Health IT, Hospitals, Policy

Four types of data analytics that providers are using to improve population health

The push by the government to reduce healthcare costs and the increased liability providers have […]

The push by the government to reduce healthcare costs and the increased liability providers have is forcing them to more easily identify and help chronic care patients to better manage their conditions. At the same time healthcare IT vendors are expanding their big data armories to help providers, particularly accountable care organizations mine claims and clinical data to get a better sense of patient outcomes, performance and how and where they can reduce costs. As more providers convert from paper to electronic records they are working with health IT vendors that can help them produce more accurate assessment of their patient populations to mine patient data to help predict outcomes.

At HIMSS earlier this month Dr. Anil Jain, the CMIO of Explorys, a spinout from the Cleveland Clinic, highlighted some of the different analytics approaches it is offering clients as they get more involved in population health.

Descriptive Analytics This accounts for the biggest chunk of big data across industries and it tends to focus on what went wrong or assessing why outcomes are more or less than what was expected. “Most people are  pretty well covered when you think of descriptive analytics,” says Jain. One example of descriptive analytics is giving hospitals a better understanding of current assessments, like how many of its patients should have received a pneumococcal vaccine or how many diabetes patients in an endocrinology department have their blood sugar under control?

Predictive Analytics Big data is chiefly being used to identify patterns, predict how to predict future outcomes, and avoid preventable events as a way to reduce healthcare costs. Jain says the most frequently asked question, particularly from accountable care organizations is,  “‘What percent of our patients will be re-admitted?’  They are also looking at how many patients will use the emergency room.”  Explorys’ big data platform includes a tool that can score patients based on their risk profile, such as whether they have chronic conditions, so providers can develop more effective approaches to care.

Prescriptive Analytics  One of the most noticeable trends at HIMSS this year was the increasing interest in prescriptive analytics. A recent report from Gartner looking across business intelligence said that only 13 percent of organizations are using predictive analytic but even fewer — 3 percent — are using prescriptive analytics, so there is plenty of opportunity for growth and the demand is increasing.  Prescriptive analytics involves helping a provider measure and manage a patient population. For example, one tool from Explorys’ big data platform allows users to focus on patients with obesity, add a morbidty like diabetes and assess their LDL levels or other measurement to determine where they need to focus attention.

“When you have an ACO that is trying to change the cost curve it is about good data but once the data is in, most providers look at the computer screen and try to figure out what the focus should be.”

Jain likens shifting from a descriptive to prescriptive data analytics platform to the equivalent of going from a broad, fluorescent light to a laser beam focus. “We don’t bring customers on if they are not ready to address population health as a solution. Provider groups have the same end-goal in mind: How do we stay relevant as pay-for-performance models change?”

Comparative Analytics One of the most interesting ways providers can use big data is to compare their performance to other healthcare facilities. Explorys expanded into the comparative analytics market this year with its National Benchmarks platform. The platform uses comparative metrics throughout more than 92 billion clinical, financial, and operational data sets across a continuum of care. By combining clinical data with claims and administrative data, it gives insights into patterns and trends. Providers can compare their performance with a particular patient population compared with the aggregate network, made up of providers such as the Cleveland Clinic, St Joseph Health System and Legacy Health.  Patient information is de-identified and made HIPAA compliant while keeping participating providers private. For example, providers can see how the LDL levels of their patients compares with that of the network and can use different sets of criteria across age, race, geography and gender. Providers can use the information to develop insights to improve performance.

Shares0
Shares0