Table 1 Statistics of the four document types in the EMC clinical corpus
From: ContextD: an algorithm to identify contextual properties of medical terms in a Dutch clinical corpus
Type | No. of documents | No. of recognized UMLS terms | No. of words per document* | Â |
|---|---|---|---|---|
GP entries | 2000 | 3626 | 23 | (14-38) |
Specialist letters | 2000 | 2748 | 39 | (16-113) |
Radiology reports | 1500 | 3684 | 66 | (46-94) |
Discharge letters | 2000 | 2830 | 163 | (95-201) |