@inproceedings{7c2eccfe8eca48598a3a4004ca4447a6,
title = "Taming big data: An information extraction strategy for large clinical text corpora",
abstract = "Concepts of interest for clinical and research purposes are not uniformly distributed in clinical text available in electronic medical records. The purpose of our study was to identify filtering techniques to select 'high yield' documents for increased efficacy and throughput. Using two large corpora of clinical text, we demonstrate the identification of 'high yield' document sets in two unrelated domains: homelessness and indwelling urinary catheters. For homelessness, the high yield set includes homeless program and social work notes. For urinary catheters, concepts were more prevalent in notes from hospitalized patients; nursing notes accounted for a majority of the high yield set. This filtering will enable customization and refining of information extraction pipelines to facilitate extraction of relevant concepts for clinical decision support and other uses.",
keywords = "Big data, Information extraction, Natural language processing",
author = "Gundlapalli, \{Adi V.\} and Guy Divita and Carter, \{Marjorie E.\} and Andrew Redd and Samore, \{Matthew H.\} and Kalpana Gupta and Barbara Trautner",
note = "Publisher Copyright: {\textcopyright} 2015 The authors and IOS Press. All rights reserved.; 13th International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2015 ; Conference date: 09-07-2015 Through 11-07-2015",
year = "2015",
doi = "10.3233/978-1-61499-538-8-175",
language = "English",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press",
pages = "175--178",
editor = "John Mantas and Househ, \{Mowafa S.\} and Arie Hasman",
booktitle = "Enabling Health Informatics Applications",
}