Table 1.
The number of semantically similar terms identified by human experts based on 40 top-ranked terms by word2vec for each 14 DS from 7 corpora
| Time span of clinical notes for 7 corpora |
|||||||
|---|---|---|---|---|---|---|---|
| 3 months | 6 months | 9 months | 12 months | 15 months | 18 months | 21 months | |
| Vocabulary size | 214 948 | 312 557 | 388 891 | 454 459 | 520 127 | 577 362 | 635 176 |
| Semantic variants | 12 | 14 | 13 | 13 | 11 | 10 | 9 |
| Brand names | 7 | 9 | 8 | 9 | 6 | 7 | 5 |
| Misspellings | 4 | 8 | 10 | 14 | 13 | 14 | 21 |
| Total | 23 | 31 | 31 | 36 | 30 | 31 | 35 |
| MAP | 0.313 | 0.294 | 0.356 | 0.247 | 0.242 | 0.280 | 0.263 |
MAP: mean average precision; DS: dietary supplements.