@inproceedings{72c5fb86723d452d8f3c4250603bd060,
title = "Rich text formatted EHR narratives: A hidden and ignored trove",
abstract = "This study presents an approach for mining structured information from clinical narratives in Electronic Health Records (EHRs) by using Rich Text Formatted (RTF) records. RTF is adopted by many medical information management systems. There is rich structural information in these files which can be extracted and interpreted, yet such information is largely ignored. We investigate multiple types of EHR narratives in the Enterprise Data Warehouse from a multisite large healthcare chain consisting of both, an academic medical center and community hospitals. We focus on the RTF constructs related to tables and sections that are not available in plain text EHR narratives. We show how to parse these RTF constructs, analyze their prevalence and characteristics in the context of multiple types of EHR narratives. Our case study demonstrates the additional utility of the features derived from RTF constructs over plain text oriented NLP.",
keywords = "Electronic Health Records, Information Management, Natural Language Processing",
author = "Zexian Zeng and Yuan Zhao and Mengxin Sun and Vo, {Andy H.} and Starren, {Justin B} and Yuan Luo",
note = "Funding Information: This project is supported in part by NIH grant R21 LM012618. Publisher Copyright: {\textcopyright} 2019 International Medical Informatics Association (IMIA) and IOS Press.; 17th World Congress on Medical and Health Informatics, MEDINFO 2019 ; Conference date: 25-08-2019 Through 30-08-2019",
year = "2019",
month = aug,
day = "21",
doi = "10.3233/SHTI190266",
language = "English (US)",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press",
pages = "472--476",
editor = "Brigitte Seroussi and Lucila Ohno-Machado and Lucila Ohno-Machado and Brigitte Seroussi",
booktitle = "MEDINFO 2019",
}