Table 5. Comparison of pMCI and sMCI classification performance in the ADNI cohort between the proposed MSRNet and other methods.

Method	ACC (%)	SEN (%)	SPE (%)	AUC (%)
AGNN	72.0	45.7	83.1	74.5
GAT	70.2	46.1	80.3	73.8
GraphSAGE	72.8	57.5	79.3	76.3
HGNN	70.4	22.2	90.6	66.0
Graph U-Net	70.5	23.0	90.2	65.3
ConvMixer	69.3	50.7	77.1	73.7
3D VGG-16	72.1	63.1	75.8	78.4
3DAN	72.5	62.4	76.7	77.6
Proposed MSRNet	73.4	63.7	77.5	78.6

pMCI, progressive mild cognitive impairment; sMCI, stable mild cognitive impairment; ACC, accuracy; SEN, sensitivity; SPE, specificity; AUC, area under the curve; MSRNet, multispatial information representation model; ADNI, Alzheimer’s Disease Neuroimaging Initiative database; AGNN, attention-based graph neural network; GAT, graph attention network; HGNN, hypergraph neural network; 3D VGG-16, 3D visual geometry group 16; 3DAN, 3D attention network.