Skip to main content
. Author manuscript; available in PMC: 2018 May 4.
Published in final edited form as: J Biomed Inform. 2017 Apr 12;70:35–51. doi: 10.1016/j.jbi.2017.04.009

Fig. 2.

Fig. 2

Fig. 2

a–d Base-level data profiles of the four phenotypic models in the order of: microbiology, antibiotic, blood test and urine test, respectively, where training set sizes are illustrated in the background in contrast with the number of unique patients in the foreground.

a Distribution of training set sizes for the microbiology model.

b Distribution of training set sizes for the antibiotic model

c Distribution of training set sizes for the blood-test model.

d Distribution of training set sizes for the urine-test model.