Research Article
[Retracted] Automatic Detection of High-Frequency Oscillations Based on an End-to-End Bi-Branch Neural Network and Clinical Cross-Validation
Table 5
The results for the bi-branch feature fusion model using cross-subject validation.
| Group | Confusion matrix | Evaluation metrics (%) | TN | FP | FN | TP | SEN | SPE | PRE | ACC | FDR | F1 | SEN_SPE |
| 1 | 838 | 132 | 50 | 675 | 93.10 | 86.39 | 83.64 | 89.26 | 16.36 | 88.12 | 89.62 | 2 | 954 | 109 | 120 | 780 | 86.67 | 89.75 | 87.74 | 88.33 | 12.26 | 87.20 | 88.18 | 3 | 865 | 256 | 30 | 783 | 96.31 | 77.16 | 75.36 | 85.21 | 24.64 | 84.56 | 85.68 | 4 | 2282 | 61 | 41 | 2370 | 98.30 | 97.40 | 97.49 | 97.85 | 2.51 | 97.89 | 97.85 | 5 | 2642 | 274 | 418 | 2487 | 85.61 | 90.60 | 90.08 | 88.11 | 9.92 | 87.79 | 88.04 | Average | 92.00 | 88.26 | 86.86 | 89.76 | 13.14 | 89.11 | 89.87 |
|
|