Machine Learning for High-dimensional Proxy Covariate Adjustment in Healthcare Database Studies: An Overview of the Current Literature

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 presentation, the presenter discussed current approaches and recent advancements for high-dimensional proxy confounder adjustment in healthcare database studies. The presentation focused on 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. The presenter discussed challenges and avenues of future development within each area.