Table 4 Comparison with previous research on AD diagnosis (mean ± standard deviation, %)
From: Multimodal diagnosis model of Alzheimer’s disease based on improved Transformer
Methods | ACC | Precision | SPE | SEN | F1S | AUC |
|---|---|---|---|---|---|---|
3DCNN + SBi-RNN [17] | 93.33 ± 5.59 | 93.67 ± 7.22 | 94.91 ± 5.90 | 91.81 ± 8.01 | 92.52 ± 6.16 | 93.43 ± 5.56 |
3DCNN + FSBi-LSTM [18] | 94.76 ± 5.70 | 95.78 ± 7.21 | 96.78 ± 5.53 | 93.76 ± 9.35 | 94.38 ± 6.12 | 94.85 ± 5.38 |
3D PMNet [23] | 96.19 ± 4.92 | 98.89 ± 3.51 | 98.89 ± 2.78 | 93.19 ± 7.99 | 95.84 ± 5.40 | 96.47 ± 4.67 |
Proposed method | 98.10 ± 2.46 | 99.09 ± 2.87 | 96.75 ± 5.28 | 95.82 ± 5.03 | 97.81 ± 2.87 | 98.35 ± 2.14 |