In longitudinal studies of disease, patients
can experience several events across a follow-up period. Analysis of such
studies can be successfully performed by multi-state models (Andersen et al.
1993; Meira-Machado et al. 2009). In the multi-state framework, one major goal
is to study the relationship between the different covariates and disease
evolution. Other issues of interest include the estimation of transition
probabilities and survival rates. Despite its potential, multi-state modeling
is not used by practitioners as frequently as other survival analysis
techniques. We believe that lack of knowledge of available software and
non-implementation of the new methodologies in user-friendly software may be
responsible for this lack of popularity. The aim of this paper is, therefore, to
report on the existing software for implementing these models. In this
presentation, we will focus our attention to the available R packages for the
analysis of multi-state survival data. All packages will be illustrated using
data from a colon cancer study. |