Table 2.
Micro-averaged results on the test data (514 narratives). (P = precision; R = recall; F = F1-measure)
| Token level matching | Text strict matching | HIPAA strict matching | |||||||
|---|---|---|---|---|---|---|---|---|---|
| P% | R% | F% | P% | R% | F% | P% | R% | F% | |
| Submission 1 | 97.11 | 86.49 | 91.49 | 93.02 | 81.94 | 87.13 | 94.46 | 82.80 | 88.25 |
| Submission 2 | 96.55 | 93.16 | 94.82 | 91.73 | 88.50 | 90.09 | 93.11 | 92.00 | 92.55 |
| Submission 3 | 97.22 | 92.50 | 94.80 | 93.06 | 88.36 | 90.65 | 94.37 | 92.13 | 93.23 |