The Centers for Medicare & Medicaid Services (CMS) use Hierarchical Condition Categories (HCC) and demographic information to calculate beneficiary risk scores, which predict expected Medicare spending by beneficiaries. CMS-HCC risk scores may be underestimating expected healthcare utilization among rural beneficiaries compared to urban beneficiaries. Incorrect estimation of expected healthcare utilization can lead to important financial losses for providers.

With Medicare claims data, this study examines the relationship between CMS-HCC risk scores and future healthcare utilization among rural and urban beneficiaries. CMS‐HCC risk scores are significantly and positively associated with increased acute inpatient stays, hospital readmissions, inpatient emergency room visits, and hospital outpatient emergency room visits among Medicare beneficiaries.

After controlling for CMS‐HCC risk scores, rural beneficiaries generally had greater healthcare utilization than urban beneficiaries (e.g., more acute inpatient stays, more hospital readmissions, and more hospital outpatient emergency room visits). Overall, the results indicate that CMS-HCC risk scores provide utility in predicting patients that are expected to be more costly. However, the results also suggest that there are systematic differences in the risk adjustment model's predictive capabilities in rural versus urban populations, as rural beneficiaries in our study generally had greater healthcare utilization even after controlling for risk scores. Going forward, policymakers might consider the possibility that Medicare provider payment models using CMS-HCC risks scores may underestimate the costs associated with treatment of rural beneficiaries.