Skip to main content

Table 4 Performance of miRNAs selected by PCA-based FE with PCA-based LDA and SVM

From: Universal disease biomarker: can a fixed set of blood microRNAs diagnose multiple diseases?

    

Number of

Diseases

Accuracy

Sens.

Spec.

miRNAs*

PCs+

Δ #

PCA-based LDA

AD

0.886

0.917

0.818

22

16

2.5

Carcinoma

0.857

0.846

0.867

36

2

7

CAD

0.885

0.923

0.846

16

14

9

NPC

0.720

0.806

0.579

28

18

5

HCC

0.650

0.600

0.700

8

1

7

BC

1.000

1.000

1.000

18

13

6

AML

0.862

0.846

0.923

11

8

7

Mean

0.837

0.848

0.819

   

Mean of previous study [23]

0.784

0.750

0.800

   

SVM

AD

0.843

0.833

0.864

22

  

Carcinoma

0.786

0.807

0.767

36

  

CAD

0.807

0.615

1.000

16

  

NPC

0.720

0.774

0.632

28

  

HCC

0.770

0.550

0.850

8

  

BC

0.963

1.000

0.938

18

  

AML

0.969

1.000

0.846

11

  

Mean

0.837

0.797

0.842

   
  1. *number of miRNAs selected by PCA-based FE, +optimal number of PCs estimated by LOOCV, #threshold value of PCA-based FE. Data from previous study [23] are also shown for comparison. AD, Alzheimer’s disease; CAD, coronary artery disease; NPC, nasopharyngeal carcinoma; HCC, hepatocellular carcinoma; BC, breast cancer; AML, acute myeloid leukemia; UDB, universal disease biomarker; SVM, support vector machine; LDA, linear discriminant analysis; PCA, principal component analysis.
Back to article page

BMC Research Notes

ISSN: 1756-0500

Contact us