Learning the Representation of Medical Features for Clinical Pathway Analysis View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2018-05-12

AUTHORS

Xiao Xu , Ying Wang , Tao Jin , Jianmin Wang

ABSTRACT

Clinical Pathway (CP) represents the best practice of treatment process management for inpatients with specific diagnosis, and a treatment process can be divided into several stages, usually in units of days. With the explosion of medical data, CP analysis is receiving increasing attention, which provides important support for CP design and optimization. However, these data-driven researches often suffer from the high complexity of medical data, so that a proper representation of medical features is necessary. Most of existing representation learning methods in healthcare domain focus on outpatient data, which get weak performance and interpretability when adopted for CP analysis. In this paper, we propose a new representation, RoMCP, which can capture both diagnosis information and temporal relations between days. The learned diagnosis embedding grasps the key factors of the disease, and each day embedding is determined by the diagnosis together with the preorder days. We evaluate RoMCP on real-world dataset with 538K inpatient visits for several typical CP analysis tasks. Our method demonstrates significant improvement on performance and interpretation. More... »

PAGES

37-52

Book

TITLE

Database Systems for Advanced Applications

ISBN

978-3-319-91457-2
978-3-319-91458-9

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-91458-9_3

DOI

http://dx.doi.org/10.1007/978-3-319-91458-9_3

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1103951534


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/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "School of Software, Tsinghua University, 100084, Beijing, China", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "School of Software, Tsinghua University, 100084, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Xu", 
        "givenName": "Xiao", 
        "id": "sg:person.012212057233.22", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012212057233.22"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Software, Tsinghua University, 100084, Beijing, China", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "School of Software, Tsinghua University, 100084, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Ying", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Software, Tsinghua University, 100084, Beijing, China", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "School of Software, Tsinghua University, 100084, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Jin", 
        "givenName": "Tao", 
        "id": "sg:person.010343202465.45", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010343202465.45"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "School of Software, Tsinghua University, 100084, Beijing, China", 
          "id": "http://www.grid.ac/institutes/grid.12527.33", 
          "name": [
            "School of Software, Tsinghua University, 100084, Beijing, China"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wang", 
        "givenName": "Jianmin", 
        "id": "sg:person.012303351315.43", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012303351315.43"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2018-05-12", 
    "datePublishedReg": "2018-05-12", 
    "description": "Clinical Pathway (CP) represents the best practice of treatment process management for inpatients with specific diagnosis, and a treatment process can be divided into several stages, usually in units of days. With the explosion of medical data, CP analysis is receiving increasing attention, which provides important support for CP design and optimization. However, these data-driven researches often suffer from the high complexity of medical data, so that a proper representation of medical features is necessary. Most of existing representation learning methods in healthcare domain focus on outpatient data, which get weak performance and interpretability when adopted for CP analysis. In this paper, we propose a new representation, RoMCP, which can capture both diagnosis information and temporal relations between days. The learned diagnosis embedding grasps the key factors of the disease, and each day embedding is determined by the diagnosis together with the preorder days. We evaluate RoMCP on real-world dataset with 538K inpatient visits for several typical CP analysis tasks. Our method demonstrates significant improvement on performance and interpretation.", 
    "editor": [
      {
        "familyName": "Pei", 
        "givenName": "Jian", 
        "type": "Person"
      }, 
      {
        "familyName": "Manolopoulos", 
        "givenName": "Yannis", 
        "type": "Person"
      }, 
      {
        "familyName": "Sadiq", 
        "givenName": "Shazia", 
        "type": "Person"
      }, 
      {
        "familyName": "Li", 
        "givenName": "Jianxin", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-91458-9_3", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-91457-2", 
        "978-3-319-91458-9"
      ], 
      "name": "Database Systems for Advanced Applications", 
      "type": "Book"
    }, 
    "keywords": [
      "medical data", 
      "real-world datasets", 
      "representation learning method", 
      "data-driven research", 
      "clinical pathway analysis", 
      "analysis tasks", 
      "process management", 
      "domain focus", 
      "learning method", 
      "diagnosis information", 
      "medical features", 
      "high complexity", 
      "temporal relations", 
      "new representation", 
      "representation", 
      "important support", 
      "proper representation", 
      "weak performance", 
      "datasets", 
      "performance", 
      "interpretability", 
      "units of days", 
      "embedding", 
      "best practices", 
      "complexity", 
      "task", 
      "features", 
      "CP design", 
      "significant improvement", 
      "optimization", 
      "information", 
      "data", 
      "grasp", 
      "method", 
      "clinical pathway", 
      "design", 
      "CP analysis", 
      "explosion", 
      "key factor", 
      "outpatient data", 
      "support", 
      "management", 
      "improvement", 
      "research", 
      "analysis", 
      "process", 
      "focus", 
      "attention", 
      "units", 
      "practice", 
      "stage", 
      "interpretation", 
      "diagnosis", 
      "relation", 
      "treatment process", 
      "factors", 
      "inpatient visits", 
      "days", 
      "pathway analysis", 
      "visits", 
      "specific diagnosis", 
      "disease", 
      "inpatients", 
      "paper", 
      "pathway", 
      "treatment process management", 
      "healthcare domain focus", 
      "RoMCP", 
      "diagnosis embedding grasps", 
      "embedding grasps", 
      "day embedding", 
      "preorder days", 
      "typical CP analysis tasks", 
      "CP analysis tasks"
    ], 
    "name": "Learning the Representation of Medical Features for Clinical Pathway Analysis", 
    "pagination": "37-52", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1103951534"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-91458-9_3"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-91458-9_3", 
      "https://app.dimensions.ai/details/publication/pub.1103951534"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-01-01T19:16", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/chapter/chapter_281.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-91458-9_3"
  }
]
 

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.10.1007/978-3-319-91458-9_3'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-91458-9_3'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-91458-9_3'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-91458-9_3'


 

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

169 TRIPLES      23 PREDICATES      99 URIs      92 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-91458-9_3 schema:about anzsrc-for:08
2 anzsrc-for:0806
3 schema:author N0bf020c8f20143c6815edfd69aac93a0
4 schema:datePublished 2018-05-12
5 schema:datePublishedReg 2018-05-12
6 schema:description Clinical Pathway (CP) represents the best practice of treatment process management for inpatients with specific diagnosis, and a treatment process can be divided into several stages, usually in units of days. With the explosion of medical data, CP analysis is receiving increasing attention, which provides important support for CP design and optimization. However, these data-driven researches often suffer from the high complexity of medical data, so that a proper representation of medical features is necessary. Most of existing representation learning methods in healthcare domain focus on outpatient data, which get weak performance and interpretability when adopted for CP analysis. In this paper, we propose a new representation, RoMCP, which can capture both diagnosis information and temporal relations between days. The learned diagnosis embedding grasps the key factors of the disease, and each day embedding is determined by the diagnosis together with the preorder days. We evaluate RoMCP on real-world dataset with 538K inpatient visits for several typical CP analysis tasks. Our method demonstrates significant improvement on performance and interpretation.
7 schema:editor N909ce41879434fcb9132bb5b37003047
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N6b0992c39e1c401ab0346eea3f0fce1a
12 schema:keywords CP analysis
13 CP analysis tasks
14 CP design
15 RoMCP
16 analysis
17 analysis tasks
18 attention
19 best practices
20 clinical pathway
21 clinical pathway analysis
22 complexity
23 data
24 data-driven research
25 datasets
26 day embedding
27 days
28 design
29 diagnosis
30 diagnosis embedding grasps
31 diagnosis information
32 disease
33 domain focus
34 embedding
35 embedding grasps
36 explosion
37 factors
38 features
39 focus
40 grasp
41 healthcare domain focus
42 high complexity
43 important support
44 improvement
45 information
46 inpatient visits
47 inpatients
48 interpretability
49 interpretation
50 key factor
51 learning method
52 management
53 medical data
54 medical features
55 method
56 new representation
57 optimization
58 outpatient data
59 paper
60 pathway
61 pathway analysis
62 performance
63 practice
64 preorder days
65 process
66 process management
67 proper representation
68 real-world datasets
69 relation
70 representation
71 representation learning method
72 research
73 significant improvement
74 specific diagnosis
75 stage
76 support
77 task
78 temporal relations
79 treatment process
80 treatment process management
81 typical CP analysis tasks
82 units
83 units of days
84 visits
85 weak performance
86 schema:name Learning the Representation of Medical Features for Clinical Pathway Analysis
87 schema:pagination 37-52
88 schema:productId N40e58e3fc6ed4b76a867ac84a9254cd6
89 Nf46d6ae6c74f439cacf652fa3cf743aa
90 schema:publisher N3dfac0ee6c6b449c9a49ae8dd41e533f
91 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103951534
92 https://doi.org/10.1007/978-3-319-91458-9_3
93 schema:sdDatePublished 2022-01-01T19:16
94 schema:sdLicense https://scigraph.springernature.com/explorer/license/
95 schema:sdPublisher Nb49fcd16c0cb447b8ada5c13b153ae42
96 schema:url https://doi.org/10.1007/978-3-319-91458-9_3
97 sgo:license sg:explorer/license/
98 sgo:sdDataset chapters
99 rdf:type schema:Chapter
100 N0bf020c8f20143c6815edfd69aac93a0 rdf:first sg:person.012212057233.22
101 rdf:rest Nb39684c4c86d4bfca4d9116a0e0fb886
102 N0d3b56e6d6fe427f84e06904043a25f2 schema:familyName Li
103 schema:givenName Jianxin
104 rdf:type schema:Person
105 N25dbf51e7bf84e8394013b1817239775 rdf:first Nc4c5203923264985862a5f6b9be8d5eb
106 rdf:rest N3c11b0e811de4806ac9c29c541e086a9
107 N3c11b0e811de4806ac9c29c541e086a9 rdf:first N0d3b56e6d6fe427f84e06904043a25f2
108 rdf:rest rdf:nil
109 N3dfac0ee6c6b449c9a49ae8dd41e533f schema:name Springer Nature
110 rdf:type schema:Organisation
111 N40e58e3fc6ed4b76a867ac84a9254cd6 schema:name dimensions_id
112 schema:value pub.1103951534
113 rdf:type schema:PropertyValue
114 N6b0992c39e1c401ab0346eea3f0fce1a schema:isbn 978-3-319-91457-2
115 978-3-319-91458-9
116 schema:name Database Systems for Advanced Applications
117 rdf:type schema:Book
118 N8591f3ce6786410e814f57b31743d042 rdf:first sg:person.012303351315.43
119 rdf:rest rdf:nil
120 N909ce41879434fcb9132bb5b37003047 rdf:first N9c536da3195647b9b5be06ec3ec03c07
121 rdf:rest Nf25c65546af54d27bd43b384b8a376c5
122 N982175e4191148a2bb2696a39010fb92 schema:familyName Manolopoulos
123 schema:givenName Yannis
124 rdf:type schema:Person
125 N9c536da3195647b9b5be06ec3ec03c07 schema:familyName Pei
126 schema:givenName Jian
127 rdf:type schema:Person
128 Nb39684c4c86d4bfca4d9116a0e0fb886 rdf:first Nf253b0f4575b414994164b966f0f21df
129 rdf:rest Nb5e28405750c4463aa385e75abe4919d
130 Nb49fcd16c0cb447b8ada5c13b153ae42 schema:name Springer Nature - SN SciGraph project
131 rdf:type schema:Organization
132 Nb5e28405750c4463aa385e75abe4919d rdf:first sg:person.010343202465.45
133 rdf:rest N8591f3ce6786410e814f57b31743d042
134 Nc4c5203923264985862a5f6b9be8d5eb schema:familyName Sadiq
135 schema:givenName Shazia
136 rdf:type schema:Person
137 Nf253b0f4575b414994164b966f0f21df schema:affiliation grid-institutes:grid.12527.33
138 schema:familyName Wang
139 schema:givenName Ying
140 rdf:type schema:Person
141 Nf25c65546af54d27bd43b384b8a376c5 rdf:first N982175e4191148a2bb2696a39010fb92
142 rdf:rest N25dbf51e7bf84e8394013b1817239775
143 Nf46d6ae6c74f439cacf652fa3cf743aa schema:name doi
144 schema:value 10.1007/978-3-319-91458-9_3
145 rdf:type schema:PropertyValue
146 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
147 schema:name Information and Computing Sciences
148 rdf:type schema:DefinedTerm
149 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
150 schema:name Information Systems
151 rdf:type schema:DefinedTerm
152 sg:person.010343202465.45 schema:affiliation grid-institutes:grid.12527.33
153 schema:familyName Jin
154 schema:givenName Tao
155 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010343202465.45
156 rdf:type schema:Person
157 sg:person.012212057233.22 schema:affiliation grid-institutes:grid.12527.33
158 schema:familyName Xu
159 schema:givenName Xiao
160 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012212057233.22
161 rdf:type schema:Person
162 sg:person.012303351315.43 schema:affiliation grid-institutes:grid.12527.33
163 schema:familyName Wang
164 schema:givenName Jianmin
165 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012303351315.43
166 rdf:type schema:Person
167 grid-institutes:grid.12527.33 schema:alternateName School of Software, Tsinghua University, 100084, Beijing, China
168 schema:name School of Software, Tsinghua University, 100084, Beijing, China
169 rdf:type schema:Organization
 




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


...