Artificial neural network (ANN) theory is emerging as an alternative to conventional statistical methods in modeling nonlinear\nfunctions.The popular Cox proportional hazard model falls short in modeling survival data with nonlinear behaviors. ANN is a\ngood alternative to the Cox PHas the proportionality of the hazard assumption andmodel relaxations are not required. In addition,\nANN possesses a powerful capability of handling complex nonlinear relations within the risk factors associated with survival time.\nIn this study,we present a comprehensive comparison of two different approaches of utilizingANNinmodeling smooth conditional\nhazard probability function.We use real melanoma cancer data to illustrate the usefulness of the proposedANNmethods.We report\nsome significant results in comparing the survival time of male and female melanoma patients.
Loading....