Skip to main content

Table 4 – Comparison of performance of different systems reported on the same i2b2–2010 corpus

From: Integrating shortest dependency path and sentence sequence into a deep learning framework for relation extraction in clinical text

Publications

Models

Precision (%)

Recall (%)

F-measure (%)

Rink et al. [33]

SVM

67.44

57.85

59.31

Sahu te al. [19]

Multi-CNN-Max

55.73

50.08

49.42

Sahu and Anand [34]

LSTM-ATT

65.23

56.77

60.04

Wang et al. [35]

RCNN

50.07

45.34

46.47

Raj et al. [20]

CRNN

67.91

61.98

64.38

*Luo et al. [21]

Seg-CNN

–

–

74.20

 

Our model

75.69

73.03

74.34

  1. *Luo et al. used the original dataset from the challenge (871 documents in total)
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us