Table 3 Comparison of generalization error with and without expert features
From: Hybrid-FHR: a multi-modal AI approach for automated fetal acidosis diagnosis
Method | Train Acc% | Test Acc% | Generalization error% |
|---|---|---|---|
Without expert features | 96.9 | 92.0 | 4.9 |
With expert features | 99.8 | 96.8 | 3 |