Skip to main content

Table 2 The performances of our model and baseline models on the same dataset

From: Automated classification of clinical trial eligibility criteria text based on ensemble learning and metric learning

Model

Accuracy

Precision

Recall

Macro F1

TextCNN

0.8256

0.8074

0.7538

0.7696

TextRNN

0.8094

0.7262

0.7369

0.7258

TextRCNN

0.8256

0.7894

0.7678

0.7704

FastText

0.8116

0.7732

0.7268

0.7385

Transformer

0.7934

0.7545

0.6469

0.6721

BERT

0.8385

0.8055

0.7980

0.7973

XLNet

0.8508

0.8164

0.8011

0.803

ERNIE

0.8382

0.8035

0.7969

0.7952

RoBERTa

0.8439

0.7929

0.8215

0.7992

ELECTRA

0.8324

0.7935

0.791

0.7862

Our model

0.850

0.825

0.821

0.8167

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us