Methods for estimating survival benefits in the presence of treatment crossover: A simulation study (2012)

Treatment crossover occurs when patients randomised to the control group of a clinical trial are permitted to switch onto the experimental treatment at some point during follow-up. It is common in oncology trials for a number of reasons, both practical and ethical, and can cause problems in estimating the true size of the efficacy gain provided by the experimental treatment. An intention to treat (ITT) analysis is likely to provide an underestimate of the “true” survival benefit associated with the new treatment – that is, the benefit that would have been observed had treatment crossover not been allowed.

Simple methods for adjusting for crossover, such as excluding or censoring crossover patients from the analysis, are highly prone to selection bias. More complex methods have been described in the literature, but a full comparison of these across a range of scenarios has not previously been undertaken.