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

BMC Research Notes

Table 1 Performance of UDB with PCA-based LDA and SVM

Diseases	Accuracy	Sensitivity	Specificity
PCA-based LDA
AD	0.829	0.833	0.818
Carcinoma	0.768	0.730	0.800
CAD	0.846	0.846	0.846
NPC	0.740	0.806	0.632
HCC	0.700	0.700	0.700
BC	0.870	0.813	0.955
AML	0.784	0.769	0.846
Mean	0.791	0.785	0.800
Mean of previous study [23]	0.784	0.750	0.800
SVM
AD	0.914	0.917	0.909
Carcinoma	0.786	0.867	0.692
CAD	0.769	0.769	0.769
NPC	0.720	0.806	0.579
HCC	0.725	0.550	0.900
BC	0.852	0.813	0.909
AML	0.938	0.981	0.769
Mean	0.815	0.815	0.800

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. Data from previous study [23] are also shown for comparison.

ISSN: 1756-0500