Table 1 Results of ANN classification.

From: Rapid discrimination of multiple myeloma patients by artificial neural networks coupled with mass spectrometry of peripheral blood plasma

Dataset

Training

Verification

Cases

40 (20 MM, 20 HD)

44 (24 MM, 20 HD)

True positive (MM)

20 (100%)

23 (95.83%)

True negative (HD)

20 (100%)

19 (95.00%)

False positive

0

1 (5.00%)

False negative

0

0

Unidentified

0

1 (4.17%)*

Sensitivity [%]

100%

95.83%

Specificity [%]

100%

95.00%

Accuracy [%]

100%

95.45%

  1. *Unidentified case (MM) arbitrarily classified as false negative.
Back to article page