is to identify patients in need of special services. Some high-risk patients frequently change doctors and don’t use the same primary care provider consistently. Such patient behavior can create gaps in their medical care, allowing them to fall through the cracks and increasing the likelihood that the patient will end up requiring a hospital stay or making use of emergency services. That, in turn, drives up North Shore’s unnecessary resource utilization rate and total cost of care, running afoul of the health system’s outcome-based agreements.
However, the Optum risk-reporting tools allow the provider to identify and track these patients. The provider proactively contacts these patients to investigate why they are running from practitioner to practitioner and to try and steer them to a primary care physician who can more fully address their needs.
Care Solutions also feeds the data into North Shore’s health information exchange (HIE), a care management solution based on InterSystems’ HealthShare health informatics platform and developed by North Shore to coordinate and document high-risk patient care. Both patient and physician data is tracked through this system.
On the physician side, the HIE identifies patients’ primary care practitioners, providing information about the density of high-risk patients in the areas serviced by these physicians and whether or not they already have an affiliation with the North Shore health system. This helps the provider determine with which doctors it needs to cultivate a relationship in order to effectively manage its high-risk population.
On the patient side, lab test values, hospital registration and emergency room admittance data are associated with the patient ID, claim history and demographic data assembled earlier in the process. In this way, Care Solutions’ executive director Schulman says, a comprehensive record of all relevant factors pertaining to a patient’s health status is maintained and used to manage the patient’s course of treatment.
The HIE in turn feeds data into the North Shore-LIJ Care Tool, another system built on the HealthShare informatics platform and developed by North Shore to coordinate care for high-risk Medicaid populations.
Care Tool supports low resource utilization rates and good patient outcomes by allowing case coordinators, care managers and social workers to monitor patient and provider interactions in real time. Schulman says Care Tool was originally intended to manage the provider network’s bundled payment program, but was increasingly used to manage large volumes of claims and EHR records spanning all venues of care.
Among its other features, Care Tool uses claims data to provide predictive patient risk scoring, drawing on the patient’s most recent diagnostic data. The tool also automates routine data gathering and creates a workflow that spans from the call center to the clinician. The system also generates quality metrics, which are used for continuous improvement assessments.
Vishwanath Anantraman, an MD and North Shore’s chief information architect who led the development of Care Tool, provides this example: When a Medicaid patient is admitted to a North Shore emergency room or seen as an outpatient, Care Tool sends the staff member charged with overseeing that patient a real-time alert signaling that further intervention may be needed. The system lets the staffer monitor what took place during the visit and arrange follow up appointments with the patient’s primary care physician, alert other family members and suggest support groups, as appropriate.
“One of the keys to managing a high-risk patient population is an interdisciplinary approach,” says Anantraman. “We created Care Tool as an electronic environment where all members of a patient’s care team can collaborate and coordinate efforts toward helping patients meet their health and personal wellness goals.”
Like other elements of North Shore’s two-year-old big data initiative, Care Tool is still relatively new and rapidly evolving in terms of the types and volume of data that it draws on and the various ways in which the technology is employed. But the results are already having a positive impact on the health system’s bottom line. For instance, Schulman estimates that North Shore’s average 30-day spend for its Total Joint care bundle – a package of treatment services -- has dropped 4.2 percent year over year.
So what’s next for Care Solutions? Schulman and his team emphasize the need for more data standardization along with greater speed and scale. The aim is to further improve data quality and consistency in support of the health network’s continuous improvement efforts.
North Shore’s Kraut puts it this way: “We’re on a journey,” he says, “where we’re harnessing the data we have and the data we’re about to get.”
Register or login for access to this item and much more
All Health Data Management content is archived after seven days.
Community members receive:
- All recent and archived articles
- Conference offers and updates
- A full menu of enewsletter options
- Web seminars, white papers, ebooks
Already have an account? Log In
Don't have an account? Register for Free Unlimited Access