STMT

Sub-Term Mapping Tools

Terms have no Norm-Mapping with no SMT synonyms lsit

The setup of thsi test are described as follows:

Input Terms: terms from UMLS-Core have no Norm-Mapping:
- Original ID|TERM|CUI: 15,447
- Total term with multi-CUI: 35
- Total term with multi-ID: 1,492
- It has been modified to 13,077 input TERM|CUI.
- Removed terms has Norm-CUI-Mapping, 2,847 TERM|CUI are used
SMT model:
- Lexicon, 2013
- Meta-thesaurus, 2013AA
- Synonyms list: none

Test ID	Synonyms	lvg flow	No Sub.	1 Sub.	2 Sub.	Precision	Recall	F₁-measure	MetaMap Distance Score
baseline	None		0.00% (0)	0.00% (0)	0.00% (0)	N/A	0.00%	N/A
s	spelling variants	-f:s	0.00% (0)	1.37% (39)	0.04% (1)	47.92%	0.81%	0.0159	0
i	inflectional variants	-f:i	0.00% (0)	0.11% (3)	0.00% (0)	25.00%	0.04%	0.0007	1
y	synonyms	-f:y	0.00% (0)	0.81% (23)	0.00% (0)	27.59%	0.28%	0.0056	2
A	Acronym/Abbreviation variants	-f:A	0.00% (0)	13.98% (398)	0.60% (17)	55.91%	10.96%	0.1833	2
a	expansion variants	-f:a	0.00% (0)	14.33% (408)	0.77% (22)	56.67%	11.35%	0.1891	2
d	derivational variants	-f:d	0.00% (0)	3.83% (109)	0.18% (5)	52.63%	2.46%	0.0470	3
Ge	fruitful variants	-f:Ge	0.00% (0)	21.15% (602)	1.79% (51)	45.58%	15.38%	0.2300	varies

SMT	SMT synonyms		0.00% (0)	21.78% (620)	1.40% (40)	48.25%	15.95%	0.2397	N/A

Precision = relevant, retrieved / total retrieved
Recall = relevant, retrieved / total relevant
F₁ = (2 x Precision x Recall) / (Precision + Recall)
precision and recall are equally important, so use F₁ (β = 1)