Skip to main content

Table 2 Classification performance of GCN-EMCI based on different subject graphs

From: Identification of early mild cognitive impairment using multi-modal data and graph convolutional networks

Features ACC(%) SEN(%) SPE(%) AUC
FGMV 65.8 69.8 62.7 0.672
FSPL 62.7 66.5 59.4 0.637
FGMV+FSPL 69.7 71.4 65.6 0.719
FGMVS 79.8 83.4 77.1 0.802
FSPLS 75.3 78.3 73.2 0.765
FC 81.5 82.7 80.2 0.828
FC+H 84.1 86.5 81.3 0.856