Skip to main content
. 2010 Apr 20;28(15):2529–2537. doi: 10.1200/JCO.2009.23.4732

Table 3.

Independent Testing Set of Acute Leukemias

GS/Call Class Prediction
Average No. of IDC As a Result of Ties of Majority Votes Total No. of Specimens in Every Class CR Sensitivity for Called Specimens Specificity for Called Specimens
C1 C2 C3 C4 C5 C6 C7 C8 C9 C10 C11 C12 C13 C14
C1/GS 4* 1 5 0.800 1.000 0.999
C2/GS 23* 0 23 1.000 1.000 0.998
C3/GS 53* 8 1 0 62 1.000 0.855 0.995
C4/GS 75* 1 1 1 1 79 0.987 0.962 0.992
C5/GS 59* 5 0 64 1.000 0.922 0.995
C6/GS 10* 0 10 1.000 1.000 0.997
C7/GS 22* 12 1 35 0.971 0.647 0.989
C8/GS 1 1 2 2 2 7 141* 2 158 0.987 0.904 0.950
C9/GS 16* 0 16 1.000 1.000 1.000
C10/GS 19* 1 0 20 1.000 0.950 0.998
C11/GS 20* 0 20 1.000 1.000 1.000
C12/GS 1 15* 1 0 17 1.000 0.882 1.000
C13/GS 1 3 1 148* 1 6 160 0.963 0.961 0.985
C14/GS 1 4 17* 2 24 0.917 0.773 0.998

NOTE. Classification prediction results for 693 prospectively collected acute leukemia samples from stage II. Gold standard classes are given in rows C1/GS to C14/GS; the prediction results are displayed for each sample in columns C1 to C14.

Abbreviations: IDC, indeterminable calls; CR, call rate [(No. of specimens–IDC)/No. of specimens]; GS, gold standard.

*

Values indicate correct prediction results.

Values represent misclassifications for each class.