Using risk adjustment and predictive methodologies to drive capitation arrangements, population health management and network performance initiatives.
Despite 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) beginning 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 qualified health plans offering essential health benefits will soon be faced with an influx of new customers seeking insurance. Specifically, 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 beneficiaries.
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 fluctuating 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 consumers, 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 further than Massachusetts. Using risk-adjustment technology proved to be crucial, when, in 2006, Massachusetts became the first state in the nation to overhaul its healthcare system by implementing the country’s first health insurance exchange. Six years after the state’s landmark legislation was passed, the Commonwealth has achieved more than 98 percent 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 fiscal 2011.”
How was it possible that Massachusetts managed to achieve more than 98 percent coverage without “busting the budget,” as many warned? A significant 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 quantified the financial and clinical 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 information. Not only was a comprehensive clinical profile created for each individual, but more importantly, each profile 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 benefit plans to those electing coverage through the exchange. The risk-adjusted payments protected MCOs from attracting a higher-than- average health risk by providing higher rates to those plans managing sicker populations. The methodology also protected the needs of Massachusetts residents by deterring plans from attempting to “cherry pick” only the healthiest patients.
The other side of the coin: Lessons from managed care
MCOs and other health plans across the country will soon be bidding for the healthcare business of previously uninsured individuals and newly eligible public program beneficiaries. These new members come in all shapes and sizes – from the young and healthy to the elderly and sick. Changes to Medicaid eligibility and the subsidized coverage available through the exchanges will drive a greater number of low-income individuals with pent-up demand for healthcare services to seek subsidized coverage.
How will private payers manage the health and wellness of such diverse and potentially high-risk populations? Risk adjustment and predictive modeling technology is not only designed to drive pricing but it can also be used to optimize reimbursement, contain costs, measure performance and – most importantly – implement targeted population health-management initiatives.
Similarly to the process taken by the Massachusetts Health Connector, private payers can transform disparate data sources – including diagnosis, eligibility and utilization – and assess the risk, likelihood of adverse events and future cost of individuals, cohorts and populations. Beyond risk assessment and cost prediction, payers can also utilize this valuable information to improve the quality of care provided to members and drive down spending and unnecessary utilization.
Event-based predictive models and other risk-assessment methodologies designed for medical management enable payers to strategically design, implement and target clinical interventions based on near-term predicted costs, disease factors impacting the population, as well as potentially avoidable utilization such as hospitalizations, emergency department visits and expensive imaging. Payers can stratify large amounts of difficult-to-measure data to investigate discreet populations with specific conditions in order to distinguish patient needs and implement the most impactful clinical interventions.
Another factor to consider in the health management of these new beneficiaries is that a sub-set of this group could periodically move between private coverage and public program eligibility. Since Medicaid and exchange eligibility will be based on income, changes in those guidelines or changes in the financial status of an individual could spark a shift. MCOs can utilize advanced risk adjustment and predictive modeling to assess the risk of newly eligible members using less than one year of historical data.
What’s up, doc? Engaging providers with predictive modeling technologies
Managing the health and wellness of Medicaid and exchange patients in this new healthcare landscape will require collaboration between MCOs and service providers. Supporting medical groups, hospitals and primary care physicians with predictive analytics on their patient populations can enable proactive care management initiatives at the point of care. Understanding which patients are likely to be hospitalized, end up in the emergency room or be high cost in the near future will enable providers to intervene early and potentially prevent avoidable utilization and reduce associated costs.
Besides near-term cost savings, early interventions at the point of care can also improve the long-term health status of a population and strengthen relationships between doctors and patients.
But predictive models are not just designed for cost prediction and medical management. MCOs and other private payers can use advanced methodologies to measure and monitor network performance and incent providers to collaborate in the cost-effective care delivery process. Risk-adjustment models can be used to assess the risk of patient populations (based on conditions, demographics and utilization factors) managed by individual doctors in order to level the playing field and objectively compare and benchmark quality and efficiency of care delivered across a network of providers.
Risk-adjusted measurement of network performance can be used by health plans to incent doctors and medical groups with bonus dollars and pay-for-performance programs. Sharing of capitation dollars with point-of-care providers can also go a long way at reducing costs and improving network relations.
Next steps: Risk sharing and collaboration
The future of our health system will be dependent on many things, but the use of risk adjustment and predictive modeling has proved to be essential for states and private payers to establish risk-sharing partnerships that benefit both organizations and patients.
Many things can be learned from the Massachusetts experience. The details of the state’s healthcare reform efforts were recently published by the state’s Blue Cross Blue Shield Foundation (BCBS MA) as part of the organization’s Health Reform Tool Kit Series. To keep up with the changing times, BCBS MA implemented its own risk-sharing contract initiative in 2009 using the same risk-adjustment technology as the Health Connector. The private plan’s Alternative Quality Contract enables local providers to share in the risk, as well as the rewards, of managing the health and wellness of Massachusetts residents.
Navigating the new healthcare landscape will require collaboration between public payers, private health plans and providers. Risk adjustment and predictive models will play a significant role in fostering those partnerships and engaging consumers in the health management process.
About the author
Matt Siegel is VP of market strategy at Verisk Health, a subsidiary of Verisk Analytics. For more on Verisk Health, click here.