Clustering WHO-ART terms using semantic distance and machine learning algorithms

WHO-ART was developed by the WHO collaborating centre for international drug monitoring in order to code adverse drug reactions. We assume that computation of semantic distance between WHO-ART terms may be an efficient way to group related medical conditions in the WHO database in order to improve s...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:AMIA ... Annual Symposium proceedings s. 369
Hlavní autoři: Iavindrasana, Jimison, Bousquet, Cedric, Degoulet, Patrice, Jaulent, Marie-Christine
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States 2006
Témata:
ISSN:1942-597X, 1559-4076
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract WHO-ART was developed by the WHO collaborating centre for international drug monitoring in order to code adverse drug reactions. We assume that computation of semantic distance between WHO-ART terms may be an efficient way to group related medical conditions in the WHO database in order to improve signal detection. Our objective was to develop a method for clustering WHO-ART terms according to some proximity of their meanings. Our material comprises 758 WHO-ART terms. A formal definition was acquired for each term as a list of elementary concepts belonging to SNOMED international axes and characterized by modifier terms in some cases. Clustering was implemented as a terminology service on a J2EE server. Two different unsupervised machine learning algorithms (KMeans, Pvclust) clustered WHO-ART terms according to a semantic distance operator previously described. Pvclust grouped 51% of WHO-ART terms. K-Means grouped 100% of WHO-ART terms but 25% clusters were heterogeneous with k = 180 clusters and 6% clusters were heterogeneous with k = 32 clusters. Clustering algorithms associated to semantic distance could suggest potential groupings of WHO-ART terms that need validation according to the user's requirements.
AbstractList WHO-ART was developed by the WHO collaborating centre for international drug monitoring in order to code adverse drug reactions. We assume that computation of semantic distance between WHO-ART terms may be an efficient way to group related medical conditions in the WHO database in order to improve signal detection. Our objective was to develop a method for clustering WHO-ART terms according to some proximity of their meanings. Our material comprises 758 WHO-ART terms. A formal definition was acquired for each term as a list of elementary concepts belonging to SNOMED international axes and characterized by modifier terms in some cases. Clustering was implemented as a terminology service on a J2EE server. Two different unsupervised machine learning algorithms (KMeans, Pvclust) clustered WHO-ART terms according to a semantic distance operator previously described. Pvclust grouped 51% of WHO-ART terms. K-Means grouped 100% of WHO-ART terms but 25% clusters were heterogeneous with k = 180 clusters and 6% clusters were heterogeneous with k = 32 clusters. Clustering algorithms associated to semantic distance could suggest potential groupings of WHO-ART terms that need validation according to the user's requirements.WHO-ART was developed by the WHO collaborating centre for international drug monitoring in order to code adverse drug reactions. We assume that computation of semantic distance between WHO-ART terms may be an efficient way to group related medical conditions in the WHO database in order to improve signal detection. Our objective was to develop a method for clustering WHO-ART terms according to some proximity of their meanings. Our material comprises 758 WHO-ART terms. A formal definition was acquired for each term as a list of elementary concepts belonging to SNOMED international axes and characterized by modifier terms in some cases. Clustering was implemented as a terminology service on a J2EE server. Two different unsupervised machine learning algorithms (KMeans, Pvclust) clustered WHO-ART terms according to a semantic distance operator previously described. Pvclust grouped 51% of WHO-ART terms. K-Means grouped 100% of WHO-ART terms but 25% clusters were heterogeneous with k = 180 clusters and 6% clusters were heterogeneous with k = 32 clusters. Clustering algorithms associated to semantic distance could suggest potential groupings of WHO-ART terms that need validation according to the user's requirements.
WHO-ART was developed by the WHO collaborating centre for international drug monitoring in order to code adverse drug reactions. We assume that computation of semantic distance between WHO-ART terms may be an efficient way to group related medical conditions in the WHO database in order to improve signal detection. Our objective was to develop a method for clustering WHO-ART terms according to some proximity of their meanings. Our material comprises 758 WHO-ART terms. A formal definition was acquired for each term as a list of elementary concepts belonging to SNOMED international axes and characterized by modifier terms in some cases. Clustering was implemented as a terminology service on a J2EE server. Two different unsupervised machine learning algorithms (KMeans, Pvclust) clustered WHO-ART terms according to a semantic distance operator previously described. Pvclust grouped 51% of WHO-ART terms. K-Means grouped 100% of WHO-ART terms but 25% clusters were heterogeneous with k = 180 clusters and 6% clusters were heterogeneous with k = 32 clusters. Clustering algorithms associated to semantic distance could suggest potential groupings of WHO-ART terms that need validation according to the user's requirements.
Author Jaulent, Marie-Christine
Iavindrasana, Jimison
Degoulet, Patrice
Bousquet, Cedric
Author_xml – sequence: 1
  givenname: Jimison
  surname: Iavindrasana
  fullname: Iavindrasana, Jimison
  organization: University Hospitals of Geneva - CH-1211 Geneva 4, Switzerland
– sequence: 2
  givenname: Cedric
  surname: Bousquet
  fullname: Bousquet, Cedric
– sequence: 3
  givenname: Patrice
  surname: Degoulet
  fullname: Degoulet, Patrice
– sequence: 4
  givenname: Marie-Christine
  surname: Jaulent
  fullname: Jaulent, Marie-Christine
BackLink https://www.ncbi.nlm.nih.gov/pubmed/17238365$$D View this record in MEDLINE/PubMed
BookMark eNo1kE1LwzAcxoNM3It-BcnJW6F5bXMcRZ0wmMhEbyVN_t0iTTqb9OC3t8N5el748RyeJZqFPsAVWhAhVMbzQs4mrzjNhCo-52gZ41ee80KU8gbNSUFZyaRYoNeqG2OCwYUD_tjssvXbHk_RRzzGcxfB65CcwdbFpIMBrIPFXpujC4A70EM4Y7o79INLRx9v0XWruwh3F12h96fHfbXJtrvnl2q9zU6kUClTNhe2ZQKIbhnlUnGmGmlsqZTkhDZGUUtpyYFY1TKeC2hMK3INFASjhaEr9PC3exr67xFiqr2LBrpOB-jHWMuSKk4kmcD7Czg2Hmx9GpzXw0_9_wH9BRgnWwQ
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
EISSN 1559-4076
ExternalDocumentID 17238365
Genre Research Support, Non-U.S. Gov't
Journal Article
GroupedDBID 2WC
53G
ADBBV
ALMA_UNASSIGNED_HOLDINGS
BAWUL
CGR
CUY
CVF
DIK
E3Z
ECM
EIF
GX1
HYE
M~E
NPM
OK1
RPM
WOQ
7X8
ID FETCH-LOGICAL-p179t-9d05df35e1af32469439b6cd8996412bc92d2284e1d9f3405ebcf50ae2e5327c2
IEDL.DBID 7X8
ISSN 1942-597X
IngestDate Sun Nov 09 10:06:50 EST 2025
Sat Sep 28 07:58:00 EDT 2024
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-p179t-9d05df35e1af32469439b6cd8996412bc92d2284e1d9f3405ebcf50ae2e5327c2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 17238365
PQID 68294161
PQPubID 23479
ParticipantIDs proquest_miscellaneous_68294161
pubmed_primary_17238365
PublicationCentury 2000
PublicationDate 2006-00-00
20060101
PublicationDateYYYYMMDD 2006-01-01
PublicationDate_xml – year: 2006
  text: 2006-00-00
PublicationDecade 2000
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle AMIA ... Annual Symposium proceedings
PublicationTitleAlternate AMIA Annu Symp Proc
PublicationYear 2006
References 11079852 - Proc AMIA Symp. 2000;:96-100
9865050 - Methods Inf Med. 1998 Nov;37(4-5):518-26
11144660 - Drug Saf. 2000 Dec;23(6):533-42
17108617 - Stud Health Technol Inform. 2006;124:839-44
9656658 - Methods Inf Med. 1998 Jun;37(2):161-4
9696956 - Eur J Clin Pharmacol. 1998 Jun;54(4):315-21
References_xml – reference: 17108617 - Stud Health Technol Inform. 2006;124:839-44
– reference: 9865050 - Methods Inf Med. 1998 Nov;37(4-5):518-26
– reference: 11079852 - Proc AMIA Symp. 2000;:96-100
– reference: 9696956 - Eur J Clin Pharmacol. 1998 Jun;54(4):315-21
– reference: 9656658 - Methods Inf Med. 1998 Jun;37(2):161-4
– reference: 11144660 - Drug Saf. 2000 Dec;23(6):533-42
SSID ssj0047586
Score 1.703144
Snippet WHO-ART was developed by the WHO collaborating centre for international drug monitoring in order to code adverse drug reactions. We assume that computation of...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 369
SubjectTerms Adverse Drug Reaction Reporting Systems
Algorithms
Artificial Intelligence
Humans
Semantics
Subject Headings
Systematized Nomenclature of Medicine
Unified Medical Language System
Vocabulary, Controlled
World Health Organization
Title Clustering WHO-ART terms using semantic distance and machine learning algorithms
URI https://www.ncbi.nlm.nih.gov/pubmed/17238365
https://www.proquest.com/docview/68294161
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8MwDLYGQ4gL78d45sC1ok3atJGQEEJMu2zsAKK3Ks1jTNq6QTd-P07Xwglx4NJb1MiO7c-x4w_gOlRUxlInaGnCDdX2nR-MrGdDgdFSaWpkUpFNxINBkqZi2ILb5i2Ma6tsfGLlqPVMuTvyG55Q4cD43fzdc5xRrrZaE2isQZsFLHHEDXH6XUMIEQlXb4tEiOmWiNPfMWQVS7o7_9vFLmzXGJLcr5S-By1T7MNmv66SH8DwYbJ08w8wKpHX3pOHmJU4D1wS1-U-IqWZojzHimgHHlHrRBaaTKu2SkNqHokRkZMR_nzxNi0P4aX7-PzQ82rmBG-OBrbwhPYjbVlkAmkRMXGBsCPnSmNyxcOA5kpQTTEwmUALyxCzmVzZyJeGmoihiugRrBezwpwA8a1gmvMwMjTH2GWljRnHvAfVyvLAyg5cNZLK8GS6coMszGxZZo2sOnC8EnY2Xw3QyALHdMZ4dPrn2jPY-rnzOIe2RZs0F7ChPhfj8uOyUjh-B8P-F0dOuCk
linkProvider ProQuest
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=Clustering+WHO-ART+terms+using+semantic+distance+and+machine+learning+algorithms&rft.jtitle=AMIA+...+Annual+Symposium+proceedings&rft.au=Iavindrasana%2C+Jimison&rft.au=Bousquet%2C+Cedric&rft.au=Degoulet%2C+Patrice&rft.au=Jaulent%2C+Marie-Christine&rft.date=2006-01-01&rft.issn=1942-597X&rft.eissn=1559-4076&rft.spage=369&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1942-597X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1942-597X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1942-597X&client=summon