The correction involved 2 figures (), but the captions of 3 figures were actually effected (3,4 and 5).

The correct figure-diagram combinations are:
- the plate diagram (graphic with boxes and circles) belongs to the caption "Figure 4. Red-LDA graphical model."
- the coloured word cloud with the word 'breast' prominent belongs to the caption "Figure 3. Topics learnxled by Red-LDA (top) and Vanilla LDA (bottom) on the EHR corpus."
- the text description of the generative algorithm belongs to the caption "Figure 5. Red-LDA generative story."

There is also a typo in the Figure 3 caption title . The word "learnxled" should be "learned".