호흡기 질환 약물처방정보를 활용한 계절성 독감의 조기 감지

Early detection of seasonal influenza through medical prescriptions of respiratory diseases

초록

This study proposes a new non-clinical surveillance system for seasonal influenza using NHIS-NSC. In particular, we take notice that the symptoms of influenza at early stage of infection are similar to those of respiratory disease, and we aim to detect an early outbreak of influenza by monitoring the activity of non-influenza respiratory disease. Our surveillance system yielded a quite reliable classification result with the average AUROC value above 0.75 and the precision rate above 80%. Furthermore, our system is able to effectively detect an outbreak that can be easily missed by disease control authorities, during the influenza “off-season”. The recall rate, however, is somewhat low, and thus it would be most beneficial to use our surveillance system as a complementary tool for the current surveillance program, not as a stand-alone replacement.

키워드

AUROC; influenza-like illness; NHIS-NSC; precision; recall; respiratory disease; seasonal influenza; 계절성 인플루엔자; 수신자 조작 특성 곡선; 인플루엔자 의사환자; 재현율; 정확도; 표본코호트DB; 호흡기 질환
제목
호흡기 질환 약물처방정보를 활용한 계절성 독감의 조기 감지
제목 (타언어)
Early detection of seasonal influenza through medical prescriptions of respiratory diseases
저자
Kim, Tae Heung; Jang, Eun Jin; Jung, Sun-Young; Yang, Ji-Yeon
DOI
10.7465/jkdi.2018.29.2.391
발행일
2018-03
저널명
한국데이터정보과학회지
권
29
호
2
페이지
391 ~ 402