Breast Cancer Prognosis via Gaussian Mixture Regression

Author

Falk, Tiago H. ; Shatkay, Hagit ; Chan, Wai-Yip

Author_Institution

Dept. of Electr. & Comput. Eng., Queen´´s Univ.

fYear

2006

fDate

38838

Firstpage

987

Lastpage

990

Abstract

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

Gaussian processes; cancer; medical diagnostic computing; pattern classification; regression analysis; splines (mathematics); trees (mathematics); Gaussian mixture regression; automatic feature selection; breast cancer prognosis; classification-regression trees; model optimization; multivariate adaptive regression splines; Breast cancer; Breast neoplasms; Classification tree analysis; Electronic mail; Impurities; Lymph nodes; Machine learning algorithms; Mars; Oncological surgery; Regression tree analysis; CART; Gaussian mixture regressor; MARS; Prognosis prediction; automatic feature selection; breast cancer; time-to-recur;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering, 2006. CCECE '06. Canadian Conference on

Conference_Location

Ottawa, Ont.

Print_ISBN

1-4244-0038-4

Electronic_ISBN

1-4244-0038-4

Type

conf

DOI

10.1109/CCECE.2006.277570

Filename

4054924