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

• Published in: Computers in biology and medicine Vol. 58; pp. 63 - 72
• Main Authors: Garcia-Gathright, Jean I, Oh, Andrea, Abarca, Phillip A, Han, Mary, Sago, William, Spiegel, Marshall L, Wolf, Brian, Garon, Edward B, Bui, Alex A.T, Aberle, Denise R
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2015; Elsevier Limited
• Subjects: Automatic summarization; Biomedical research; Cancer therapies; Classification; Clinical trials; Computational Biology - methods; Databases, Factual; Humans; Information retrieval; Information Storage and Retrieval; Internal Medicine; Lung cancer; Lung Neoplasms - diagnosis; Lung Neoplasms - genetics; Lung Neoplasms - therapy; Medical prognosis; Metadata; Mutation; Other; Prognosis; Quality of evidence; Research Design; ROC Curve; Studies; Support Vector Machine; Automatic summarization; Quality of evidence; Information retrieval
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2015.01.004

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.