Skip to main content
. Author manuscript; available in PMC: 2020 Sep 1.
Published in final edited form as: IEEE J Biomed Health Inform. 2018 Dec 28;23(5):2052–2062. doi: 10.1109/JBHI.2018.2890084

Fig. 1.

Fig. 1.

Overview for each case control experiment. In step 1, the EMR phenotypes associated with disease D, Psig are learnt from dataset E. In Step 2, EMR context signature vectors, XEMR are calculated from Psig and XRad is calculated from imaging. XRE, XRad, and XEMR are used to train an elastic net classifier and ROC curves are computed.