Table 3 External evaluation metrics of the ‘non-affirmative’ class in IULA and NUBes corpus. External validation using the IULA Spanish Clinical Record Corpus with 1,172 and the NUBes corpus with 11,400 negated entities. For both, metrics are shown using the CNN model solely and in combination with the customized rule-based NegEx layer. As the IULA corpus only contains negated entities, only the ‘non-affirmative’ class is shown. The NUBes corpus only contains negated and speculated entities and both were considered ‘non-affirmative’. Only the ‘non-affirmative’ class is shown
Precision | Recall | F1-score | |||||
|---|---|---|---|---|---|---|---|
N | CNN | NegEx + CNN | CNN | NegEx + CNN | CNN | NegEx + CNN | |
IULA corpus | 1,172 | 1.00 | 1.00 | 0.92 | 0.99 | 0.96 | 0.99 |
NUBes corpus | 11,400 | 1.00 | 1.00 | 0.76 | 0.93 | 0.86 | 0.96 |