Two-stage estimation to adjust for treatment switching in randomised trials: a simulation study investigating the use of inverse probability weighting instead of re-censoring

Abstract

Background Treatment switching is common in randomised trials of oncology treatments, with control group patients switching onto the experimental treatment during follow-up. This distorts an intention-to-treat comparison of the treatments under investigation. Two-stage estimation (TSE) can be used to estimate counterfactual survival times for patients who switch treatments – that is, survival times that would have been observed in the absence of switching. However, when switchers do not die during the study, counterfactual censoring times are estimated, inducing informative censoring. Re-censoring is usually applied alongside TSE to resolve this problem, but results in lost longer-term information – a major concern if the objective is to estimate long-term treatment effects, as is usually the case in health technology assessment. Inverse probability of censoring weights (IPCW) represents an alternative technique for addressing informative censoring but has not before been combined with TSE. We aim to determine whether combining TSE with IPCW (TSEipcw) represents a valid alternative to re-censoring. Methods We conducted a simulation study to compare TSEipcw to TSE with and without re-censoring. We simulated 48 scenarios where control group patients could switch onto the experimental treatment, with switching affected by prognosis. We investigated various switching proportions, treatment effects, survival function shapes, disease severities and switcher prognoses. We assessed the alternative TSE applications according to their estimation of control group restricted mean survival (RMST) that would have been observed in the absence of switching up to the end of trial follow-up. Results TSEipcw performed well when its weights had a low coefficient of variation, but performed poorly when the coefficient of variation was high. Re-censored analyses usually under-estimated control group RMST, whereas non-re-censored analyses usually produced over-estimates, with bias more serious when the treatment effect was high. In scenarios where TSEipcw performed well, it produced low bias that was often between the two extremes associated with the re-censoring and non-recensoring options. Conclusions Treatment switching adjustment analyses using TSE should be conducted with re-censoring, without re-censoring, and with IPCW to explore the sensitivity in results to these application options. This should allow analysts and decision-makers to better interpret the results of adjustment analyses. Electronic supplementary material The online version of this article (10.1186/s12874-019-0709-9) contains supplementary material, which is available to authorized users.

Analysis approaches to address treatment nonadherence in pragmatic trials with point-treatment settings: a simulation study

“…Fourth, the results in this paper may not be generalizable to other types of outcomes. Some previous studies compared different methods to address treatment nonadherence when the outcome is continuous [ 60 , 61 ] and time-to-event [ 26 , 62 – 64 ]. However, these studies mostly focused on comparing either IV or PP methods with the naive methods, or considered different data structures or treatment strategies (e.g., sustained treatment strategies in longitudinal studies) [ 26 , 64 ].…”

“…Some previous studies compared different methods to address treatment nonadherence when the outcome is continuous [ 60 , 61 ] and time-to-event [ 26 , 62 – 64 ]. However, these studies mostly focused on comparing either IV or PP methods with the naive methods, or considered different data structures or treatment strategies (e.g., sustained treatment strategies in longitudinal studies) [ 26 , 64 ]. Future studies should explore the performance of both IV and PP methods in the point-treatment setting for continuous and time-to-event outcomes, multiple treatment arms, and when effect modifiers are present.…”

Improved two-stage estimation to adjust for treatment switching in randomised trials: g-estimation to address time-dependent confounding

“…In one previous study it was demonstrated that this results in adequate coverage levels, in scenarios where adjustment methods result in low bias. 46 We therefore chose to focus on bias in this study, and are confident that methods that produce low bias would provide adequate standard errors and coverage provided bootstrapping is used.…”

Machine learning to guide the use of adjuvant therapies for breast cancer

“…21,22 This is consistent with previous approaches used to create adjusted counterfactual survival times in cross-over trials. 40 The same procedure was applied to the Cox PH model. The Adjutorium model incorporates four treatments: chemotherapy, hormone therapy, bisphosphonates and trastuzumab.…”