Skip to main content

Table 5 The overall performance of different approaches on the i2b2-labtest dataset in detecting values (val) of given lab tests. Best results are shown in boldface

From: Applying a deep learning-based sequence labeling approach to detect attributes of medical concepts in clinical text

Attribute

VAL

Baseline

(Bi-LSTM+SVM)

Acc.

0.4415

P

0.7160

R

0.4193

F

0.5289

Baseline

(Bi-LSTM+Bi-LSTM)

Acc.

0.8993

P

0.9248

R

0.9288

F

0.9268

Sequence Labeling

Acc.

0.9456

P

0.9526

R

0.9582

F

0.9554

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us