Can “Big Data” help address the challenges of risk adjustment?

Much has been written about “Big Data” and its potential for helping companies turn information it collects into critical business insights. Amazon’s product recommendation feature is one example of big data at work, but companies are also using it as a tool for many strategic decisions, including pricing, staffing, and product development. As the health care industry transitions from fee-based to value-based care models, big data holds a lot of promise for health plans and providers who are looking for better ways to measure value and assess risk within patient populations. One important area is risk adjustment.

Health plans have used risk adjustment for years to reflect the expected cost of providing coverage for their members. With the passage of the Affordable Care Act, risk adjustment serves as an important stabilization feature, ensuring that health plans don’t benefit from enrolling a disproportionate share of healthy patients and compensating them based on the underlying health status of member populations. As a result, the values assigned to new risk adjustment models are much more precise, and include the direct costs of primary care services and management of chronic conditions, as well as the indirect costs of care coordination.

Because so many rapidly changing variables factor into risk adjustment models, it’s critical for health plans to have accurate and timely data. But this is a challenge. The systems and processes health plans use to collect, store, and analyze this data are not where they need to be. The question is: How can they get there?

For insight into the challenges health plans face with data and risk adjustment and some possible solutions, download our new white paper, Risk Adjustment: A Roadmap to Success.