🤖 AI Summary
Existing Area Deprivation Index (ADI) variants over-rely on housing-related variables—particularly home values—leading to distorted deprivation assessments in high-cost regions and obscuring genuine health inequities and cost heterogeneity.
Method: We propose the standardized, balanced ADI (bADI), which mitigates housing-price bias through variable rebalancing and z-score standardization across domains. Leveraging large-scale real-world Medicare data (Fee-for-Service and Medicare Advantage), we employ multivariate modeling and weighted analyses to evaluate bADI’s performance.
Contribution/Results: bADI significantly outperforms conventional ADI in predicting clinical outcomes, life expectancy, healthcare utilization, and expenditures. Critically, it more accurately captures cost stratification patterns aligned with health equity principles, thereby enhancing social risk detection and enabling more equitable resource allocation.
📝 Abstract
Background: As value-based care expands across the U.S. healthcare system, reducing health disparities has become a priority. Social determinants of health (SDoH) indices, like the widely used Area Deprivation Index (ADI), guide efforts to manage patient health and costs. However, the ADI's reliance on housing-related variables (e.g., median home value) may reduce its effectiveness, especially in high-cost regions, by masking inequalities and poor health outcomes. Methods: To overcome these limitations, we developed the balanced ADI (bADI), a new SDoH index that reduces dependence on housing metrics through standardized construction. We evaluated the bADI using data from millions of Medicare Fee-for-Service and Medicare Advantage beneficiaries. Correlation analyses measured its association with clinical outcomes, life expectancy, healthcare use, and cost, and compared results to the ADI. Results: The bADI showed stronger correlations with clinical outcomes and life expectancy than the ADI. It was less influenced by housing costs in expensive regions and more accurately predicted healthcare use and costs. While ADI-based research suggested both the most and least disadvantaged groups had higher healthcare costs, the bADI revealed a more nuanced pattern, showing more accurate cost differences across groups. Conclusions: The bADI offers stronger predictive power for healthcare outcomes and spending, making it a valuable tool for accountable care organizations. By reallocating resources from less to more disadvantaged areas, ACOs could use the bADI to promote equity and cost-effective care within population health initiatives.