Supporting the annotation of chronic obstructive pulmonary disease (COPD) phenotypes with text mining workflows

Table 5 Results of 10-fold cross validation of concept recognisers, using exact matching

	Concept recognisers currently in Argo			Concept recognisers trained on our corpus
	Precision	Recall	F-score	Precision	Recall	F-score
AnatomicalConcept	0.2361	0.6617	0.3428	0.7602	0.4990	0.5912
Drug	0.7318	0.2161	0.3283	0.8576	0.4499	0.5873
MedicalCondition	0.3986	0.2436	0.3010	0.8510	0.4590	0.5932
TestOrMeasure	0.0766	0.0182	0.0289	0.6850	0.3190	0.4332
Treatment	0.4330	0.1021	0.1635	0.8276	0.3458	0.4829
Micro-average	0.3305	0.1776	0.2310	0.7929	0.3970	0.5291
Macro-average	0.3752	0.2483	0.2988	0.7963	0.4145	0.5452

Performance is compared with that of the components utilised in the text mining-assisted workflow.

ISSN: 2041-1480