Investigating the causal effects of multiple treatments using longitudinal data: a simulation study

TL;DR

This paper compares five causal inference methods for estimating effects of multiple treatments over time using longitudinal observational data, highlighting their performance through simulations and real data application.

Contribution

It extends five g-methods to handle multiple treatments in longitudinal data and compares their effectiveness via simulation and real-world example.

Findings

Different methods show varying bias and variance in simulations.

Some methods perform better with certain treatment complexities.

Application to UK CF Registry data illustrates practical use.

Abstract

Many clinical questions involve estimating the effects of multiple treatments using observational data. When using longitudinal data, the interest is often in the effect of treatment strategies that involve sustaining treatment over time. This requires causal inference methods appropriate for handling multiple treatments and time-dependent confounding. Robins Generalised methods (g-methods) are a family of methods which can deal with time-dependent confounding and some of these have been extended to situations with multiple treatments, although there are currently no studies comparing different methods in this setting. We show how five g-methods (inverse-probability-of-treatment weighted estimation of marginal structural models, g-formula, g-estimation, censoring and weighting, and a sequential trials approach) can be extended to situations with multiple treatments, compare their performances in a simulation study, and demonstrate their application with an example using data from the UK CF Registry.