Background: Randomised controlled trials in reproductive medicine are often subject to outcome truncation, where the study outcomes are only defined in a subset of the randomised cohort. Examples include birthweight (measurable only in the subgroup of participants who give birth) and miscarriage (which can only occur in participants who become pregnant). These outcomes are typically analysed by making a comparison between treatment arms within the subgroup (for example, comparing birthweights in the subgroup who gave birth, or miscarriages in the subgroup who became pregnant). However, this approach does not represent a randomised comparison when treatment influences the probability of being observed (i.e. survival). The practical implications of this for the design and interpretation of reproductive trials are unclear however.
Methods: We developed a simulation platform to investigate the implications of outcome truncation for reproductive medicine trials. We used this to perform a simulation study, in which we considered the bias, Type 1 error, coverage, and precision of standard statistical analyses for truncated continuous and binary outcomes. Simulation settings were informed by published assisted reproduction trials.
Results: Increasing treatment effect on the intermediate variable, strength of confounding between the intermediate and outcome variables, and presence of an interaction between treatment and confounder were found to adversely affect performance. However, within parameter ranges we would consider to be more realistic, the adverse effects were generally not drastic. For binary outcomes, the study highlighted that outcome truncation could cause separation in smaller studies, where none or all of the participants in a study arm experience the outcome event. This was found to have severe consequences for inferences.
Conclusion: We have provided a simulation platform that can be used by researchers in the design and interpretation of reproductive medicine trials subject to outcome truncation, and have used this to conduct a simulation study. The study highlights several key factors which trialists in the field should consider carefully to protect against erroneous inferences. Standard analyses of truncated binary outcomes in small studies may be highly biased, and it remains to identify suitable approaches for analysing data in this context.