Classifying relations in clinical narratives using segment graph convolutional and recurrent neural networks (Seg-GCRNs)

Yifu Li, Ran Jin, Yuan Luo*

*Corresponding author for this work

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

We propose to use segment graph convolutional and recurrent neural networks (Seg-GCRNs), which use only word embedding and sentence syntactic dependencies, to classify relations from clinical notes without manual feature engineering. In this study, the relations between 2 medical concepts are classified by simultaneously learning representations of text segments in the context of sentence syntactic dependency: preceding, concept1, middle, concept2, and succeeding segments. Seg-GCRN was systematically evaluated on the i2b2/VA relation classification challenge datasets. Experiments show that Seg-GCRN attains state-of-the-art micro-averaged F-measure for all 3 relation categories: 0.692 for classifying medical treatment-problem relations, 0.827 for medical test-problem relations, and 0.741 for medical problem-medical problem relations. Comparison with the previous state-of-the-art segment convolutional neural network (Seg-CNN) suggests that adding syntactic dependency information helps refine medical word embedding and improves concept relation classification without manual feature engineering. Seg-GCRN can be trained efficiently for the i2b2/VA dataset on a GPU platform.

Original languageEnglish (US)
Pages (from-to)262-268
Number of pages7
JournalJournal of the American Medical Informatics Association
Volume26
Issue number3
DOIs
StatePublished - Jan 1 2019

Fingerprint

Learning
Dependency (Psychology)
Datasets

Keywords

  • Bidirectional long short-term memory networks
  • Graph convolutional networks
  • Medical relation classification
  • Natural language processing

ASJC Scopus subject areas

  • Health Informatics

Cite this

@article{3a39045a666549a38df762e7ddb33803,
title = "Classifying relations in clinical narratives using segment graph convolutional and recurrent neural networks (Seg-GCRNs)",
abstract = "We propose to use segment graph convolutional and recurrent neural networks (Seg-GCRNs), which use only word embedding and sentence syntactic dependencies, to classify relations from clinical notes without manual feature engineering. In this study, the relations between 2 medical concepts are classified by simultaneously learning representations of text segments in the context of sentence syntactic dependency: preceding, concept1, middle, concept2, and succeeding segments. Seg-GCRN was systematically evaluated on the i2b2/VA relation classification challenge datasets. Experiments show that Seg-GCRN attains state-of-the-art micro-averaged F-measure for all 3 relation categories: 0.692 for classifying medical treatment-problem relations, 0.827 for medical test-problem relations, and 0.741 for medical problem-medical problem relations. Comparison with the previous state-of-the-art segment convolutional neural network (Seg-CNN) suggests that adding syntactic dependency information helps refine medical word embedding and improves concept relation classification without manual feature engineering. Seg-GCRN can be trained efficiently for the i2b2/VA dataset on a GPU platform.",
keywords = "Bidirectional long short-term memory networks, Graph convolutional networks, Medical relation classification, Natural language processing",
author = "Yifu Li and Ran Jin and Yuan Luo",
year = "2019",
month = "1",
day = "1",
doi = "10.1093/jamia/ocy157",
language = "English (US)",
volume = "26",
pages = "262--268",
journal = "Journal of the American Medical Informatics Association : JAMIA",
issn = "1067-5027",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - Classifying relations in clinical narratives using segment graph convolutional and recurrent neural networks (Seg-GCRNs)

AU - Li, Yifu

AU - Jin, Ran

AU - Luo, Yuan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We propose to use segment graph convolutional and recurrent neural networks (Seg-GCRNs), which use only word embedding and sentence syntactic dependencies, to classify relations from clinical notes without manual feature engineering. In this study, the relations between 2 medical concepts are classified by simultaneously learning representations of text segments in the context of sentence syntactic dependency: preceding, concept1, middle, concept2, and succeeding segments. Seg-GCRN was systematically evaluated on the i2b2/VA relation classification challenge datasets. Experiments show that Seg-GCRN attains state-of-the-art micro-averaged F-measure for all 3 relation categories: 0.692 for classifying medical treatment-problem relations, 0.827 for medical test-problem relations, and 0.741 for medical problem-medical problem relations. Comparison with the previous state-of-the-art segment convolutional neural network (Seg-CNN) suggests that adding syntactic dependency information helps refine medical word embedding and improves concept relation classification without manual feature engineering. Seg-GCRN can be trained efficiently for the i2b2/VA dataset on a GPU platform.

AB - We propose to use segment graph convolutional and recurrent neural networks (Seg-GCRNs), which use only word embedding and sentence syntactic dependencies, to classify relations from clinical notes without manual feature engineering. In this study, the relations between 2 medical concepts are classified by simultaneously learning representations of text segments in the context of sentence syntactic dependency: preceding, concept1, middle, concept2, and succeeding segments. Seg-GCRN was systematically evaluated on the i2b2/VA relation classification challenge datasets. Experiments show that Seg-GCRN attains state-of-the-art micro-averaged F-measure for all 3 relation categories: 0.692 for classifying medical treatment-problem relations, 0.827 for medical test-problem relations, and 0.741 for medical problem-medical problem relations. Comparison with the previous state-of-the-art segment convolutional neural network (Seg-CNN) suggests that adding syntactic dependency information helps refine medical word embedding and improves concept relation classification without manual feature engineering. Seg-GCRN can be trained efficiently for the i2b2/VA dataset on a GPU platform.

KW - Bidirectional long short-term memory networks

KW - Graph convolutional networks

KW - Medical relation classification

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=85060826879&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060826879&partnerID=8YFLogxK

U2 - 10.1093/jamia/ocy157

DO - 10.1093/jamia/ocy157

M3 - Article

C2 - 30590613

AN - SCOPUS:85060826879

VL - 26

SP - 262

EP - 268

JO - Journal of the American Medical Informatics Association : JAMIA

JF - Journal of the American Medical Informatics Association : JAMIA

SN - 1067-5027

IS - 3

ER -