Representing and extracting lung cancer study metadata: Study objective and study design

Jean I. Garcia-Gathright; Andrea Oh; Phillip A. Abarca; Mary Han; William Sago; Marshall L. Spiegel; Brian Wolf; Edward B. Garon; Alex A.T. Bui; Denise R. Aberle

doi:10.1016/j.compbiomed.2015.01.004

Back

Representing and extracting lung cancer study metadata: Study objective and study design

Journal article

Peer reviewed

Representing and extracting lung cancer study metadata: Study objective and study design

Jean I. Garcia-Gathright, Andrea Oh, Phillip A. Abarca, Mary Han, William Sago, Marshall L. Spiegel, Brian Wolf, Edward B. Garon, Alex A.T. Bui and Denise R. Aberle

Computers in biology and medicine, Vol.58, pp.63-72

03/01/2015

DOI: 10.1016/j.compbiomed.2015.01.004

PMCID: PMC4331232

PMID: 25618216

View Online

Abstract

This paper describes the information retrieval step in Casama (Contextualized Semantic Maps), a project that summarizes and contextualizes current research papers on driver mutations in non-small cell lung cancer. Casama׳s representation of lung cancer studies aims to capture elements that will assist an end-user in retrieving studies and, importantly, judging their strength. This paper focuses on two types of study metadata: study objective and study design. 430 abstracts on EGFR and ALK mutations in lung cancer were annotated manually. Casama׳s support vector machine (SVM) automatically classified the abstracts by study objective with as much as 129% higher F-scores compared to PubMed׳s built-in filters. A second SVM classified the abstracts by epidemiological study design, suggesting strength of evidence at a more granular level than in previous work. The classification results and the top features determined by the classifiers suggest that this scheme would be generalizable to other mutations in lung cancer, as well as studies on driver mutations in other cancer domains. •We propose to improve retrieval by representing and extracting study metadata.•Multiple expert readers produced a gold standard of 430 abstracts on lung cancer.•Automatic classification performed better than or comparable to PubMed׳s filters.•Study design classification was robust to differences in vocabulary across corpora.•Top-ranked features were not domain-specific and could generalize to other domains.

Automatic summarization

Information retrieval

Quality of evidence

Details

Title: Subtitle: Representing and extracting lung cancer study metadata: Study objective and study design
Creators: Jean I. Garcia-Gathright - University of California, Los Angeles
Andrea Oh - University of California, Los Angeles
Phillip A. Abarca - University of California, Los Angeles
Mary Han - University of California, Los Angeles
William Sago - University of California, Los Angeles
Marshall L. Spiegel - University of California, Los Angeles
Brian Wolf - University of California, Los Angeles
Edward B. Garon - University of California, Los Angeles
Alex A.T. Bui - University of California, Los Angeles
Denise R. Aberle - University of California, Los Angeles
Resource Type: Journal article
Publication Details: Computers in biology and medicine, Vol.58, pp.63-72
DOI: 10.1016/j.compbiomed.2015.01.004
PMID: 25618216
PMCID: PMC4331232
NLM abbreviation: Comput Biol Med
ISSN: 0010-4825
eISSN: 1879-0534
Publisher: Elsevier Ltd
Grant note: name: the UCLA Department of Radiological Sciences, award: NLM T15-LM007356, NIH/NLM R01-LM009961, NIH K23CA149079
Language: English
Date published: 03/01/2015
Academic Unit: Orthopedics and Rehabilitation; Physical Therapy and Rehabilitation Science
Record Identifier: 9984295055902771

Metrics

11 Record Views

3 Times Cited - Web of Science