Estimating Effects of Dynamic Treatment Strategies in Pharmacoepidemiologic Studies with Time-varying Confounding: A Primer

Abstract

Purpose of review: Pharmacoepidemiologists are often interested in estimating the effects of dynamic treatment strategies, where treatments are modified based on patients' evolving characteristics. For such problems, appropriate control of both baseline and time-varying confounders is critical. Conventional methods that control confounding by including time-varying treatments and confounders in an outcome regression model may not have a causal interpretation, even when all baseline and time-varying confounders are measured. This problem occurs when time-varying confounders are, themselves, affected by past treatment. We review alternative analytic approaches that can produce valid inferences in the presence of such confounding. We focus on the parametric g-formula and inverse probability weighting of marginal structural models, two examples of Robins' g-methods.

Recent findings: Unlike standard outcome regression methods, the parametric g-formula and inverse probability weighting of marginal structural models can estimate the effects of dynamic treatment strategies and appropriately control for measured time-varying confounders affected by prior treatment. Few applications of g-methods exist in the pharmacoepidemiology literature, primarily due to the common use of administrative claims data, which typically lack detailed measurements of time-varying information, and the limited availability of or familiarity with tools to help perform the relatively complex analysis. These barriers may be overcome with the increasing availability of data sources containing more detailed time-varying information and more accessible learning tools and software.

Summary: With appropriate data and study design, g-methods can improve our ability to make causal inferences on dynamic treatment strategies from observational data in pharmacoepidemiology.

Keywords: Causal Inference; Dynamic Treatment Strategies; G-methods; Pharmacoepidemiology; Time-varying Confounding.

Figure 1. A simplified graphic depiction of an observational pharmacoepidemiologic study with measured time-varying confounders affected by past treatment

The schematic represents a screenshot of two observational intervals during follow-up.

Figure 2. A graphical depiction of bias due to conditioning on a confounder for future treatment effects that is also affected by past treatment

Standard regression methods include time-dependent anemia parameters m in the model, resulting in a biased estimate of the causal effect of iron treatment m − 1 on mortality due to an induced association with unmeasured hemochromatosis.