Artificial neural networks since the survival Kaplan-Meier function

Nowadays, the statistical applications include modules with advanced technologies for the models' development that allow the simulation of the behaviour of key variables in the organization. The reliability analysis, or survival analysis, is defined as a set of techniques that analyze the elapsed time from the well defined origin up to the occurrence of a previously established event of interest; in turn, an artificial neural network can be defined as a mathematical model whose construction is carried out by means of a process that imitates the functioning of the biological neural networks, and can be used to shape phenomena that involve some response that depends on a combination of factors. This research approaches the survival analysis using artificial intelligence technologies for the purpose of estimating, since a neural network, the survival Kaplan-Meier function. The results demonstrate that the models of artificial neural networks allow the managing of survival data without needing to impose departure assumptions in the mentioned models. Thus, it is evident the potential of the RNA to evaluate the partial information from a censured data set of survival.