Skip to main content

Table 4 F-scores calculated from the evaluation outcomes

From: Automated SNOMED CT concept and attribute relationship detection through a web-based implementation of cTAKES

  Development set (n = 30) Test set (n = 68)
Algorithm Concept Approach UMLS2011 UMLS2016 UMLS2016D DIRECT UMLS2011 UMLS2016 UMLS2016D DIRECT
Named-entity recognition Lung cancera Implied 0.698 0.541 0.920 0.920 0.814 0.725 0.828 0.828
Strict 0.769 0.606 1.000 1.000 0.880 0.841 0.947 0.947
Non-small cell lung cancerb Implied 0.759 0.455 0.867 1.000 0.879 0.655 0.746 0.862
Strict 0.759 0.455 0.867 1.000 0.951 0.720 0.815 0.933
Recurrencec   0.000 0.000 1.000 1.000 0.000 0.000 0.938 0.921
Relationship detection Recurrent lung cancerd      1.000     0.857
  1. aSNOMED CT concept 93880001 | Primary malignant neoplasm of lung (disorder)
  2. bSNOMED CT concept 254637007 | Non-small cell lung cancer (disorder)
  3. cSNOMED CT concept 255227004 | Recurrent (qualifier value)
  4. dRelationship between three SNOMED CT concepts: 93880001 | Primary malignant neoplasm of lung (disorder) |: 263502005 | Clinical course (attribute) | = 255227004 | Recurrent (qualifier value)