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

논문 기본 정보

자료유형
학술저널
저자정보
이혜원 (이화여자대학교 의학과) 오경선 (동덕여자대학교 약학대학) 권혜준 (이화여자대학교 휴먼바이오기계공학부) 임솔하 (한양대학교 사학과) 최승호 (한성대학교 기초교양학부) 김종윤 (동덕여자대학교 약학대학)
저널정보
한국병원약사회 병원약사회지 병원약사회지 제41권 제3호
발행연도
2024.8
수록면
275 - 283 (9page)

이용수

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

초록· 키워드

오류제보하기
Background : Cross-reactivity and hypersensitivity to β-lactam antibiotics significantly limit their use. This study aimed to analyze cutaneous adverse reaction patterns associated with cefoxitin and cephalothin, which share R1 side chain chemical structures, using machine learning techniques applied to the Korea Adverse Event Reporting System Database (KAERS DB). The goal was to establish evidence for safer antibiotic use. Methods : We utilized KAERS DB data from January 2018 to December 2022. The dataset was divided into dermatological adverse events and others, with 2018-2019 data serving as the training set and 2020-2022 data as the test set. Eight machine learning models were developed to predict cutaneous adverse reaction risks. Model performance was evaluated using accuracy and Area under the Receiver Operating Characteristic Curve (AUC) on both training and test sets. Statistical analyses were performed using Python 3.7.6. Results : In the training dataset, most models achieved high accuracy (0.986), with Bagging Classifier and Extra Trees Classifier demonstrating excellent performance (AUC 0.974). The test dataset also showed high accuracy (0.998) across models, but AUC scores varied. AdaBoost Classifier (AUC 0.812), Random Forest Classifier (AUC 0.786), and MLP Classifier (AUC 0.736) performed particularly well. Conclusion : This study employed machine learning techniques to classify cutaneous adverse reactions associated with second-generation (cefoxitin) and first-generation (cephalothin) cephalosporins, which have relatively high adverse event risks, and to predict potential cutaneous reactions in new cases. The models incorporated cross-reactivity possibilities based on cephalosporin chemical structures and demonstrated high predictive accuracy. These findings are expected to contribute to the development of safer antibiotic use guidelines based on scientific evidence.

목차

등록된 정보가 없습니다.

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

최근 본 자료

전체보기

댓글(0)

0