Table 2 Count of entries according to each method, and count of concept codes from each source
From: MedLexSp – a medical lexicon for Spanish medical natural language processing
Method | # entries |
|---|---|
1. Abbreviations / acronyms | 6679 |
2. Affixes / roots | 914 |
3. Conjugated verbs | 867 |
4. Derivational variants | 801 |
5. String distance method | 1463 |
6. Syntactic variants | 134 |
7. Terms collected using word embeddings | 222 |
8. Terms from corpora: | |
CANTEMIST | 2619 |
CODIESP | 3384 |
CWLC | 1511 |
MedlinePlus | 1682 |
PharmaCoNER | 173 |
SPCs (EasyDLP corpus) | 837 |
9. Thesauri, dictionaries and knowledge bases: | # codes |
DTM | 30 816 |
ATC + Nomenclátor + SDEdb | 2931 |
DSM-5 | 188 |
ICD-10 | 19 888 |
ICPC | 179 |
MedDRA | 20 209 |
MeSH | 20 911 |
NCI | 7621 |
OMIM | 15 143 |
OrphaData | 10 741 |
SNOMED-CT | 53 893 |
WHO | 2811 |
Other | 4939 |