The most basic problem considered in Machine Learning is the supervised binary data classification, where one is given a training sample – a random sample (xi, yi), i = 1, ..., ` of examples – attribute vectors xi equipped with labels yi = ±1 – drawn from unknown distribution P , and the goal is to build, based on this sample, a classifier – a function f(x) taking values ±1 such that the genera...

We have developed a prognostic index model for survival data based on an ensemble of artificial neural networks that optimizes directly on the concordance index. Approximations of the c-index are avoided with the use of a genetic algorithm, which does not require gradient information. The model is compared with Cox proportional hazards (COX) and three support vector machine (SVM) models by Van ...