Breast Cancer Prognosis via Gaussian Mixture Regression

This paper compares the performance of classification and regression trees (CART), multivariate adaptive regression splines (MARS), and a Gaussian mixture regressor (GMR) method in predicting breast cancer recurrence time in patients that have undergone cancer excision. It is shown that the GMR-based algorithm demonstrates an improved performance compared to CART and MARS. Moreover, GMR performance is comparable to that of a baseline predictor with the advantage of performing automatic feature selection and model optimization. Keywords—Prognosis prediction, breast cancer, time-to-recur, automatic feature selection, Gaussian mixture regressor, CART, MARS.

• Type: Conference
• Year: 2006
• Where: CCECE
• Authors: Tiago H. Falk, Hagit Shatkay, Wai-Yip Chan
• Keywords: Automatic Feature Selection, CCECE 2006, Electrical And Computer Engineering, Gaussian Mixture Regressor, Multivariate Adaptive Regression Splines