Predictive Analytics - PrecisionBI
Lowering Costs and Improving Patient Care
GlobalHealth’s Comprehensive 10% MLR Reduction Program
GlobalHealth is an HMO offering Medicare Advantage plans for seniors and retired government employees and also covers a large percentage of Oklahoma’s state and federal government employees, including educators. Since 2014, GlobalHealth has utilized prescriptive and predictive health analytics as the basis for a proactive outreach program. The outreach program was established to find the members whose health was most likely to change for the worse in the next 12 months and prevent catastrophic health events. Today, GlobalHealth can successfully predict nearly 70 percent of its hospital admissions, has achieved a 22 percent reduction in ER admissions, a 20 percent reduction in PMPM costs, and a 10 percent reduction in overall healthcare costs—a projected annual cost savings of $25 million dollars.
During the second quarter of 2013, GlobalHealth began examining its options for building a predictive analytics program. One of GlobalHealth’s priorities was finding a clinical analytics partner with a solution that could seamlessly integrate and evolve with their existing IT structure. After an extensive search of potential providers, VitreosHealth was selected as the predictive health analytics vendor because of its strong data architecture, standards-compliant interface capabilities, and a proven track record of delivering actionable insights from big data analysis.
A Novel Approach to Managing Risk
“Most health plans only look at the members who have generated the highest costs historically and focus on them,” said Scott Vaughn, CEO of GlobalHealth. “Whereas the predictive analytics solution we selected from VitreosHealth looks at those members and also identifies members who haven’t generated high costs in the last 12 months but are at risk of experiencing serious health complications in the near future.”
“We call that ‘insights as a service,’” said David Thompson, COO of GlobalHealth. “VitreosHealth sorts through the data, says this is what it means, and these are the actions you can take to see results.” Working together, VitreosHealth ran a regression analysis on member data to identify care gaps while GlobalHealth provided a crash course on the Oklahoma healthcare scene and the care gaps encountered through the care management program.
Beyond Traditional Utilization Analytics
Traditionally, most organizations only use historical utilization (spend) to understand population risk and cost differences with respect to variations in care, non-compliance to evidence-based care guidelines, and opportunities for care management. This is a single dimensional risk stratification. GlobalHealth was able to gain a more holistic view of their population’s state of health (SOH) using VitreosHealth’s IaaS Platform. GlobalHealth now employs a multi-dimensional risk stratification approach using predictive risks and predictive health analytics (disease-specific risks, composite risk, utilization risk) and outcomes (hospitalizations, ER visits, PMPM) to understand the SOH at any point of time.
Using the SOH quadrant approach to understand the changes in the state of health risk from year to year, GlobalHealth was then able to determine what was driving changes in costs and risks. This approach helped them to identify each percentage of costs and where they were coming from:
- New members
- Patient movement from a “Hidden” to “Critical” state
- Patient movement from a “Healthy/Unknown” to “High Utilizers” state
- Per Unit Cost changes, etc.
- Impact of care management programs by understanding these changes in populations from “Critical” and “High Utilizers” to the left of the quadrant
By understanding these “mover populations”, GlobalHealth was able to identify the cohorts of a population to target for care management programs and design the right care management programs supported with the optimal resources. In a relatively short amount of time, GlobalHealth launched its outreach program and has experienced success. Member’s lives have been positively impacted, and millions of dollars have been saved. Some of the reasons for this program’s success are unique to GlobalHealth, it’s predictive health analytics, and its corporate culture while others are more universal and could pertain to a variety of payers or providers. What is clear though is any payer or provider interested in an effective outreach program could certainly find useful lessons from GlobalHealth’s example.
GlobalHealth intends to continue to evolve their clinical analysis and outreach program. Plans include bringing in more data sources—including clinic, laboratory, and imaging center medical records—to further refine the analysis. The overall goal is to continue to reduce medical costs by improving the health and wellness of their members. “There’s a lot of waste in health-care,” said Thompson. “That’s why we made achieving a negative trend our objective. As we lower premiums and improve benefits, we believe we’ll reach a negative 10 percent trend on this initiative and then continue the cycle.”
“We have had a 10-fold return on our investment and the value we’ve gotten out of it in terms of reduced healthcare costs,” said Vaughn. “This year, we have an initiative in place where we plan to reduce healthcare costs by 10 percent. That would be about 25 million dollars in savings that we can then pass on to the members, use to improve healthcare benefits, or reinvest to help us deliver better service.”
David Thompson, VP | COO, GlobalHealth
On working with VitreosHealth