Dataset Information

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

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.

SUBMITTER: Garcia-Gathright JI

PROVIDER: S-EPMC4331232 | biostudies-literature | 2015 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Garcia-Gathright Jean I JI Oh Andrea A Abarca Phillip A PA Han Mary M Sago William W Spiegel Marshall L ML Wolf Brian B Garon Edward B EB Bui Alex A T AA Aberle Denise R DR

Computers in biology and medicine 20150113

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 mutati ...[more]

PMID: 25618216

Similar Datasets

Project description:Accelerometer-based activity monitors are widely used in research and surveillance applications for quantifying sedentary behavior (SB) and physical activity (PA). Considerable research has been done to refine methods for assessing PA, but relatively little attention has been given to operationalizing SB parameters (i.e., sedentary time and breaks) from accelerometer data - particularly in relation to health outcomes. This study investigated: (a) the accrued patterns of sedentary time and breaks; and (b) the associations of sedentary time and breaks in different bout durations with cardiovascular risk factors.Accelerometer data on 5,917 adults from the National Health Examination and Nutrition Survey (NHANES) 2003-2006 were used. Sedentary time and breaks at different bout durations (i.e., 1, 2-4, 5-9, 10-14, 15-19, 20-24, 25-29, and ≥ 30-min) were obtained using a threshold of < 100 counts per minute. Sedentary time and breaks were regressed on cardiovascular risk factors (waist circumference, triglyceride, and high-density lipoprotein cholesterol) and body mass index across bout durations.The results revealed that the majority of sedentary time occurred within relatively short bout durations (≈ 70% and ≈ 85% for < 5-min and < 10-min, respectively). The associations of sedentary time and breaks with health outcomes varied depending on how bout time was defined. Estimates of SB parameters based on bout durations of 5 min or shorter were associated with reduced cardiovascular risk factors while durations longer than 10-min were generally associated with increased risk factors.The present study demonstrates that the duration of sedentary bouts should be further considered when operationalizing the SB parameters from accelerometer data. The threshold of 5 minutes to define a bout is defensible, but a 10 minute threshold would provide a more conservative estimate to clearly capture the prolonged nature of sedentary behavior. Additional research is needed to determine the relative sensitivity and specificity of these thresholds.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure