Fitting cure models using pseudo-observations approaches with the R package pseudoCure

Abstract In survival analysis, it is traditionally assumed that all individuals are susceptible to the event of interest given sufficient time, a premise supported by well-established statistical software. However, scenarios exist where a considerable subset of individuals may never experience the event, highlighting the need for more sophisticated models. To address this, cure rate models have been developed, which acknowledge a “cured” subpopulation inherently nonsusceptible to the event. Existing methods for these analyses can be complex and computationally demanding. In response, the pseudoCure package (Chiou et al. in pseudoCure: a pseudoobservations approach for analyzing survival data with a cure fraction, 2024) implements an innovative solution by utilizing the pseudo-observations approach, as proposed by Su et al. (Stat Methods Med Res 31:2037–2053, 2022), offering a computationally efficient alternative. This package not only provides robust estimations but also enhances the application of generalized estimating equations in specialized cases, providing an invaluable tool in statistical practices. We demonstrate the efficacy of this package in this paper through examples to highlighting its substantial contributions to the field of survival analysis.