By Jay Reddy, BS, MBA
That’s how it feels when you are working very hard and investing millions on population care management programs and the results don’t meet your expectations! Some population care management programs are successful while some are not delivering the expected results. The case study results we are going to share will show you why there are “winners” and “losers” in effective population management programs. We hope that the results we share are not only going to be an “eye-opener” but a “game-changer” as the healthcare providers take on risk for population health.
VitreosHealth® (formerly PSCI) has completed multiple population State-of-Health (SOH) risk analyses for Medicare ACOs and Medicare Advantage programs harvesting their EMR, demographics and claims data. Centers for Medicare and Medicaid services (CMS) are the first payers in the industry who are sharing claims data of their patient population with providers. We hope that rest of the private payer market follows the lead, considering how it can change the economics of the provider-driven population management programs.
Our vision is that the case study below will compel all private payers to do so if they want to be on the fore-front of healthcare transformation. The results we are sharing are a representative sample of what we are seeing as a pattern across multiple Medicare ACO customers.
A leading Physician-led ACO used VitreosHealth® SaaS to perform the population State-of-Health (SOH) analyses by running the predictive risk analytics which leveraged both EMR and claims data. Our predictive models helped identify the risky patients, the underlying risk factors and help design tailor-made care management programs for the high risk cohort of population. VitreosHealth® uses a closed-loop provider-driven population process as shown in Figure 1.
VitreosHealth® received historical claims and EMR data for 3-years (2011 – 2013) from the ACO for the Medicare population cohort. VitreosHealth® cleansed the data and ran the predictive risk analytics algorithms to identify the clinical risk scores for each patient. The SOH clinical risk score is a composite of the individual disease risk scores and is calculated from EMR (clinical) data that includes vitals and lab results. We then plotted the members’ SOH clinical risk on y-axis and the per-member-per-month (PMPM) utilization costs on the x-axis.
The top right quadrant (“Critical”) is the cohort of high cost, high clinical risk score patients. These patients are clinically risky based on the current state-of-health and are also high utilizers today and account for about 42% of the total population. The lower right quadrant represents the cohort that are high utilizers today even though they are relatively at a lower clinical risk based on their state-of-health analysis using EMR data. Typically, they are emergency room (ER) and medication ‘abusers’ and are either hypochondriacs, and/or may have socio-economic and access-to-care problems.
Both these segments are typically identified through claims analysis in most population and disease management programs and become ‘high risk candidates’ for care management programs. However, there is a far more important category of patients which is the upper left (“Hidden Opportunity”). This cohort is compromised of members that are clinically at a higher risk today based on EMR data analysis, but have historically not been high utilizers, hence they are not identified by claims based risk scores that are biased towards historical utilization costs. In most cases, they account for only 10% of the total spent and have very low PMPM costs, so most of these members are ignored by CM programs.
Representative results for 2011 are shown in Figure 2.
VitreosHealth® performed similar analysis for Year 2011 1Q and Year 2012 1Q to understand the movement of the population over the 12 month period. Figure 3 shows the movement of the population from “Hidden Category” to “Critical” category and “The Unknowns/Relatively Healthy” to “High Utilizers” during this period.
These similar findings which we are seeing across the ACO populations are “transformational” for the care management strategy development and execution. Most of the current care management programs (See Figure 4) are focused on the “Critical” and “High Utilizers” categories which make up 70% of last year costs. Our analysis points out, 44% of the costs in the following year were coming from 17% of “Hidden” and “Unknown” cohort populations migration into the “Critical” and “High Uilizer” categories. This means that nearly 40% of the costs by the end of the year were contributed by members who were not being identified by the current care management programs at the beginning of the year and hence not being cared for proactively.
So your clinical teams are working very hard, investing millions on the care management programs that are not focused on the right members.! If you don’t put the right passengers on the right bus with no Future Visibility, the population management journey will have a destination with undesired outcomes.
Do you know who these 17% of population in the “Hidden” category and “Unknown” category in 2013 that will be migrating to the right by 2014 and making up 44% of new costs? What are their risk drivers and what care management programs to design for them?
Are you feeling like you have been running the marathon with one-leg tied?
This is why ACOs cannot drive their population management programs using claims-based predictive risk analytics and get the desired results. For superior results, ACOs need to use Next Generation Population Predictive Models that leverage multiple data sources – EMR, claims and demographics to help identify the high risk patients and design tailor-made care management programs.