Fig. 2.

Elastic net model learnt features for predicting WS status. The blue or red indicates that the surface measures at that region were selected to be discriminative features. The red represents WS individuals with increased value of measures on that region, whereas the blue represents the decreased value of measures among WS individuals. The magnitude of those colors indicates their relative importance for classifying WS and HC. (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)