Program Background

Each year the Centers for Medicare & Medicaid Services (CMS) calculates a capitated payment, on a monthly basis, for each Medicare beneficiary enrolled in a Medicare Advantage (MA) contract based on diagnosis data previously submitted by MA Organizations to CMS. The diagnosis data and beneficiary demographics are input into the CMS-Hierarchical Condition Category (CMS-HCC) risk adjustment model. This model provides additive relative factors that are used to determine risk scores and calculate risk-adjusted payments to MA Organizations for their enrollees. 

Inaccurate or incomplete diagnosis data may lead CMS to disburse overpayments or underpayments to MA Organizations. CMS conducts an annual Part C Improper Payment Measure (IPM) activity to estimate the improper payments for the Medicare Part C program due to unsubstantiated risk adjustment data. 

Part C IPM activities are conducted each year for a sample of Medicare Part C enrollees. After defining the eligible population, a representative sample of beneficiaries from risk adjustment eligible contracts are selected for medical record review. MA Organizations submit medical record documentation to substantiate the sampled beneficiaries’ CMS-HCCs that were used to determine the amounts CMS paid to the MA Organizations for that year. Certified coders code the medical records and the findings are used to recalculate risk scores for each sampled beneficiary. The difference between the original payment risk scores and the recalculated risk scores is termed Risk Adjustment Error. Validation results from the sample are extrapolated to the broader Part C population to produce payment error estimates that meet the Payment Integrity Information Act (PIIA) of 2019 requirements for the payment year. 

Sampling Details

CMS selects two distinct samples each year:

• Non-ESRD Sample: A stratified random sample of 930 beneficiaries with a risk-adjusted payment in the applicable calendar year (e.g., CY 2023 for FY 2025) who did not have end-stage renal disease (ESRD) status as of January. This group is divided into low-, medium-, and high-risk score strata, and a representative sample is drawn from each.
• ESRD Sample: To reflect expanded enrollment options under the 21st Century Cures Act, CMS also selects a simple random sample of individuals who had ESRD status as of January. This forms a separate group and ensures appropriate representation of ESRD beneficiaries.

For the calendar year 2023 Part C IPM sample, both the non-ESRD and ESRD cohorts consist of beneficiaries who were enrolled in contracts active in January of the year for which risk adjustment payments were made. CMS also includes enrollees who received hospice care in the eligible sampling frame. The data collection period spans January 1 through December 31 of the previous year. Note that enrollee sampling criteria are subject to modification as changes in MA payment policy occur.