The Target Cohort Approach: An Extension of the Target Trial Framework to Nested Case-Control Studies with Incidence Density Sampling

The target trial framework is a well-known tool for estimating causal effects from observational data. The target trial approach can be used with data from any type of observational study, but it has most often been used to emulate a hypothetical target trial using data from a prospective cohort study.

In this manuscript, we present the target cohort framework for estimating causal effects from case-control studies. The target cohort approach extends the existing target trial framework for estimating causal effects using observational data but has an explicit case-control perspective.

There are clear conceptual links from randomized trials to cohort studies and from cohort studies to case control studies. The target cohort framework uses a nested case control study to emulate a cohort study that has been designed to emulate a hypothetical pragmatic randomized controlled trial. Both target trial and target cohort frameworks require clear specification of eligibility criteria, treatment strategies, treatment assignment (randomization), follow-up period, outcomes of interest, causal contrast, and analysis plan. We demonstrate the target cohort approach using an example of an observational study to estimate the causal effect of semaglutide, a type of GLP-1 medication sold under the brand name Ozempic, on adverse gastrointestinal events.