Table 1 The performance of PLS-DA predictive model was assessed using accuracy, sensitivity and specificity, accompanied by 95% Wilson confidence intervals (CI).

From: Liquid biopsy of peripheral blood using mass spectrometry detects primary extramedullary disease in multiple myeloma patients

 

Training dataset

Test dataset

Total samples

121

51

EMD

70

22

MM

51

29

True positive (EMD)

63

19

True negative (MM)

43

21

False positive

8

8

False negative

7

3

Sensitivity (EMD)

90.0% (CI 80.8–95.1%)

86.4% (CI 66.7–95.3%)

Specificity (MM)

84.3% (CI 72.0–91.8%)

72.4% (CI 54.3–85.3%)

Accuracy (total)

87.6% (CI 80.6–92.3%)

78.4% (CI 65.4–87.5%)

Back to article page