PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 21, 2026BMJ Open0 citationsOpen Access

Integrating healthcare system context to improve risk prediction and assess racial disparities among dual-eligible Medicare–Medicaid beneficiaries: a retrospective cohort study using national fee-for-service claims

SPShama PatelSBSanjay Basu

Key Points

  • This research aims to evaluate the impact of healthcare system context on risk prediction and assess racial disparities among dual-eligible Medicare–Medicaid beneficiaries.
  • Conducted a retrospective cohort analysis using national fee-for-service claims data.
  • Included 3,877,563 dual-eligible beneficiaries enrolled for at least 8 months in 2023.
  • Estimated future Medicare spending and acute care utilization for July–December 2023.
  • Incorporating healthcare context improved prediction model performance from R²=0.454 to 0.615 (p<0.001).
  • Sensitivity for predicting acute care visits increased from 25.0% to 33.8% while maintaining high specificity.
  • Contextual risk assessments revealed differential impacts for racial groups, with Black beneficiaries facing greater risk amplification.

Abstract

Objectives Medicare–Medicaid dual-eligible beneficiaries comprise 97%). System context reduced predicted risk for 86% of beneficiaries (mean −8.8 percentage points), while increasing risk for 14%. Black beneficiaries experienced higher rates of contextual risk amplification (15.8% vs 13.6% White) and showed distinct vulnerability to large practice coordination and workforce composition factors, while Hispanic populations’ risk was primarily associated with geographic access barriers. Conclusions Healthcare delivery context substantially improves prediction of future spending among dual-eligible beneficiaries. These findings suggest risk adjustment incorporating context should account for differential racial impacts.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Patel et al. (2026) studied this question.

synapsesocial.com/papers/69be36086e48c4981c6749dfhttps://doi.org/10.1136/bmjopen-2025-111343
Ask AI
Helpful
Bookmark
Share
View Full Paper