Skip to main content

Table 4 Ablation experiment results of the proposed NER model on i2b2-clinical and our test set using micro-averaged F1-score

From: Entity and relation extraction from clinical case reports of COVID-19: a natural language processing approach

Model

i2b2-clinical

Our data

Full

90.10

94.78

BiLSTM-CRF

86.10

88.10

BiLSTM

85.13

87.63

Transformer-BiLSTM

88.12

90.28

Transformer

87.10

90.23

  1. Bold means best score, italic second-best score
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us