Skip to main content
. Author manuscript; available in PMC: 2015 May 19.
Published in final edited form as: Cancer Prev Res (Phila). 2014 Mar 18;7(5):545–555. doi: 10.1158/1940-6207.CAPR-13-0416

Figure 2.

Figure 2

ROC curve comparison for classification of breast cancer patients. The autoantibody responses against seven antigens (i.e. ANGPTL4, DKK1, GAL1, GFRA1, GRN, LRRC15 and MUC1) were added to a logistic regression model that included age, BMI, race and current smoking status. The ROC curves were determined for all subjects (top) and by specific subtypes of breast cancer including ER positive, invasive, maximum tumor dimension > 1 cm, in situ, lymph node involvement and HER-2 amplification (bottom).