Skip to main content

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

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

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