Abstract

LLORCA, Javier  and  DELGADO-RODRIGUEZ, Miguel. Survival analysis with competing risks: estimating failure probability. Gac Sanit [online]. 2004, vol.18, n.5, pp. 391-397. ISSN 0213-9111.  http://dx.doi.org/10.1590/S0213-91112004000500009.

Objective: To show the impact of competing risks of death on survival analysis. Method: We provide an example of survival time without chronic rejection after heart transplantation, where death before rejection acts as a competing risk. Using a computer simulation, we compare the Kaplan-Meier estimator and the multiple decrement model. Results: The Kaplan-Meier method overestimated the probability of rejection. Next, we illustrate the use of the multiple decrement model to analyze secondary end points (in our example: death after rejection). Finally, we discuss Kaplan-Meier assumptions and why they fail in the presence of competing risks. Conclusions: Survival analysis should be adjusted for competing risks of death to avoid overestimation of the risk of rejection produced with the Kaplan-Meier method.

Keywords : Survival analysis; Kaplan-Meier; Multiple decrement model; Competing risks; Heart transplantation.