Table 5 The characteristic of ALL data
From: Using random forest for reliable classification and cost-sensitive learning for medical diagnosis
Group (Class) | Size of training set | Size of testing set |
|---|---|---|
(1)BCR-ABL | 9 | 6 |
(2)E2A-PBX1 | 18 | 9 |
(3)Hyperdiploid>50 | 42 | 22 |
(4)MLL | 14 | 6 |
(5)T-ALL | 28 | 15 |
(6)TEL-AML1 | 52 | 27 |
(7)Others | 52 | 27 |
Total | 215 | 112 |