Skip to main content
. 2019 May 6;2019:515–523.

Figure 3:

Figure 3:

Classifier performance for predicting whether a lab test will be “stable” compared to the previous one, in terms of standard deviation. Performance is shown in AU-ROC and Predictability99 under 5 different definitions of “stability”: within ± 0.1, 0.2, 0.3, 0.4, or 0.5 SD of the previous measurement.