Table 6.
Test data results broken down by semantic type with requirement of accurate negation, excluding spans of discontinuous text, with strict and relaxed matching expectations
| Scored items | Matching standard | TP | FP | FN | Precision | Recall | F1 | |
|---|---|---|---|---|---|---|---|---|
| Disorder | 104 | Strict | 80 | 22 | 13 | 0.78 | 0.86 | 0.82 |
| Relaxed | 83 | 23 | 9 | 0.78 | 0.9 | 0.84 | ||
| Family history | 5 | Strict | 5 | 0 | 0 | 1.00 | 1.00 | 1.00 |
| Relaxed | 5 | 0 | 0 | 1.00 | 1.00 | 1.00 | ||
| Finding | 61 | Strict | 45 | 7 | 17 | 0.88 | 0.74 | 0.8 |
| Relaxed | 45 | 8 | 16 | 0.87 | 0.75 | 0.8 | ||
| History of procedure | 14 | Strict | 5 | 3 | 10 | 0.63 | 0.33 | 0.43 |
| Relaxed | 5 | 3 | 10 | 0.63 | 0.33 | 0.43 | ||
| Situation affecting health | 10 | Strict | 8 | 3 | 3 | 0.73 | 0.73 | 0.73 |
| Relaxed | 8 | 3 | 3 | 0.73 | 0.73 | 0.73 | ||
| Disorder + finding | 165 | Strict | 125 | 29 | 30 | 0.82 | 0.81 | 0.81 |
| Relaxed | 128 | 31 | 25 | 0.81 | 0.84 | 0.83 |