Table 6 Average performance with different semantic space ensemble sizes
From: Ensembles of randomized trees using diverse distributed representations of clinical events
Pool size | Accuracy | AUC | ||||
|---|---|---|---|---|---|---|
| Â | Mean score | Mean rank | P-value | Mean score | Mean rank | P-value |
1 | 84.80 | 8.7 | <0.0001 | 0.934 | 9.3 | <0.0001 |
2 | 86.12 | 6.5 | Â | 0.945 | 8.0 | Â |
3 | 86.31 | 5.6 | Â | 0.949 | 7.0 | Â |
4 | 86.43 | 5.2 | Â | 0.950 | 6.4 | Â |
5 | 86.45 | 4.9 | Â | 0.951 | 5.7 | Â |
6 | 86.45 | 5.4 | Â | 0.952 | 4.6 | Â |
7 | 86.43 | 4.7 | Â | 0.953 | 3.7 | Â |
8 | 86.60 | 4.4 | Â | 0.953 | 3.3 | Â |
9 | 86.27 | 5.1 | Â | 0.954 | 3.1 | Â |
10 | 86.98 | 4.4 | Â | 0.957 | 3.8 | Â |