Extraction of Temporal Information from Clinical Narratives View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-02-27

AUTHORS

Gandhimathi Moharasan, Tu-Bao Ho

ABSTRACT

The existence of massive quantity of clinical text in electronic medical records (EMRs) has created significant demand for clinical text processing and information extraction in the field of health care and medical research. Detailed clinical observations of patients are typically recorded chronologically. Temporal information in such clinical texts consist of three elements: temporal expressions, temporal events, and temporal relations. Due to the implicit expression of temporal information, lack of writing quality, and domain-specific nature in the clinical text, extraction of temporal information is much more complex than for newswire texts. In spite of these difficulties, to extract temporal information using the annotated corpora, few research works reported rule-based, machine-learning, and hybrid methods. On the other hand, creating the annotated corpora is expensive, time-consuming, and demands significant human effort; the processing quality is inevitably affected by the small size of corpora. Motivated by this issue, in this research work, we present a novel method to effectively extract the temporal information from EMR clinical texts. The essential idea of this method is first to build a feature set appropriately for clinical expressions, followed by the development of a semi-supervised framework for temporal event extraction, and finally detection of temporal relations among events with a newly formulated hypothesis. Comparative experimental evaluation on the I2B2 data set has clearly shown improved performance of the proposed methods. Specifically, temporal event and relation extraction is possible with an F-measure 89.98 and 67.1% respectively. More... »

PAGES

220-244

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s41666-019-00049-0

DOI

http://dx.doi.org/10.1007/s41666-019-00049-0

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1112442016


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Japan Advanced Institute of Science and Technology, Nomi, Japan", 
          "id": "http://www.grid.ac/institutes/grid.444515.5", 
          "name": [
            "Japan Advanced Institute of Science and Technology, Nomi, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Moharasan", 
        "givenName": "Gandhimathi", 
        "id": "sg:person.010224132663.80", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010224132663.80"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "John Von Neumann Institute, VNU-HCM, Ho Chi Minh City, Vietnam", 
          "id": "http://www.grid.ac/institutes/grid.444808.4", 
          "name": [
            "Japan Advanced Institute of Science and Technology, Nomi, Japan", 
            "John Von Neumann Institute, VNU-HCM, Ho Chi Minh City, Vietnam"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ho", 
        "givenName": "Tu-Bao", 
        "id": "sg:person.01346567517.58", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01346567517.58"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/978-3-319-61845-6_41", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090239185", 
          "https://doi.org/10.1007/978-3-319-61845-6_41"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-1-4614-3223-4_4", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049258309", 
          "https://doi.org/10.1007/978-1-4614-3223-4_4"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10579-009-9086-z", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1043605567", 
          "https://doi.org/10.1007/s10579-009-9086-z"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-02-27", 
    "datePublishedReg": "2019-02-27", 
    "description": "The existence of massive quantity of clinical text in electronic medical records (EMRs) has created significant demand for clinical text processing and information extraction in the field of health care and medical research. Detailed clinical observations of patients are typically recorded chronologically. Temporal information in such clinical texts consist of three elements: temporal expressions, temporal events, and temporal relations. Due to the implicit expression of temporal information, lack of writing quality, and domain-specific nature in the clinical text, extraction of temporal information is much more complex than for newswire texts. In spite of these difficulties, to extract temporal information using the annotated corpora, few research works reported rule-based, machine-learning, and hybrid methods. On the other hand, creating the annotated corpora is expensive, time-consuming, and demands significant human effort; the processing quality is inevitably affected by the small size of corpora. Motivated by this issue, in this research work, we present a novel method to effectively extract the temporal information from EMR clinical texts. The essential idea of this method is first to build a feature set appropriately for clinical expressions, followed by the development of a semi-supervised framework for temporal event extraction, and finally detection of temporal relations among events with a newly formulated hypothesis. Comparative experimental evaluation on the I2B2 data set has clearly shown improved performance of the proposed methods. Specifically, temporal event and relation extraction is possible with an F-measure 89.98 and 67.1% respectively.", 
    "genre": "article", 
    "id": "sg:pub.10.1007/s41666-019-00049-0", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1284856", 
        "issn": [
          "2509-4971", 
          "2509-498X"
        ], 
        "name": "Journal of Healthcare Informatics Research", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "2", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "3"
      }
    ], 
    "keywords": [
      "clinical text", 
      "temporal information", 
      "significant human effort", 
      "semi-supervised framework", 
      "clinical text processing", 
      "temporal events", 
      "temporal relations", 
      "domain-specific nature", 
      "research work", 
      "information extraction", 
      "event extraction", 
      "electronic medical records", 
      "relation extraction", 
      "human effort", 
      "text processing", 
      "clinical narratives", 
      "comparative experimental evaluation", 
      "experimental evaluation", 
      "newswire text", 
      "massive quantities", 
      "data sets", 
      "hybrid method", 
      "corpus", 
      "essential idea", 
      "information", 
      "significant demand", 
      "improved performance", 
      "novel method", 
      "text", 
      "extraction", 
      "medical research", 
      "implicit expression", 
      "framework", 
      "processing", 
      "method", 
      "set", 
      "quality", 
      "work", 
      "processing quality", 
      "performance", 
      "detection", 
      "issues", 
      "features", 
      "idea", 
      "demand", 
      "efforts", 
      "research", 
      "temporal expression", 
      "health care", 
      "difficulties", 
      "evaluation", 
      "small size", 
      "medical records", 
      "hand", 
      "field", 
      "writing quality", 
      "development", 
      "records", 
      "events", 
      "elements", 
      "lack", 
      "nature", 
      "size", 
      "relation", 
      "quantity", 
      "spite", 
      "existence", 
      "observations", 
      "care", 
      "detailed clinical observations", 
      "hypothesis", 
      "narratives", 
      "expression", 
      "clinical observations", 
      "patients", 
      "clinical expression", 
      "such clinical texts", 
      "EMR clinical texts", 
      "temporal event extraction", 
      "I2B2 data set"
    ], 
    "name": "Extraction of Temporal Information from Clinical Narratives", 
    "pagination": "220-244", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1112442016"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s41666-019-00049-0"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s41666-019-00049-0", 
      "https://app.dimensions.ai/details/publication/pub.1112442016"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2021-12-01T19:45", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/article/article_812.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1007/s41666-019-00049-0"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s41666-019-00049-0'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s41666-019-00049-0'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s41666-019-00049-0'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s41666-019-00049-0'


 

This table displays all metadata directly associated to this object as RDF triples.

161 TRIPLES      22 PREDICATES      108 URIs      97 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s41666-019-00049-0 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N0b7de2f963ea43a28ad129f1fa157145
4 schema:citation sg:pub.10.1007/978-1-4614-3223-4_4
5 sg:pub.10.1007/978-3-319-61845-6_41
6 sg:pub.10.1007/s10579-009-9086-z
7 schema:datePublished 2019-02-27
8 schema:datePublishedReg 2019-02-27
9 schema:description The existence of massive quantity of clinical text in electronic medical records (EMRs) has created significant demand for clinical text processing and information extraction in the field of health care and medical research. Detailed clinical observations of patients are typically recorded chronologically. Temporal information in such clinical texts consist of three elements: temporal expressions, temporal events, and temporal relations. Due to the implicit expression of temporal information, lack of writing quality, and domain-specific nature in the clinical text, extraction of temporal information is much more complex than for newswire texts. In spite of these difficulties, to extract temporal information using the annotated corpora, few research works reported rule-based, machine-learning, and hybrid methods. On the other hand, creating the annotated corpora is expensive, time-consuming, and demands significant human effort; the processing quality is inevitably affected by the small size of corpora. Motivated by this issue, in this research work, we present a novel method to effectively extract the temporal information from EMR clinical texts. The essential idea of this method is first to build a feature set appropriately for clinical expressions, followed by the development of a semi-supervised framework for temporal event extraction, and finally detection of temporal relations among events with a newly formulated hypothesis. Comparative experimental evaluation on the I2B2 data set has clearly shown improved performance of the proposed methods. Specifically, temporal event and relation extraction is possible with an F-measure 89.98 and 67.1% respectively.
10 schema:genre article
11 schema:inLanguage en
12 schema:isAccessibleForFree false
13 schema:isPartOf Nb621f7f8d71e44bd887b9d6c7ebd7c91
14 Nd9c9995121c941d4ada08014f7c38990
15 sg:journal.1284856
16 schema:keywords EMR clinical texts
17 I2B2 data set
18 care
19 clinical expression
20 clinical narratives
21 clinical observations
22 clinical text
23 clinical text processing
24 comparative experimental evaluation
25 corpus
26 data sets
27 demand
28 detailed clinical observations
29 detection
30 development
31 difficulties
32 domain-specific nature
33 efforts
34 electronic medical records
35 elements
36 essential idea
37 evaluation
38 event extraction
39 events
40 existence
41 experimental evaluation
42 expression
43 extraction
44 features
45 field
46 framework
47 hand
48 health care
49 human effort
50 hybrid method
51 hypothesis
52 idea
53 implicit expression
54 improved performance
55 information
56 information extraction
57 issues
58 lack
59 massive quantities
60 medical records
61 medical research
62 method
63 narratives
64 nature
65 newswire text
66 novel method
67 observations
68 patients
69 performance
70 processing
71 processing quality
72 quality
73 quantity
74 records
75 relation
76 relation extraction
77 research
78 research work
79 semi-supervised framework
80 set
81 significant demand
82 significant human effort
83 size
84 small size
85 spite
86 such clinical texts
87 temporal event extraction
88 temporal events
89 temporal expression
90 temporal information
91 temporal relations
92 text
93 text processing
94 work
95 writing quality
96 schema:name Extraction of Temporal Information from Clinical Narratives
97 schema:pagination 220-244
98 schema:productId N76fa1e7f7bda485d905566e416f91d25
99 Nd6e83daae6d3433cbfd6bf7eb5d979fa
100 schema:sameAs https://app.dimensions.ai/details/publication/pub.1112442016
101 https://doi.org/10.1007/s41666-019-00049-0
102 schema:sdDatePublished 2021-12-01T19:45
103 schema:sdLicense https://scigraph.springernature.com/explorer/license/
104 schema:sdPublisher N3b13b52c0c144da789e21e380fc66cd5
105 schema:url https://doi.org/10.1007/s41666-019-00049-0
106 sgo:license sg:explorer/license/
107 sgo:sdDataset articles
108 rdf:type schema:ScholarlyArticle
109 N04332e695f4144609319a4dc90ce4ff8 rdf:first sg:person.01346567517.58
110 rdf:rest rdf:nil
111 N0b7de2f963ea43a28ad129f1fa157145 rdf:first sg:person.010224132663.80
112 rdf:rest N04332e695f4144609319a4dc90ce4ff8
113 N3b13b52c0c144da789e21e380fc66cd5 schema:name Springer Nature - SN SciGraph project
114 rdf:type schema:Organization
115 N76fa1e7f7bda485d905566e416f91d25 schema:name doi
116 schema:value 10.1007/s41666-019-00049-0
117 rdf:type schema:PropertyValue
118 Nb621f7f8d71e44bd887b9d6c7ebd7c91 schema:volumeNumber 3
119 rdf:type schema:PublicationVolume
120 Nd6e83daae6d3433cbfd6bf7eb5d979fa schema:name dimensions_id
121 schema:value pub.1112442016
122 rdf:type schema:PropertyValue
123 Nd9c9995121c941d4ada08014f7c38990 schema:issueNumber 2
124 rdf:type schema:PublicationIssue
125 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
126 schema:name Information and Computing Sciences
127 rdf:type schema:DefinedTerm
128 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
129 schema:name Artificial Intelligence and Image Processing
130 rdf:type schema:DefinedTerm
131 sg:journal.1284856 schema:issn 2509-4971
132 2509-498X
133 schema:name Journal of Healthcare Informatics Research
134 schema:publisher Springer Nature
135 rdf:type schema:Periodical
136 sg:person.010224132663.80 schema:affiliation grid-institutes:grid.444515.5
137 schema:familyName Moharasan
138 schema:givenName Gandhimathi
139 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010224132663.80
140 rdf:type schema:Person
141 sg:person.01346567517.58 schema:affiliation grid-institutes:grid.444808.4
142 schema:familyName Ho
143 schema:givenName Tu-Bao
144 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01346567517.58
145 rdf:type schema:Person
146 sg:pub.10.1007/978-1-4614-3223-4_4 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049258309
147 https://doi.org/10.1007/978-1-4614-3223-4_4
148 rdf:type schema:CreativeWork
149 sg:pub.10.1007/978-3-319-61845-6_41 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090239185
150 https://doi.org/10.1007/978-3-319-61845-6_41
151 rdf:type schema:CreativeWork
152 sg:pub.10.1007/s10579-009-9086-z schema:sameAs https://app.dimensions.ai/details/publication/pub.1043605567
153 https://doi.org/10.1007/s10579-009-9086-z
154 rdf:type schema:CreativeWork
155 grid-institutes:grid.444515.5 schema:alternateName Japan Advanced Institute of Science and Technology, Nomi, Japan
156 schema:name Japan Advanced Institute of Science and Technology, Nomi, Japan
157 rdf:type schema:Organization
158 grid-institutes:grid.444808.4 schema:alternateName John Von Neumann Institute, VNU-HCM, Ho Chi Minh City, Vietnam
159 schema:name Japan Advanced Institute of Science and Technology, Nomi, Japan
160 John Von Neumann Institute, VNU-HCM, Ho Chi Minh City, Vietnam
161 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...