Skip to main content

Table 3 Comparative AUC results of the previous methods and the proposed method for different AD patient groups

From: Stratifying patients using fast multiple kernel learning framework: case studies of Alzheimer’s disease and cancers

Method

AUC

AD/NC

AD/MCI

NC/MCI

MCIc/MCInc

Chupin et al., 2009 [8]

0.7851

0.7328

0.7155

0.6638

Ahmed et al., 2015 [11]

0.8487

0.7562

0.7677

0.6814

Khedher et al., 2015 [12]

0.9256

0.8859

0.8134

0.7076

Dai et al., 2013 [9]

0.9429

0.8743

0.8118

0.7086

Suk et al., 2014 [10]

0.9475

0.9007

0.8203

0.7123

Liu et al., 2017 [13]

0.9754

0.9355

0.9107

0.7885

Proposed method (the best result among 20 runs)

0.9786

0.9412

0.9151

0.8024

Proposed method (at 90% confidence level of t-test)

0.9705

0.936

0.911

0.7945