Optimizing feature representation for automated systematic review work prioritization.

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

Automated document classification can be a valuable tool for enhancing the efficiency of creating and updating systematic reviews (SRs) for evidence-based medicine. One way document classification can help is in performing work prioritization: given a set of documents, order them such that the most likely useful documents appear first. We evaluated several alternate classification feature systems including unigram, n-gram, MeSH, and natural language processing (NLP) feature sets for their usefulness on 15 SR tasks, using the area under the receiver operating curve as a measure of goodness. We also examined the impact of topic-specific training data compared to general SR inclusion data. The best feature set used a combination of n-gram and MeSH features. NLP-based features were not found to improve performance. Furthermore, topic-specific training data usually provides a significant performance gain over more general SR training.

Original languageEnglish (US)
Pages (from-to)121-125
Number of pages5
JournalAMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
StatePublished - 2008

Fingerprint

Natural Language Processing
Evidence-Based Medicine

ASJC Scopus subject areas

  • Medicine(all)

Cite this

@article{e6723bf2051843dc91e96d1595d45846,
title = "Optimizing feature representation for automated systematic review work prioritization.",
abstract = "Automated document classification can be a valuable tool for enhancing the efficiency of creating and updating systematic reviews (SRs) for evidence-based medicine. One way document classification can help is in performing work prioritization: given a set of documents, order them such that the most likely useful documents appear first. We evaluated several alternate classification feature systems including unigram, n-gram, MeSH, and natural language processing (NLP) feature sets for their usefulness on 15 SR tasks, using the area under the receiver operating curve as a measure of goodness. We also examined the impact of topic-specific training data compared to general SR inclusion data. The best feature set used a combination of n-gram and MeSH features. NLP-based features were not found to improve performance. Furthermore, topic-specific training data usually provides a significant performance gain over more general SR training.",
author = "Aaron Cohen",
year = "2008",
language = "English (US)",
pages = "121--125",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1559-4076",
publisher = "American Medical Informatics Association",

}

TY - JOUR

T1 - Optimizing feature representation for automated systematic review work prioritization.

AU - Cohen, Aaron

PY - 2008

Y1 - 2008

N2 - Automated document classification can be a valuable tool for enhancing the efficiency of creating and updating systematic reviews (SRs) for evidence-based medicine. One way document classification can help is in performing work prioritization: given a set of documents, order them such that the most likely useful documents appear first. We evaluated several alternate classification feature systems including unigram, n-gram, MeSH, and natural language processing (NLP) feature sets for their usefulness on 15 SR tasks, using the area under the receiver operating curve as a measure of goodness. We also examined the impact of topic-specific training data compared to general SR inclusion data. The best feature set used a combination of n-gram and MeSH features. NLP-based features were not found to improve performance. Furthermore, topic-specific training data usually provides a significant performance gain over more general SR training.

AB - Automated document classification can be a valuable tool for enhancing the efficiency of creating and updating systematic reviews (SRs) for evidence-based medicine. One way document classification can help is in performing work prioritization: given a set of documents, order them such that the most likely useful documents appear first. We evaluated several alternate classification feature systems including unigram, n-gram, MeSH, and natural language processing (NLP) feature sets for their usefulness on 15 SR tasks, using the area under the receiver operating curve as a measure of goodness. We also examined the impact of topic-specific training data compared to general SR inclusion data. The best feature set used a combination of n-gram and MeSH features. NLP-based features were not found to improve performance. Furthermore, topic-specific training data usually provides a significant performance gain over more general SR training.

UR - http://www.scopus.com/inward/record.url?scp=69549134271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=69549134271&partnerID=8YFLogxK

M3 - Article

C2 - 18998798

AN - SCOPUS:69549134271

SP - 121

EP - 125

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1559-4076

ER -