This is a collection of simple R functions that were used for computing the time-dependant ROC curve for a prognostic marker from aggregated data (survival probabilities in strata of the marker) and from several studies.

Microarray data can be used to identify prognostic signatures based on time-to-event data. The analysis of microarrays is often associated with overfitting and many papers have dealt with this issue. However, little attention has been paid to incomplete time-to-event data (truncated and censored follow-up). We have adapted the 0.632+ bootstrap estimator for the evaluation of time-dependent ROC curves. The interpration of ROC-based results is well-established among the scientific and medical comunity. Moreover, the results do not depend on the incidence of the event, as opposed to many other prognostic statistics. Here, we have validated this methodology by similutions. We have illustrated its utility by analyzing a data set of diffuse large-B-cell lymphoma patients. Our results demonstrate the well-adapted properties of the 0.632+ ROC-based approach to evaluate the true prognostic capacity of a microarray-based signature. This method has been implemented in the R package ROCt632.

 

It is a clinical composite score at 1 year, called the Kidney Transplant Failure Score (KTFS). The KTFS takes into account a series of well-accepted pre- and post-transplant risk factors of graft loss. It includes 8 parameter (blood creatinine values at 3 and 12 months, proteinuria at 12 months, number of previous transplantations, recipient age and gender, last donor creatinine level before kidney retrieval and incidence of acute rejection in the first year). The score itself is calculated using the traditional multivariate Cox model combined with a new statistical approach called the ‘time-dependent receiver–operator characteristic (ROC) curves’.