This software implements the models described in the paper "The dynamics of breast cancer relapse" (Rueda et al, Nature 2019). https://doi.org/10.1038/s41586-019-1007-8 .
Please note that the predictions returned are meant for research purposes only and they should not be used in a clinical setting.
In order to obtain predictions, the user must fill the time of loco-regional relapse in days from surgery (leave as NA if the patient hasn't had this type of relapse), the time of distant relapse from surgery (leave as NA if the patient hasn't had this type of relapse) and the time of prediction in days from diagnosis (it should be equal to the maximum time of relapse or zero for predictions after diagnosis).
Then, a number of covariables can be specified, as age of the patients, tumour grade, tumour size and number of positive lymph nodes.
The user must specify the tumour subtype based on one of the following stratification schemes: either ER status, IHC subtype, Pam50 subtype or Integrative Cluster subtype.
Note that in order to produce predictions faster, this software may use simulations from the multistate model described in Rueda et al.