메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색

초록· 키워드

오류제보하기
De-identification of personal health information is essential in order not to require writtenpatient informed consent. Previous de-identification methods were proposed using naturallanguage 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, wepropose a regular expression-based de-identification method used to address bilingualclinical records written in Korean and English. To develop and validate regular expressionrules, we obtained training and validation datasets composed of 6,039 clinical notes of 20types and 5,000 notes of 33 types, respectively. Fifteen regular expression rules wereconstructed using the development dataset and those rules achieved 99.87% precision and96.25% recall for the validation dataset. Our de-identification method successfullyremoved the identifiers in diverse types of bilingual clinical narrative texts. This method willthus assist physicians to more easily perform retrospective research.

목차

등록된 정보가 없습니다.

참고문헌 (39)

참고문헌 신청

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0