Tag Archives: Anders Larson

What predictive analytics can tell us about key drivers of MSSP results

We recently used machine learning techniques to understand key drivers of Medicare Shared Savings Program (MSSP) financial performance. Of the 190 plus objective accountable care organization (ACO) features reviewed, ACO baseline efficiency proved to be the most important financial performance driver we identified. Another way of putting it is that MSSP rewarded inefficient ACOs more than ACOs that have attained efficiency.

You may be asking, “How did you measure baseline efficiency?” The chart below tells an interesting story.

We analyzed ACO baseline efficiency by reviewing ACO baseline expenditures that were unadjusted, risk-adjusted, and geographic-risk-adjusted. Risk-adjusted per capita expenditures were adjusted to account for each ACO’s average risk score and mix of entitlement categories. Geographic risk-adjusted per capita expenditures were adjusted to account for Medicare reimbursement levels in each ACO’s area.

Below are a few interesting notes:

1. Despite adjusting for risk levels, mix of entitlement categories, and reimbursement levels, there is still significant variation in baseline per capita expenditures. See the third column above for this wide range of variation.
2. Centers for Medicare and Medicaid Services (CMS) has already made MSSP rule changes that balance the rewards between ACOs at different levels of starting efficiencies. Past financial performance in MSSP agreement period 1 may not be a strong indicator of performance in agreement period 2. ACOs should understand how these rule changes affect them.

Beyond baseline efficiency, we found that several other features were strongly associated with gross savings:

1. National fee-for-service (FFS) trends higher than local market trends
2. Location in the Southeast and south central regions
3. Low performance year expenditures for short-term inpatient admissions
4. High baseline per capita expenditures, unadjusted
5. High CMS-hierarchical condition category (HCC) risk scores

However, we also found that these features still explained less than half of the variation in gross savings across ACOs. This may indicate that ACO care management efforts may be accounting for some of the remaining variation.

The full report is posted at Milliman Insight and includes a deeper dive into research conducted by Jill Herbold, Cory Gusland, and myself.

Measuring performance of skilled nursing facilities

The skilled nursing facility (SNF) industry is an important area for Medicare accountable care organizations (ACOs), Medicare Advantage health plans, and other Medicare programs. How can these organizations appropriately benchmark performance to provide efficient healthcare and reduce spending for SNF services?

Milliman’s Jill Herbold and Anders Larson offer some perspective in their report “Performance of skilled nursing facilities for the Medicare population.” The report highlights several utilization and expenditure metrics for measuring SNF performance. It also explores SNF performance levels across the United States and provides a quantitative assessment of the opportunities to reduce spending for SNF services.

Shared savings arrangements and ACOs provide cost savings opportunity

Sponsors of self-funded group health benefits may be able to reduce their healthcare expenditures by entering into a shared savings arrangement with an accountable care organization (ACO). In the latest issue of Milliman’s Benefits Perspectives, actuaries Anders Larson and Paul Houchens highlight some items that plan sponsors should consider regarding such an arrangement. The following is an excerpt from the article.

For plan sponsors determining whether a shared savings arrangement is appropriate, the following are some of the key factors to consider:

Number of plan participants: For plan sponsors with fewer than 2,000 plan employee participants, independently developing a shared savings arrangement with an ACO may be problematic as the plan may experience significant claims volatility from year to year. Additionally, the plan sponsor may not have the necessary leverage in terms of healthcare service volume to garner favorable terms with the ACO. For plan sponsors with limited size, exploring a shared savings arrangement as part of a purchasing coalition or through an insurer may be beneficial; however, the outcome of the shared savings calculation might not be shared directly with individual plan sponsors.

Geographic dispersion: ACOs generally have a localized geographic focus. Therefore, for employers with employees dispersed across the country, having an ACO manage the majority of the employee population may be an impossible task. For such employers, they should evaluate how their third-party administrators are building networks on a regional basis. A benchmarking exercise (discussed in the next section) will allow the plan sponsor to determine if its plan is well managed at a regional level. If the network is built with a focus on high-quality, cost-efficient care, the employer may capture the same financial benefits of a shared savings arrangement. Additionally, to the extent a private exchange could contract with ACOs on a regional or local level, the private exchange may offer purchasing power that could not be created independently by a plan sponsor.

Current healthcare utilization and cost: A plan sponsor that already enjoys partnering with a high-performing provider delivery system may have little financial incentive to deviate from its current arrangement. Employers with predominantly young adult employees also are unlikely to have the same financial savings opportunity from better utilization management as employers with a significant portion of employees with high-risk chronic conditions. Employees with high-risk chronic conditions create a larger variance in potential costs for a plan sponsor, as well as management opportunities for an ACO. As one of the first steps in evaluating whether a shared savings arrangement may be beneficial, plan sponsors should have their healthcare utilization and costs benchmarked relative to expected costs for their participants’ demographics (including population health), plan designs, geographic location, and provider discount level. Such an analysis will identify utilization management opportunities for a shared savings arrangement.

Challenges with measuring savings in shared savings arrangements

Shared savings arrangements attempt to tie provider reimbursement to performance or quality measures and reductions in the healthcare expenditures for an assigned population of patients. The most common form of these arrangements involves networks of providers that form accountable care organizations (ACOs). The practical task of measuring improvements by providers isn’t easy, especially measuring reductions in expenditure levels that are due to actions by providers. Milliman consultants Anders Larson and Jill Herbold provide more perspective in this healthcare reform paper.