Abstract
SummaryIn population-based cancer studies, net survival is a crucial measure for population comparison purposes. However, alternative measures, namely the crude probability of death (CPr) and the number of life years lost (LYL) due to death according to different causes, are useful as complementary measures for reflecting different dimensions in terms of prognosis, treatment choice, or development of a control strategy. When the cause of death (COD) information is available, both measures can be estimated in competing risks setting using either cause-specific or subdistribution hazard regression models or with the pseudo-observation approach through direct modeling. We extended the pseudo-observation approach in order to model the CPr and the LYL due to different causes when information on COD is unavailable or unreliable (i.e., in relative survival setting). In a simulation study, we assessed the performance of the proposed approach in estimating regression parameters and examined models with different link functions that can provide an easier interpretation of the parameters. We showed that the pseudo-observation approach performs well for both measures and we illustrated their use on cervical cancer data from the England population-based cancer registry. A tutorial showing how to implement the method in R software is also provided.
Highlights
When aiming to describe the survival experience of a group of individuals, estimating the overall survival is usually of primary interest
The scope of this paper is to present a way of modelling directly the crude probability of death (CPr) and life years lost (LYL) due to the disease of interest and other causes in relative survival setting according to some covariates of interest
People who were more deprived had an increased number of LYL compared to people who were less deprived in the first 5 years, with those in the most deprived group losing around 0.188 additional years due to cancer compared to the least deprived. Alternative survival indicators such as CPr and LYL attributed to different causes can prove very useful when communicating survival statistics
Summary
When aiming to describe the survival experience of a group of individuals, estimating the overall survival is usually of primary interest. Competing risks methods aim to identify covariates which affect the rate at which specific events occur, and the probability of occurrence of a specific event over time (Austin and Fine, 2017). To perform a competing risks analysis with two events, say cancer death and death from other causes, we often rely on the cause of death (COD) information attributed to each individual, assuming that this is available and reliable. Namely cause-specific and subdistribution hazard, may be used. Unlike cause-specific hazard, subdistribution hazard is useful for estimating covariate effects on the event-specific probability since it “measures the effect of the covariate that can be explained either because there is a direct effect of making the http://biostatistics.oupjournals.com/
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have