Predicting MeSH beyond MEDLINE

Adam K. Kehoe, Vetle Ingvald Torvik, Neil R. Smalheiser, Matthew B. Ross

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Medical subject headings (MeSH) are a flexible and useful tool for describing biomedical concepts. Here, we present MeSHier, a tool for assigning MeSH terms to biomedical documents based on abstract similarity and references to MEDLINE records. When applied to PubMedCentral papers, NIH grants, and USPTO patents we find that these two sources of information produce largely disjoint sets of related MEDLINE records, albeit with some overlap in MeSH. When combined they provide an enriched topical annotation that would not have been possible with either alone. MeSHier is available as a demo tool that can take as input IDs of PubMed papers, USPTO patents, and NIH grants: http://abel.lis.illinois.edu/cgi-bin/meshier/search.py.

Original languageEnglish (US)
Title of host publicationProceedings of the 1st Workshop on Scholarly Web Mining, SWM 2017
PublisherAssociation for Computing Machinery
Pages49-56
Number of pages8
ISBN (Electronic)9781450352406
DOIs
StatePublished - Feb 10 2017
Event1st Workshop on Scholarly Web Mining, SWM 2017 - Cambridge, United Kingdom
Duration: Feb 10 2017 → …

Publication series

NameACM International Conference Proceeding Series
VolumePart F127853

Other

Other1st Workshop on Scholarly Web Mining, SWM 2017
CountryUnited Kingdom
CityCambridge
Period2/10/17 → …

Fingerprint

Bins

Keywords

  • Controlled vocabularies
  • Medical subject headings

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Kehoe, A. K., Torvik, V. I., Smalheiser, N. R., & Ross, M. B. (2017). Predicting MeSH beyond MEDLINE. In Proceedings of the 1st Workshop on Scholarly Web Mining, SWM 2017 (pp. 49-56). (ACM International Conference Proceeding Series; Vol. Part F127853). Association for Computing Machinery. https://doi.org/10.1145/3057148.3057155

Predicting MeSH beyond MEDLINE. / Kehoe, Adam K.; Torvik, Vetle Ingvald; Smalheiser, Neil R.; Ross, Matthew B.

Proceedings of the 1st Workshop on Scholarly Web Mining, SWM 2017. Association for Computing Machinery, 2017. p. 49-56 (ACM International Conference Proceeding Series; Vol. Part F127853).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kehoe, AK, Torvik, VI, Smalheiser, NR & Ross, MB 2017, Predicting MeSH beyond MEDLINE. in Proceedings of the 1st Workshop on Scholarly Web Mining, SWM 2017. ACM International Conference Proceeding Series, vol. Part F127853, Association for Computing Machinery, pp. 49-56, 1st Workshop on Scholarly Web Mining, SWM 2017, Cambridge, United Kingdom, 2/10/17. https://doi.org/10.1145/3057148.3057155
Kehoe AK, Torvik VI, Smalheiser NR, Ross MB. Predicting MeSH beyond MEDLINE. In Proceedings of the 1st Workshop on Scholarly Web Mining, SWM 2017. Association for Computing Machinery. 2017. p. 49-56. (ACM International Conference Proceeding Series). https://doi.org/10.1145/3057148.3057155
Kehoe, Adam K. ; Torvik, Vetle Ingvald ; Smalheiser, Neil R. ; Ross, Matthew B. / Predicting MeSH beyond MEDLINE. Proceedings of the 1st Workshop on Scholarly Web Mining, SWM 2017. Association for Computing Machinery, 2017. pp. 49-56 (ACM International Conference Proceeding Series).
@inproceedings{7dc5905e44694873b17c4f3db047c04b,
title = "Predicting MeSH beyond MEDLINE",
abstract = "Medical subject headings (MeSH) are a flexible and useful tool for describing biomedical concepts. Here, we present MeSHier, a tool for assigning MeSH terms to biomedical documents based on abstract similarity and references to MEDLINE records. When applied to PubMedCentral papers, NIH grants, and USPTO patents we find that these two sources of information produce largely disjoint sets of related MEDLINE records, albeit with some overlap in MeSH. When combined they provide an enriched topical annotation that would not have been possible with either alone. MeSHier is available as a demo tool that can take as input IDs of PubMed papers, USPTO patents, and NIH grants: http://abel.lis.illinois.edu/cgi-bin/meshier/search.py.",
keywords = "Controlled vocabularies, Medical subject headings",
author = "Kehoe, {Adam K.} and Torvik, {Vetle Ingvald} and Smalheiser, {Neil R.} and Ross, {Matthew B.}",
year = "2017",
month = "2",
day = "10",
doi = "10.1145/3057148.3057155",
language = "English (US)",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "49--56",
booktitle = "Proceedings of the 1st Workshop on Scholarly Web Mining, SWM 2017",

}

TY - GEN

T1 - Predicting MeSH beyond MEDLINE

AU - Kehoe, Adam K.

AU - Torvik, Vetle Ingvald

AU - Smalheiser, Neil R.

AU - Ross, Matthew B.

PY - 2017/2/10

Y1 - 2017/2/10

N2 - Medical subject headings (MeSH) are a flexible and useful tool for describing biomedical concepts. Here, we present MeSHier, a tool for assigning MeSH terms to biomedical documents based on abstract similarity and references to MEDLINE records. When applied to PubMedCentral papers, NIH grants, and USPTO patents we find that these two sources of information produce largely disjoint sets of related MEDLINE records, albeit with some overlap in MeSH. When combined they provide an enriched topical annotation that would not have been possible with either alone. MeSHier is available as a demo tool that can take as input IDs of PubMed papers, USPTO patents, and NIH grants: http://abel.lis.illinois.edu/cgi-bin/meshier/search.py.

AB - Medical subject headings (MeSH) are a flexible and useful tool for describing biomedical concepts. Here, we present MeSHier, a tool for assigning MeSH terms to biomedical documents based on abstract similarity and references to MEDLINE records. When applied to PubMedCentral papers, NIH grants, and USPTO patents we find that these two sources of information produce largely disjoint sets of related MEDLINE records, albeit with some overlap in MeSH. When combined they provide an enriched topical annotation that would not have been possible with either alone. MeSHier is available as a demo tool that can take as input IDs of PubMed papers, USPTO patents, and NIH grants: http://abel.lis.illinois.edu/cgi-bin/meshier/search.py.

KW - Controlled vocabularies

KW - Medical subject headings

UR - http://www.scopus.com/inward/record.url?scp=85020863765&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020863765&partnerID=8YFLogxK

U2 - 10.1145/3057148.3057155

DO - 10.1145/3057148.3057155

M3 - Conference contribution

T3 - ACM International Conference Proceeding Series

SP - 49

EP - 56

BT - Proceedings of the 1st Workshop on Scholarly Web Mining, SWM 2017

PB - Association for Computing Machinery

ER -