Skip to main content

Table 1 The confusion matrices show the accuracy of our decision tree on the training (MILE) and test (BCCA) datasets

From: Large-scale gene network analysis reveals the significance of extracellular matrix pathway and homeobox genes in acute myeloid leukemia: an introduction to the Pigengene package and its applications

Dataset MILE (train) BCCA (test)
Disease AML-NK MDS AML-NK MDS
Full tree (155 genes) 191 (95%) 141 (86%) 51 (98%) 20 (91%)
Reduced tree (14 genes) 181 (90%) 137 (84%) 51 (98%) 20 (91%)
Mills et al. [16] 188 (93%) 82 (50%)   
Reference diagnosis 202 164 52 22
  1. The percentages of correctly identified cases with respect to the reference diagnosis are shown in parentheses. Compared to Mills et al., our decision tree is 36% more sensitive to MDS. The sensitivity to AML is comparable in both approaches