Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 1 of 1
Full-Text Articles in Physical Sciences and Mathematics
Combining Biomarkers Linearly And Nonlinearly For Classification Using The Area Under The Roc Curve, Youyi Fong, Shuxin Yin, Ying Huang
Combining Biomarkers Linearly And Nonlinearly For Classification Using The Area Under The Roc Curve, Youyi Fong, Shuxin Yin, Ying Huang
Youyi Fong
In biomedical studies, it is often of interest to classify/predict a subject's disease status based on some biomarker measurements. Two approaches have received a lot of attention in the biostatistical literature for finding optimal biomarker combinations using a training data. The likelihood approach maximizes logistic regression model likelihood, while the AUC (area under the receiver operating characteristic curve) approach maximizes the empirical AUC based on biomarker combination. The two approaches are complementary to each other in practice. Existing methods in the AUC approach either approximate the empirical AUC by a smooth function or replace it with a convex upper bound. …