This book includes a plain text version that is designed for high accessibility. To use this version please follow this link.
Predictive Modeling

Managing the risks of healthcare reform

Using risk adjustment and predictive methodologies to drive capitation arrangements, population health management and network performance initiatives.

By Matt Siegel D

espite the looming Supreme Court ruling this June, U.S. healthcare reform continues to move forward, with several states (including Rhode Island, Maryland, Oregon and New York) begin- ning the process of building health insurance exchanges. If the Patient Protection and Affordable Care Act (ACA) remains unchanged after this summer’s ruling, all 50 states will be required to establish their own exchange or participate in a federally developed exchange by January 2014. As more and more provisions of the 2010 ACA law are implemented, state agencies and qualifi ed health plans of- fering essential health benefi ts will soon be faced with an infl ux of new customers seeking insurance. Specifi cally, the individual mandate, expansion of Medicaid eligibility and subsidized coverage through exchanges for lower-income individuals and families will bring forth potentially millions of new benefi ciaries. With the deadline fast approaching, state agencies are now contemplating strategies for linking the publicly funded Medicaid programs and the newly established exchanges. A seamless integration would ideally ensure continuity of coverage, providers and health plans for those individuals whose eligibility status will change from year to year due to fl uctuating income.

As the conversation around reform progresses and health insurance coverage for the uninsured population increases, both risk adjustment and predictive modeling become a crucial part of that discussion. To fairly set capitation rates for new consum- ers, state agencies will require a mechanism for understanding the illness burden and future cost of care for each individual. Working within these capitation arrangements, managed care organizations (MCOs) tasked with delivering care to these consumers will have a greater need to drive population health management and network performance strategies focused on improving quality and reducing costs.

Ahead of the pack:

Learning from the Massachusetts experience To understand the impact of healthcare reform, and get a glimpse into the not-so-distant future, one should look no

14 June 2012

further than Massachusetts. Using risk-adjustment technol- ogy proved to be crucial, when, in 2006, Massachusetts became the fi rst state in the nation to overhaul its healthcare system by implementing the country’s fi rst health insurance exchange. Six years after the state’s landmark legislation was passed, the Commonwealth has achieved more than 98 per- cent insurance coverage of its residents, and the Connector Authority, which runs the exchange, recently announced a second consecutive reduction in risk-adjusted payment rates to participating health plans. Furthermore, according to a recent report by the Massachusetts Taxpayers Foundation, “additional state spending attributable to the health reform law accounted for only 1.4 percent of the Commonwealth’s $32 billion budget in fi scal 2011.”

How was it possible that Massachusetts managed to achieve more than 98 percent coverage without “busting the budget,” as many warned? A signifi cant factor contributing to the Connector’s success is the use of risk adjustment to better align payments to population acuity and allow competitive bidding among a greater number of participating health plans. The technology analyzed and quantifi ed the fi nancial and clini- cal risk of uninsured populations and ensured that the state was better informed in contracting with health plans. The risk methodology used by the Massachusetts Health Connector applied business analytics to data sources to examine Commonwealth Care enrollment data for 2007 to identify members with the greatest chance of incurring high costs based on their illness burden, lifestyle indicators and omissions in care. Clinical algorithms and predictive models transformed a comprehensive database, composed of medical, pharmacy, eligibility and other data, into meaningful informa- tion. Not only was a comprehensive clinical profi le created for each individual, but more importantly, each profi le included predicted costs. The risk-adjustment models use diagnostic and demographic information to form predictions (risk scores) of healthcare resource use at the individual level. Member risk scores were used to determine risk-adjusted rates paid to the MCOs providing benefi t plans to those electing coverage through the exchange. The risk-adjusted payments protected MCOs from attracting a higher-than-


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36