A bottom-up approach to MEDLINE indexing recommendations

Antonio Jimeno-Yepes; Bartlomiej Wilkowski; James/G Mork; Elizabeth Van Lenten; Dina Demner Fushman; Alan/R Aronson

A bottom-up approach to MEDLINE indexing recommendations

Antonio Jimeno-Yepes, Bartlomiej Wilkowski, James/G Mork, Elizabeth Van Lenten, Dina Demner Fushman, Alan/R Aronson

National Institutes of Health

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

MEDLINE indexing performed by the US National Library of Medicine staff describes the essence of a biomedical publication in about 14 Medical Subject Headings (MeSH). Since 2002, this task is assisted by the Medical Text Indexer (MTI) program. We present a bottom-up approach to MEDLINE indexing in which the abstract is searched for indicators for a specific MeSH recommendation in a two-step process. Supervised machine learning combined with triage rules improves sensitivity of recommendations while keeping the number of recommended terms relatively small. Improvement in recommendations observed in this work warrants further exploration of this approach to MTI recommendations on a larger set of MeSH headings.

Original language	English
Title of host publication	AMIA 2011 Proceedings
Publication date	2011
Publication status	Published - 2011
Event	AMIA 2011 Annual Symposium - Washington DC, WA, United States Duration: 22 Oct 2011 → 26 Oct 2011 http://www.amia.org/amia2011

Conference

Conference	AMIA 2011 Annual Symposium
Country/Territory	United States
City	Washington DC, WA
Period	22/10/2011 → 26/10/2011
Internet address	http://www.amia.org/amia2011

Access to Document

http://www.amia.org/amia2011

OpenUrl availability

Full text

Cite this

@inproceedings{8b6f76e723c042f587fbe61f57da5d11,

title = "A bottom-up approach to MEDLINE indexing recommendations",

abstract = "MEDLINE indexing performed by the US National Library of Medicine staff describes the essence of a biomedical publication in about 14 Medical Subject Headings (MeSH). Since 2002, this task is assisted by the Medical Text Indexer (MTI) program. We present a bottom-up approach to MEDLINE indexing in which the abstract is searched for indicators for a specific MeSH recommendation in a two-step process. Supervised machine learning combined with triage rules improves sensitivity of recommendations while keeping the number of recommended terms relatively small. Improvement in recommendations observed in this work warrants further exploration of this approach to MTI recommendations on a larger set of MeSH headings.",

author = "Antonio Jimeno-Yepes and Bartlomiej Wilkowski and James/G Mork and {Van Lenten}, Elizabeth and {Demner Fushman}, Dina and Alan/R Aronson",

year = "2011",

language = "English",

booktitle = "AMIA 2011 Proceedings",

note = "AMIA 2011 Annual Symposium ; Conference date: 22-10-2011 Through 26-10-2011",

url = "http://www.amia.org/amia2011",

}

TY - GEN

T1 - A bottom-up approach to MEDLINE indexing recommendations

AU - Jimeno-Yepes, Antonio

AU - Wilkowski, Bartlomiej

AU - Mork, James/G

AU - Van Lenten, Elizabeth

AU - Demner Fushman, Dina

AU - Aronson, Alan/R

PY - 2011

Y1 - 2011

N2 - MEDLINE indexing performed by the US National Library of Medicine staff describes the essence of a biomedical publication in about 14 Medical Subject Headings (MeSH). Since 2002, this task is assisted by the Medical Text Indexer (MTI) program. We present a bottom-up approach to MEDLINE indexing in which the abstract is searched for indicators for a specific MeSH recommendation in a two-step process. Supervised machine learning combined with triage rules improves sensitivity of recommendations while keeping the number of recommended terms relatively small. Improvement in recommendations observed in this work warrants further exploration of this approach to MTI recommendations on a larger set of MeSH headings.

AB - MEDLINE indexing performed by the US National Library of Medicine staff describes the essence of a biomedical publication in about 14 Medical Subject Headings (MeSH). Since 2002, this task is assisted by the Medical Text Indexer (MTI) program. We present a bottom-up approach to MEDLINE indexing in which the abstract is searched for indicators for a specific MeSH recommendation in a two-step process. Supervised machine learning combined with triage rules improves sensitivity of recommendations while keeping the number of recommended terms relatively small. Improvement in recommendations observed in this work warrants further exploration of this approach to MTI recommendations on a larger set of MeSH headings.

M3 - Article in proceedings

BT - AMIA 2011 Proceedings

T2 - AMIA 2011 Annual Symposium

Y2 - 22 October 2011 through 26 October 2011

ER -

A bottom-up approach to MEDLINE indexing recommendations

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this