Machine learning for improving high‐dimensional proxy confounder adjustment in healthcare database studies: An overview of the current literature

Abstract

Purpose Supplementing investigator‐specified variables with large numbers of empirically identified features that collectively serve as ‘proxies’ for unspecified or unmeasured factors can often improve confounding control in studies utilizing administrative healthcare databases. Consequently, there has been a recent focus on the development of data‐driven methods for high‐dimensional proxy confounder adjustment in pharmacoepidemiologic research. In this paper, we survey current approaches and recent advancements for high‐dimensional proxy confounder adjustment in healthcare database studies. Methods We discuss considerations underpinning three areas for high‐dimensional proxy confounder adjustment: (1) feature generation—transforming raw data into covariates (or features) to be used for proxy adjustment; (2) covariate prioritization, selection, and adjustment; and (3) diagnostic assessment. We discuss challenges and avenues of future development within each area. Results There is a large literature on methods for high‐dimensional confounder prioritization/selection, but relatively little has been written on best practices for feature generation and diagnostic assessment. Consequently, these areas have particular limitations and challenges. Conclusions There is a growing body of evidence showing that machine‐learning algorithms for high‐dimensional proxy‐confounder adjustment can supplement investigator‐specified variables to improve confounding control compared to adjustment based on investigator‐specified variables alone. However, more research is needed on best practices for feature generation and diagnostic assessment when applying methods for high‐dimensional proxy confounder adjustment in pharmacoepidemiologic studies.

Combining Super Learner with high‐dimensional propensity score to improve confounding adjustment: A real‐world application in chronic lymphocytic leukemia

“…While logistic regression is the traditional approach for estimating the propensity score, least absolute shrinkage and selection operator (LASSO) and other regularized regression tools have been recommended for hdPS 24,25 . Additionally, machine learning models like random forest and neural networks have shown promising results in prior studies utilizing alternative models for estimating the propensity score 25–28 . Future research should explore the incorporation of regularized regression and machine learning models, in addition to logistic regression, in the SL‐hdPS ensemble.…”

“…24,25 Additionally, machine learning models like random forest and neural networks have shown promising results in prior studies utilizing alternative models for estimating the propensity score. [25][26][27][28] Future research should explore the incorporation of regularized regression and machine learning models, in addition to logistic regression, in the SL-hdPS ensemble. This is particularly pertinent given SL's ability to incorporate a wide variety of models.…”