Disease Prediction via Graph Neural Networks

With the increasingly available electronic medical records (EMRs), disease prediction has recently gained immense research attention, where an accurate classifier needs to be trained to map the input prediction signals (e.g., symptoms, patient demographics, etc.) to the estimated diseases for each p...

Full description

Saved in:
Bibliographic Details
Published inIEEE journal of biomedical and health informatics Vol. 25; no. 3; pp. 818 - 826
Main Authors Sun, Zhenchao, Yin, Hongzhi, Chen, Hongxu, Chen, Tong, Cui, Lizhen, Yang, Fan
Format Journal Article
LanguageEnglish
Published United States IEEE 01.03.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Online AccessGet full text

Cover

Loading…
Abstract With the increasingly available electronic medical records (EMRs), disease prediction has recently gained immense research attention, where an accurate classifier needs to be trained to map the input prediction signals (e.g., symptoms, patient demographics, etc.) to the estimated diseases for each patient. However, existing machine learning-based solutions heavily rely on abundant manually labeled EMR training data to ensure satisfactory prediction results, impeding their performance in the existence of rare diseases that are subject to severe data scarcity. For each rare disease, the limited EMR data can hardly offer sufficient information for a model to correctly distinguish its identity from other diseases with similar clinical symptoms. Furthermore, most existing disease prediction approaches are based on the sequential EMRs collected for every patient and are unable to handle new patients without historical EMRs, reducing their real-life practicality. In this paper, we introduce an innovative model based on Graph Neural Networks (GNNs) for disease prediction, which utilizes external knowledge bases to augment the insufficient EMR data, and learns highly representative node embeddings for patients, diseases and symptoms from the medical concept graph and patient record graph respectively constructed from the medical knowledge base and EMRs. By aggregating information from directly connected neighbor nodes, the proposed neural graph encoder can effectively generate embeddings that capture knowledge from both data sources, and is able to inductively infer the embeddings for a new patient based on the symptoms reported in her/his EMRs to allow for accurate prediction on both general diseases and rare diseases. Extensive experiments on a real-world EMR dataset have demonstrated the state-of-the-art performance of our proposed model.
AbstractList With the increasingly available electronic medical records (EMRs), disease prediction has recently gained immense research attention, where an accurate classifier needs to be trained to map the input prediction signals (e.g., symptoms, patient demographics, etc.) to the estimated diseases for each patient. However, existing machine learning-based solutions heavily rely on abundant manually labeled EMR training data to ensure satisfactory prediction results, impeding their performance in the existence of rare diseases that are subject to severe data scarcity. For each rare disease, the limited EMR data can hardly offer sufficient information for a model to correctly distinguish its identity from other diseases with similar clinical symptoms. Furthermore, most existing disease prediction approaches are based on the sequential EMRs collected for every patient and are unable to handle new patients without historical EMRs, reducing their real-life practicality. In this paper, we introduce an innovative model based on Graph Neural Networks (GNNs) for disease prediction, which utilizes external knowledge bases to augment the insufficient EMR data, and learns highly representative node embeddings for patients, diseases and symptoms from the medical concept graph and patient record graph respectively constructed from the medical knowledge base and EMRs. By aggregating information from directly connected neighbor nodes, the proposed neural graph encoder can effectively generate embeddings that capture knowledge from both data sources, and is able to inductively infer the embeddings for a new patient based on the symptoms reported in her/his EMRs to allow for accurate prediction on both general diseases and rare diseases. Extensive experiments on a real-world EMR dataset have demonstrated the state-of-the-art performance of our proposed model.
With the increasingly available electronic medical records (EMRs), disease prediction has recently gained immense research attention, where an accurate classifier needs to be trained to map the input prediction signals (e.g., symptoms, patient demographics, etc.) to the estimated diseases for each patient. However, existing machine learning-based solutions heavily rely on abundant manually labeled EMR training data to ensure satisfactory prediction results, impeding their performance in the existence of rare diseases that are subject to severe data scarcity. For each rare disease, the limited EMR data can hardly offer sufficient information for a model to correctly distinguish its identity from other diseases with similar clinical symptoms. Furthermore, most existing disease prediction approaches are based on the sequential EMRs collected for every patient and are unable to handle new patients without historical EMRs, reducing their real-life practicality. In this paper, we introduce an innovative model based on Graph Neural Networks (GNNs) for disease prediction, which utilizes external knowledge bases to augment the insufficient EMR data, and learns highly representative node embeddings for patients, diseases and symptoms from the medical concept graph and patient record graph respectively constructed from the medical knowledge base and EMRs. By aggregating information from directly connected neighbor nodes, the proposed neural graph encoder can effectively generate embeddings that capture knowledge from both data sources, and is able to inductively infer the embeddings for a new patient based on the symptoms reported in her/his EMRs to allow for accurate prediction on both general diseases and rare diseases. Extensive experiments on a real-world EMR dataset have demonstrated the state-of-the-art performance of our proposed model.With the increasingly available electronic medical records (EMRs), disease prediction has recently gained immense research attention, where an accurate classifier needs to be trained to map the input prediction signals (e.g., symptoms, patient demographics, etc.) to the estimated diseases for each patient. However, existing machine learning-based solutions heavily rely on abundant manually labeled EMR training data to ensure satisfactory prediction results, impeding their performance in the existence of rare diseases that are subject to severe data scarcity. For each rare disease, the limited EMR data can hardly offer sufficient information for a model to correctly distinguish its identity from other diseases with similar clinical symptoms. Furthermore, most existing disease prediction approaches are based on the sequential EMRs collected for every patient and are unable to handle new patients without historical EMRs, reducing their real-life practicality. In this paper, we introduce an innovative model based on Graph Neural Networks (GNNs) for disease prediction, which utilizes external knowledge bases to augment the insufficient EMR data, and learns highly representative node embeddings for patients, diseases and symptoms from the medical concept graph and patient record graph respectively constructed from the medical knowledge base and EMRs. By aggregating information from directly connected neighbor nodes, the proposed neural graph encoder can effectively generate embeddings that capture knowledge from both data sources, and is able to inductively infer the embeddings for a new patient based on the symptoms reported in her/his EMRs to allow for accurate prediction on both general diseases and rare diseases. Extensive experiments on a real-world EMR dataset have demonstrated the state-of-the-art performance of our proposed model.
Author Yin, Hongzhi
Cui, Lizhen
Yang, Fan
Sun, Zhenchao
Chen, Hongxu
Chen, Tong
Author_xml – sequence: 1
  givenname: Zhenchao
  orcidid: 0000-0002-9590-0962
  surname: Sun
  fullname: Sun, Zhenchao
  email: zhenchao.sun@mail.sdu.edu.cn
  organization: School of Software, Shandong University, Jinan, China
– sequence: 2
  givenname: Hongzhi
  orcidid: 0000-0003-1395-261X
  surname: Yin
  fullname: Yin, Hongzhi
  email: db.hongzhi@gmail.com
  organization: School of Information Technology & Electrical Engineering, The University of Queensland, Saint Lucia, QLD, Australia
– sequence: 3
  givenname: Hongxu
  orcidid: 0000-0001-7963-8813
  surname: Chen
  fullname: Chen, Hongxu
  email: hongxu.chen@uts.edu.au
  organization: School of Computer Science, University of Technology Sydney, Sydney, NSW, Australia
– sequence: 4
  givenname: Tong
  surname: Chen
  fullname: Chen, Tong
  email: tong.chen@uq.edu.au
  organization: School of Information Technology & Electrical Engineering, The University of Queensland, Saint Lucia, QLD, Australia
– sequence: 5
  givenname: Lizhen
  orcidid: 0000-0002-8262-8883
  surname: Cui
  fullname: Cui, Lizhen
  email: clz@sdu.edu.cn
  organization: School of Software, Shandong University, Jinan, China
– sequence: 6
  givenname: Fan
  surname: Yang
  fullname: Yang, Fan
  email: fanyang@sdu.edu.cn
  organization: School of Public Health & Institute for Medical Dataology, Shandong University, Jinan, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/32749976$$D View this record in MEDLINE/PubMed
BookMark eNp9kE1LxDAQhoMofqz-ABFkwYsHd51k2iY56vqNqAc9h7Q7xWi3XZNW8d-bsrsePBgIE4bnnQzPDluvm5oY2-cw5hz06d35ze1YgIAxAiQ8wTW2LXimRkKAWl-9uU622F4IbxCPii2dbbItFDLRWmbb7OTCBbKBhk-epq5oXVMPP50dXns7fx0-UOdtFUv71fj3sMs2SlsF2lvWAXu5unye3IzuH69vJ2f3owIT3Y4oz1PFp6K_kKQ2R6UwVVIVUltORZ5jWWQJR64RUU9BQsbTEgGJE9clDtjxYu7cNx8dhdbMXCioqmxNTReMSBCyDKSAiB79Qd-aztdxu0hppaSE-MmAHS6pLp_R1My9m1n_bVYeIiAXQOGbEDyVpnCt7W203rrKcDC9dNNLN710s5Qek_xPcjX8v8zBIuOI6JfXXIhUIv4Aw16IDQ
CODEN IJBHA9
CitedBy_id crossref_primary_10_1016_j_jbi_2024_104616
crossref_primary_10_1016_j_knosys_2022_109722
crossref_primary_10_1016_j_compbiomed_2025_109874
crossref_primary_10_1109_TNNLS_2022_3165554
crossref_primary_10_3233_IDT_220285
crossref_primary_10_1038_s41551_022_00942_x
crossref_primary_10_3390_mi14040714
crossref_primary_10_1016_j_chaos_2023_114046
crossref_primary_10_1016_j_jbi_2023_104430
crossref_primary_10_3390_ijerph19159771
crossref_primary_10_2174_1574893617666220513114917
crossref_primary_10_3390_app14104144
crossref_primary_10_1016_j_bspc_2024_106134
crossref_primary_10_1016_j_compbiolchem_2024_108294
crossref_primary_10_3233_JIFS_223280
crossref_primary_10_1109_ACCESS_2022_3197297
crossref_primary_10_1016_j_compbiolchem_2024_108099
crossref_primary_10_3390_healthcare11071031
crossref_primary_10_1016_j_media_2024_103225
crossref_primary_10_1140_epjs_s11734_024_01382_1
crossref_primary_10_1016_j_artmed_2023_102746
crossref_primary_10_3389_frai_2024_1388479
crossref_primary_10_1016_j_artmed_2024_102848
crossref_primary_10_1016_j_suscom_2021_100622
crossref_primary_10_1007_s12559_024_10274_4
crossref_primary_10_1093_bib_bbab340
crossref_primary_10_1109_JBHI_2022_3140455
crossref_primary_10_1016_j_jbi_2022_104000
crossref_primary_10_1016_j_cmpb_2024_108058
crossref_primary_10_1109_JBHI_2022_3233498
crossref_primary_10_1038_s41598_024_72321_2
crossref_primary_10_3390_bioengineering10060701
crossref_primary_10_1109_ACCESS_2024_3495531
crossref_primary_10_1007_s10115_021_01617_w
crossref_primary_10_1109_JBHI_2021_3079302
crossref_primary_10_1109_ACCESS_2024_3412961
crossref_primary_10_1109_RBME_2022_3210270
crossref_primary_10_1109_TCBB_2022_3198798
Cites_doi 10.1111/cts.12501
10.1145/3097983.3098126
10.1145/3219819.3219986
10.1145/3292500.3330779
10.1109/ICDE.2019.00035
10.1109/CHASE.2016.7
10.1038/nature14539
10.1145/3219819.3220020
10.1093/nar/gkw1039
10.1109/ICDE.2019.00059
10.1109/BIBM.2017.8217759
10.1145/3292500.3330877
10.1377/hlthaff.24.5.1103
10.1145/3394486.3403201
10.1007/BF00994018
10.1038/s41431-019-0508-0
10.1145/2736277.2741093
10.1016/S0020-7373(87)80053-6
10.1038/s41598-017-03011-5
10.1145/3097983.3098061
10.1109/TKDE.2020.2982878
10.1038/nrg3208
10.1145/3269206.3271701
10.1145/2939672.2939753
10.1016/j.ymgme.2008.10.003
10.1109/AICCSA.2008.4493524
10.1145/3097983.3098088
10.1145/2623330.2623732
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
K9.
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
DOI 10.1109/JBHI.2020.3004143
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Ceramic Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
Materials Research Database
ProQuest Computer Science Collection
ProQuest Health & Medical Complete (Alumni)
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Nursing & Allied Health Premium
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Materials Research Database
Civil Engineering Abstracts
Aluminium Industry Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
ProQuest Health & Medical Complete (Alumni)
Ceramic Abstracts
Materials Business File
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Aerospace Database
Nursing & Allied Health Premium
Engineered Materials Abstracts
Biotechnology Research Abstracts
Solid State and Superconductivity Abstracts
Engineering Research Database
Corrosion Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
MEDLINE - Academic
DatabaseTitleList PubMed
Materials Research Database

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2168-2208
EndPage 826
ExternalDocumentID 32749976
10_1109_JBHI_2020_3004143
9122573
Genre orig-research
Journal Article
GrantInformation_xml – fundername: National Key Research and Development Program of China Stem Cell and Translational Research
  grantid: 2017YFB1400100
  funderid: 10.13039/501100013290
– fundername: Australian Research Council
  grantid: DP190101985
  funderid: 10.13039/501100000923
– fundername: Innovation Method Fund of China
  grantid: 2018IM020200
– fundername: Shandong Key R&D Program
  grantid: 2018YFJH0506; 2019JZZY011007
– fundername: National Natural Science Foundation of China
  grantid: 91846205
  funderid: 10.13039/501100001809
GroupedDBID 0R~
4.4
6IF
6IH
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
HZ~
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
RIG
NPM
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
K9.
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
ID FETCH-LOGICAL-c349t-ebb581d281d2045ab38835878c79a1ecbb3fc6413193339d070615f303e1e19f3
IEDL.DBID RIE
ISSN 2168-2194
2168-2208
IngestDate Thu Jul 10 21:59:11 EDT 2025
Mon Jun 30 04:22:24 EDT 2025
Thu Apr 03 06:57:31 EDT 2025
Thu Apr 24 22:57:23 EDT 2025
Tue Jul 01 02:59:58 EDT 2025
Wed Aug 27 02:48:57 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c349t-ebb581d281d2045ab38835878c79a1ecbb3fc6413193339d070615f303e1e19f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-7963-8813
0000-0002-8262-8883
0000-0002-9590-0962
0000-0003-1395-261X
PMID 32749976
PQID 2498877093
PQPubID 85417
PageCount 9
ParticipantIDs ieee_primary_9122573
proquest_journals_2498877093
crossref_citationtrail_10_1109_JBHI_2020_3004143
crossref_primary_10_1109_JBHI_2020_3004143
proquest_miscellaneous_2430660720
pubmed_primary_32749976
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2021-03-01
PublicationDateYYYYMMDD 2021-03-01
PublicationDate_xml – month: 03
  year: 2021
  text: 2021-03-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Piscataway
PublicationTitle IEEE journal of biomedical and health informatics
PublicationTitleAbbrev JBHI
PublicationTitleAlternate IEEE J Biomed Health Inform
PublicationYear 2021
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref35
ref34
zhang (ref5) 2004; 1
ref15
ref36
ref14
ref31
ref30
ref33
ref10
veli?kovi? (ref12) 0
ref2
ref1
ref17
ref19
lecun (ref6) 2015; 521
ref18
ho (ref32) 0
hare (ref28) 2018; 6
choi (ref16) 0
ref24
ref23
hamilton (ref11) 0
ref25
ref20
ref22
ref21
ref27
ref29
ref8
ref7
ref9
ref4
ref3
xu (ref13) 0
garg (ref26) 2016
References_xml – ident: ref9
  doi: 10.1111/cts.12501
– ident: ref15
  doi: 10.1145/3097983.3098126
– ident: ref20
  doi: 10.1145/3219819.3219986
– start-page: 278
  year: 0
  ident: ref32
  article-title: Random decision forests
  publication-title: Proc Int Conf Document Anal Recognit
– ident: ref19
  doi: 10.1145/3292500.3330779
– volume: 1
  start-page: 3
  year: 2004
  ident: ref5
  article-title: The optimality of naive bayes
  publication-title: AA
– start-page: 1025
  year: 0
  ident: ref11
  article-title: Inductive representation learning on large graphs
  publication-title: Proc Conf Neural Inf Process Syst
– ident: ref22
  doi: 10.1109/ICDE.2019.00035
– ident: ref27
  doi: 10.1109/CHASE.2016.7
– volume: 521
  start-page: 436
  year: 2015
  ident: ref6
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– ident: ref3
  doi: 10.1145/3219819.3220020
– ident: ref30
  doi: 10.1093/nar/gkw1039
– ident: ref24
  doi: 10.1109/ICDE.2019.00059
– ident: ref2
  doi: 10.1109/BIBM.2017.8217759
– ident: ref21
  doi: 10.1145/3292500.3330877
– ident: ref1
  doi: 10.1377/hlthaff.24.5.1103
– ident: ref25
  doi: 10.1145/3394486.3403201
– ident: ref31
  doi: 10.1007/BF00994018
– ident: ref10
  doi: 10.1038/s41431-019-0508-0
– ident: ref34
  doi: 10.1145/2736277.2741093
– ident: ref4
  doi: 10.1016/S0020-7373(87)80053-6
– ident: ref29
  doi: 10.1038/s41598-017-03011-5
– ident: ref36
  doi: 10.1145/3097983.3098061
– ident: ref23
  doi: 10.1109/TKDE.2020.2982878
– ident: ref14
  doi: 10.1038/nrg3208
– volume: 6
  start-page: 41
  year: 2018
  ident: ref28
  article-title: Improving accuracy in rare disease patient identification using pattern recognition ensembles
  publication-title: J Pharmaceutical Manage Sci Assoc
– year: 0
  ident: ref12
  article-title: Graph attention networks
  publication-title: Proc Int Conf Learn Representations
– ident: ref18
  doi: 10.1145/3269206.3271701
– year: 0
  ident: ref13
  article-title: How powerful are graph neural networks?
  publication-title: Proc Int Conf Learn Representations
– ident: ref35
  doi: 10.1145/2939672.2939753
– ident: ref8
  doi: 10.1016/j.ymgme.2008.10.003
– ident: ref7
  doi: 10.1109/AICCSA.2008.4493524
– start-page: 3504
  year: 0
  ident: ref16
  article-title: RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism
  publication-title: Proc Conf Neural Inf Process Syst
– ident: ref17
  doi: 10.1145/3097983.3098088
– year: 2016
  ident: ref26
  article-title: A bootstrap machine learning approach to identify rare disease patients from electronic health records
– ident: ref33
  doi: 10.1145/2623330.2623732
SSID ssj0000816896
Score 2.529152
Snippet With the increasingly available electronic medical records (EMRs), disease prediction has recently gained immense research attention, where an accurate...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 818
SubjectTerms big data health applications
Coders
data mining
Data models
Demography
Disease
Disease prediction
Diseases
Electronic health records
Electronic medical records
graph embedding
Graph neural networks
Informatics
Knowledge bases (artificial intelligence)
Learning algorithms
Machine learning
Medical diagnosis
Medical diagnostic imaging
Medical research
Neural networks
Patients
Predictions
Predictive models
Rare diseases
Signs and symptoms
Task analysis
Title Disease Prediction via Graph Neural Networks
URI https://ieeexplore.ieee.org/document/9122573
https://www.ncbi.nlm.nih.gov/pubmed/32749976
https://www.proquest.com/docview/2498877093
https://www.proquest.com/docview/2430660720
Volume 25
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8NAEB7aHsSLr_qIVongSZo2yebRPfqqtdDiwUJvobudgCittI0Hf70zmzSIqHgILNlNstnZx_ftzM4AXGgCGRzUmGgquk6Q0jyoVBo4sZ8SCdJhJM057sEw6o2C_jgcV6BZnoVBRGN8hi1OGl3-dK4z3iprS496XyyqUCXilp_VKvdTTAAJE47Lp4RDAzEolJieK9v9694DkUGfOCp7mAo4fI4gQiYlOxv5siKZECu_o02z6nS3YbCub25s8tLKVqqlP765cvzvD-3AVgE_7au8v-xCBWd7sDEoFOx1aN7mChv7ccH3WGr2-_PEvme_1jZ78qCnh7np-HIfRt27p5ueUwRUcLQI5MpBpULCpz5fBOUmSnQIgHXijo7lxEOtlEh1RMsaoToh5JSmAwI8Ka1y6KEnU3EAtdl8hkdge4QbPWK3MiYMIKNAhaFAqQW6KFGHaIG7btREF97GOejFa2JYhysTFknCIkkKkVhwWT7ylrva-KtwnZuzLFi0pAWNteSSYjAuE6ogTaWxKyn7vMymYcS6kckM5xmXIe4UubHvWnCYS7x897qjHP_8zRPY9NnQxRimNaC2WmR4Skhlpc5MF_0Et_7cGQ
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLbGkIAL78d4FokTolvb9LEceY0O2MRhSNyqJXMlBNrQ1nHg12OnXYUQIA6VoiZt09iJP8eODXCiCWRwUmNSU9Gx_ZTWQaVS3468lJQgHYTSnOPudMP40b99Cp4qcFaehUFE43yGdS4aW_5gpKe8VdaQLnFfJOZgnuR-4OantcodFZNCwiTk8qhg01T0CzOm68jG7UXcJnXQIy2VY0z5nEBHkEomJYcb-SKTTJKV3_GmkTutFejMepy7m7zUp5mq649vwRz_-0ursFwAUOs855g1qOBwHRY6hYl9A86ucpON9TDme0w36_25b91wZGuLY3nQ093ceXyyCY-t695lbBcpFWwtfJnZqFRACNXji8BcX4kmQbBm1NSR7LuolRKpDkmwEa4TQg5oQSDIk5KcQxddmYotqA5HQ9wByyXk6JJ-KyNCATL0VRAIlFqggxJ1gDVwZoOa6CLeOKe9eE2M3uHIhEmSMEmSgiQ1OC0fecuDbfzVeIOHs2xYjGQN9meUS4rpOEmog7SYRo6k6uOymiYSW0f6QxxNuQ1pT6ETeU4NtnOKl--eMcruz988gsW417lP7tvduz1Y8tjtxbip7UM1G0_xgHBLpg4Nu34CZFPfYg
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Disease+Prediction+via+Graph+Neural+Networks&rft.jtitle=IEEE+journal+of+biomedical+and+health+informatics&rft.au=Sun%2C+Zhenchao&rft.au=Yin%2C+Hongzhi&rft.au=Chen%2C+Hongxu&rft.au=Chen%2C+Tong&rft.date=2021-03-01&rft.issn=2168-2208&rft.eissn=2168-2208&rft.volume=25&rft.issue=3&rft.spage=818&rft_id=info:doi/10.1109%2FJBHI.2020.3004143&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2194&client=summon