@inproceedings{7c924d3eee3442db8e891b1a917454b1,
title = "Demographics identification: Variable extraction resource (DIVER)",
abstract = "Lack of standardization in representing phenotype data generated in different studies is a major barrier to data reuse for cross study analyses. To address this issue, we developed DIVER, a tool that identifies and standardizes demographic variables in dbGaP, based on simple natural language processing and standardized terminology mapping. In its evaluation using variables (N=3,565) from a range of pulmonary studies in dbGaP, DIVER proved to be an effective approach to standardizing dbGaP variables by successfully identifying demographic variables with high rates of recall and precision (98% and 94%, respectively). In addition, DIVER correctly modeled 79% of the identified demographic variables at the core semantic level. Examination of variables that DIVER could not handle shed light on where our tool needs enhancement so it can further improve its semantic modeling accuracy. DIVER is an important component of a system for phenotype discovery in dbGaP studies.",
keywords = "data reuse, data standardization, dbGaP, phenotype variables",
author = "Alexander Hsieh and Son Doan and Michael Conway and Lin, {Ko Wei} and Hyeoneui Kim",
year = "2012",
doi = "10.1109/HISB.2012.17",
language = "English",
isbn = "9780769549217",
series = "Proceedings - 2012 IEEE 2nd Conference on Healthcare Informatics, Imaging and Systems Biology, HISB 2012",
pages = "40--49",
booktitle = "Proceedings - 2012 IEEE 2nd Conference on Healthcare Informatics, Imaging and Systems Biology, HISB 2012",
note = "null ; Conference date: 27-09-2012 Through 28-09-2012",
}