A De-identification Method for Bilingual Clinical Texts of Various Note Types.
- Author:
Soo Yong SHIN
1
;
Yu Rang PARK
;
Yongdon SHIN
;
Hyo Joung CHOI
;
Jihyun PARK
;
Yongman LYU
;
Moo Song LEE
;
Chang Min CHOI
;
Woo Sung KIM
;
Jae Ho LEE
Author Information
- Publication Type:Original Article ; Research Support, Non-U.S. Gov't
- Keywords: De-identification; Anonymization; Clinical Text; Bilingual Text; Patient Privacy; Medical Informatics; Text Mining
- MeSH: Algorithms; *Data Anonymization; *Electronic Health Records; *Health Records, Personal; Humans; Multilingualism; Natural Language Processing; Research Design
- From:Journal of Korean Medical Science 2015;30(1):7-15
- CountryRepublic of Korea
- Language:English
- Abstract: De-identification of personal health information is essential in order not to require written patient informed consent. Previous de-identification methods were proposed using natural language processing technology in order to remove the identifiers in clinical narrative text, although these methods only focused on narrative text written in English. In this study, we propose a regular expression-based de-identification method used to address bilingual clinical records written in Korean and English. To develop and validate regular expression rules, we obtained training and validation datasets composed of 6,039 clinical notes of 20 types and 5,000 notes of 33 types, respectively. Fifteen regular expression rules were constructed using the development dataset and those rules achieved 99.87% precision and 96.25% recall for the validation dataset. Our de-identification method successfully removed the identifiers in diverse types of bilingual clinical narrative texts. This method will thus assist physicians to more easily perform retrospective research.
