Outcome-Dependent Sampling in Cluster-Correlated Data Settings with Application to Hospital Profiling

Abstract

Summary Hospital readmission is a key marker of quality of healthcare and an important policy measure, used by the Centers for Medicare and Medicaid Services to determine, in part, reimbursement rates. Currently, analyses of readmissions are based on a logistic–normal generalized linear mixed model that permits estimation of hospital‐specific measures while adjusting for case mix differences. Recent moves to identify and address healthcare disparities call for expanding case mix adjustment to include measures of socio‐economic status while minimizing additional burden to hospitals associated with collecting data on such measures. Towards resolving this dilemma, we propose that detailed socio‐economic data be collected on a subsample of patients via an outcome‐dependent sampling scheme, specifically the cluster‐stratified case–control design. Estimation and inference, for both the fixed and the random‐effects components, are performed via pseudo‐maximum‐likelihood wherein inverse probability weights are incorporated in the usual integrated likelihood to account for the design. In comprehensive simulations, cluster‐stratified case–control sampling proves to be an efficient design whenever interest lies in fixed or random effects of a generalized linear mixed model and covariates are unobserved or expensive to collect. The methods are motivated by and illustrated with an analysis of N = 889661 Medicare beneficiaries hospitalized between 2011 and 2013 with congestive heart failure at one of K = 3116 hospitals. Results highlight that the framework proposed provides a means of mitigating disparities in terms of which hospitals are indicated as being poor performers, relative to a naive analysis that fails to adjust for missing case mix variables.

On The Interplay between Exposure Misclassification and Informative Cluster Size

“…(2018), Haneuse and Rivera‐Rodriguez (2018) and McGee et al . (2020), among others), to our knowledge none have investigated such designs in the presence of informative cluster size—let alone designs based directly on cluster size that is informative. We hope to explore these and related design considerations in future research.…”

Improving large‐scale estimation and inference for profiling health care providers

“…Current approaches to profiling providers typically relate the outcome of interest to risk factors using generalized linear models (GLMs) with fixed [12][13][14][15] or random provider effects. 2,[16][17][18][19][20] The fixed effects approach shall be our primary focus here, since it has been used by CMS in profiling dialysis facilities, and has been recognized as less affected by shrinkage estimation than the random effects approach in handling the confounding of patient-level risk factors with provider-level effects when identifying outlying providers. 13,14,21,22 Despite the estimation advantage, using fixed effects models poses a computational challenge to large-scale profiling applications: existing GLM-oriented algorithms such as Newton-Raphson and Fisher scoring 23 developed for general-purpose model fitting cannot fulfill the computational task as the number of providers escalates along with the sample size (eg, 7232 dialysis facilities with 757 086 hospital discharges in our application of ED visits).…”

“…Current approaches to profiling providers typically relate the outcome of interest to risk factors using generalized linear models (GLMs) with fixed 12‐15 or random provider effects 2,16‐20 . The fixed effects approach shall be our primary focus here, since it has been used by CMS in profiling dialysis facilities, and has been recognized as less affected by shrinkage estimation than the random effects approach in handling the confounding of patient‐level risk factors with provider‐level effects when identifying outlying providers 13,14,21,22 …”

Analysis of hospital readmissions with competing risks

“…Current modeling frameworks treat UHR as a binary outcome and use logistic regression with fixed or random facility effects. [9][10][11][12][13][14][15] These analyses are routinely used by CMS in calculating readmission measures for hospital or dialysis facility evaluation. 16,17 In practice, however, a patient may experience a competing event, such as death, prior to a UHR during the follow-up.…”

“…Current modeling frameworks treat UHR as a binary outcome and use logistic regression with fixed or random facility effects. 9–15 These analyses are routinely used by CMS in calculating readmission measures for hospital or dialysis facility evaluation. 16,17…”