HOSPITAL QUALITY RISK STANDARDIZATION VIA APPROXIMATE BALANCING WEIGHTS

• 成果类型: Article
• 署名作者: Keele, Luke J.; Ben-Michael, Eli; Feller, Avi; Kelz, Rachel; Miratrix, Luke
• 署名单位: University of Pennsylvania; Harvard University; Harvard University; University of California System; University of California Berkeley; Harvard University
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/22-AOAS1629
• 发表日期: 2023
• 页码: 901-928
• 关键词: Causal Inference; propensity score; league tables; models; BIAS; benchmarking; estimators; adjustment; template; rates

摘要

Comparing outcomes across hospitals, often to identify underperform-ing hospitals, is a critical task in health services research. However, naive comparisons of average outcomes, such as surgery complication rates, can be misleading because hospital case mixes differ-a hospital's overall com-plication rate may be lower simply because the hospital serves a healthier population overall. In this paper we develop a method of direct standardiza-tion where we reweight each hospital patient population to be representative of the overall population and then compare the weighted averages across hos-pitals. Adapting methods from survey sampling and causal inference, we find weights that directly control for imbalance between the hospital patient mix and the target population, even across many patient attributes. Critically, these balancing weights can also be tuned to preserve sample size for more pre-cise estimates. We also derive principled measures of statistical uncertainty and use outcome modeling and Bayesian shrinkage to increase precision and account for variation in hospital size. We demonstrate these methods using claims data from Pennsylvania, Florida, and New York, estimating standard-ized hospital complication rates for general surgery patients. We conclude with a discussion of how to detect low performing hospitals.