Individual and Collective Prognostic Prediction

Abstract

The prediction of survival time or recurrence time is an important learning problem in medical domains. The Recurrence Surface Approximation (RSA) method is a natural, effective method for predicting recurrence times using censored input data. This paper introduces the Survival Curve RSA (SC-RSA), an extension to the RSA approach which produces accurate predicted rates of recurrence, while maintaining accuracy on individual predicted recurrence times. The method is applied to the problem of breast cancer recurrence using two different datasets