Table 2.
Dimension of feature sets using different data representations
| Dimension of the feature set | iDASH | MGH |
|---|---|---|
| Bag-of-words (Vocabulary size) | 8704 | 145,991 |
| UMLS concepts | 4751 | 25,457 |
| UMLS concepts restricted to five semantic groups | 4532 | 24,458 |
| UMLS concepts restricted to 15 semantic types | 3635 | 18,521 |
| Bag-of-words + UMLS concepts | 13,455 | 171,448 |
| Bag-of-words + UMLS concepts restricted to five semantic groups | 13,236 | 170,449 |
| Bag-of-words + UMLS concepts restricted to 15 semantic types | 12,339 | 164,512 |
| Paragraph vector (distributed memory model) | 600 | 600 |