Fig 1.
An example population decision tree and a personalized decision path.
Panel (a) gives the names of the 21 variables and panel (b) gives their values for a test (current) patient whose outcome we want to predict. Panel (c) shows a population decision tree (derived by CART) and the path used for performing inference, and panel (d) shows a personalized decision path (derived by the DP-BAY method that is described later) for the patient in (b).
Table 1.
Brief descriptions of the datasets.
Fig 2.
Pseudocode for the DP-BAY method.
Fig 3.
Pseudocode for the DP-AUC method.
Table 2.
AUCs for the datasets and outcomes shown in Table 1.
Table 3.
Two-sided paired-samples t test comparing the pairwise performance of the four methods on AUC.
Table 4.
BS and BSS for the datasets and outcomes shown in Table 1.
Table 5.
Two-sided paired-samples t test comparing the pairwise performance of the four methods on BSS.
Table 6.
Proportion of test individuals for which the decision-path model is different from the path in CART model.