@article{1b9a0be9f54a4d73b2a1ef78c5c171c4,
title = "Feasibility of Using Clinical Element Models (CEM) to Standardize Phenotype Variables in the Database of Genotypes and Phenotypes (dbGaP)",
abstract = "The database of Genotypes and Phenotypes (dbGaP) contains various types of data generated from genome-wide association studies (GWAS). These data can be used to facilitate novel scientific discoveries and to reduce cost and time for exploratory research. However, idiosyncrasies and inconsistencies in phenotype variable names are a major barrier to reusing these data. We addressed these challenges in standardizing phenotype variables by formalizing their descriptions using Clinical Element Models (CEM). Designed to represent clinical data, CEMs were highly expressive and thus were able to represent a majority (77.5%) of the 215 phenotype variable descriptions. However, their high expressivity also made it difficult to directly apply them to research data such as phenotype variables in dbGaP. Our study suggested that simplification of the template models makes it more straightforward to formally represent the key semantics of phenotype variables.",
author = "Lin, {Ko Wei} and Melissa Tharp and Mike Conway and Alexander Hsieh and Mindy Ross and Jihoon Kim and Kim, {Hyeon Eui}",
note = "Funding Information: The Phenotype Finder IN Data Resources (PFINDR) initiative, put forth by the National Heart, Lung, and Blood Institute (NHLBI), aims to make various phenotype data available for GWAS related investigations. Challenges associated with non-standardized phenotype variables generated in different research institutions are widely recognized []. The eMERGE (Electronic medical Records and Genomics) Network [], funded by the National Human Genome Research Institute (NHGRI), is another project dealing with the use of phenotypes collected in the electronic medical record to support GWAS. Standardization of the phenotype variables collected from different institutions/studies is a common challenge for these initiatives []. ",
year = "2013",
month = sep,
day = "18",
doi = "10.1371/journal.pone.0076384",
language = "English",
volume = "8",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "PLoS one",
number = "9",
}