Integration of Clinico-Pathological and microRNA Data for Intelligent Breast Cancer Relapse Prediction Systems

This paper investigates the integration of clinicopathological and microRNA data for breast cancer relapse prediction. Clinical and pathological data proved to be relevant in making predictions about cancer disease outcome. The most accurate predictive models can be obtained by using clinico-pathological information together with genomic information. We analyzed the performance of various combinations between twenty classification algorithms and thirteen feature selection methods. The best performer was the regularized regression method Elastic Net, using its built-in feature selection method, on the data set integrating clinico-pathological data with microRNAs. The hybrid signature contains four clinico-pathological features and fifteen microRNAs. Functional analysis of the selected microRNAs showed that they are involved in cancer related processes.