Table 8 Comparative results with respect to the seven-classication application and the eight-classication application of whether to use different class weights
From: Intelligent diagnosis with Chinese electronic medical records based on convolutional neural networks
Metrics | Seven-classication | Eight-classication | ||
|---|---|---|---|---|
| Â | Without class weight | With class weight | Without class weight | With class weight |
Precision (%) | 83.94 | 82.27 | 82.35 | 80.97 |
Accuracy (%) | 83.72 | 80.99 | 82.55 | 78.15 |
F1-score (%) | 83.78 | 81.25 | 82.27 | 78.45 |