잠시만 기다려 주세요. 로딩중입니다.

레벨2 장비로 전용가능한 레벨1 장비의 수면다원검사 자동화 판독과 검사자 판독 간의 비교

Performance of an Automated Polysomnography Scoring Using Noxturnal Program versus Manual Scoring

대한이비인후과학회지-두경부외과학 2021년 64권 3호 p.169 ~ 175
정수정, 성종엽, 김지수, 박종민, 성충만, 양형채, 임상철,
소속 상세정보
정수정 ( Jeong Su-Jeong ) - Chonnam National University Medical School Chonnam National University Hospital Department of Otolaryngology-Head and Neck Surgery
성종엽 ( Seong Jong-Yuap ) - Chonnam National University Medical School Chonnam National University Hospital Department of Otolaryngology-Head and Neck Surgery
김지수 ( Kim Ji-Su ) - Chonnam National University Medical School Chonnam National University Hospital Department of Otolaryngology-Head and Neck Surgery
박종민 ( Park Jong-Min ) - Chonnam National University Medical School Chonnam National University Hospital Department of Otolaryngology-Head and Neck Surgery
성충만 ( Sung Chung-Man ) - Chonnam National University Medical School Chonnam National University Hospital Department of Otolaryngology-Head and Neck Surgery
양형채 ( Yang Hyung-Chae ) - Chonnam National University Medical School Chonnam National University Hospital Department of Otolaryngology-Head and Neck Surgery
임상철 ( Lim Sang-Chul ) - Chonnam National University Medical School Chonnam National University Hospital Department of Otolaryngology-Head and Neck Surgery

Abstract


Background and Objectives : A lack of investigators for polysomnography has risen due toincreased demand since health insurance started to cover the cost of the test. We examined thereliability of the automated scoring of polysomnography, which has been deployed to improvethis imbalance.

Subjects and Method : We analyzed the data of 20 patients who underwent level 1 polysomnographyfrom April 1 to July 27, 2019. The software from Noxturnal (Nox Medical) was usedfor the scoring of the Polysomnography data. Each of the polysomnographic data was scoredboth by the automated scoring system and by a skilled technician.

Results : Twenty patients were analyzed. There was no significant difference between automatedscoring and manual scoring in sleep latency, apnea index, and rapid eye movementsleep stage ratio. However, the concordance rate of the sleep stage by epoch was 83.32%, andthere was a significant difference with regards to apnea-hypoapnea index (AHI) and respiratorydisturbance index (RDI). Two obvious errors were noted in the automated scoring that couldbe easily fixed; the failure to recognize wakefulness during sleep and the fragmentation of respiratoryevents. When two errors were corrected, many differences in polysomnography parameters,including AHI and RDI, were eliminated.

Conclusion : It showed 80% coincidence of epoch in the sleep stage between the automatedscoring and manual scoring. However, there was no difference in AHI and RDI when the fragmentedrespiratory events of the automated scoring were adjusted. Therefore, automated scoringis considered to be useful if only a little modification could be made.

키워드

Artificial intelligence; Economics; Obstructive sleep apneas; Polysomnographies; Sleep monitoring

원문 및 링크아웃 정보

등재저널 정보