Non-contact Sleep Apnea syndrome detection based on wake in sleep stage

2021 Fiscal Year Final Research Report

• Project/Area Number: 20K21829
• Research Category: Grant-in-Aid for Challenging Research (Exploratory)
• Allocation Type: Multi-year Fund
• Review Section: Medium-sized Section 62:Applied informatics and related fields
• Research Institution: The University of Electro-Communications
• Principal Investigator: Takadma Keiki 電気通信大学, 大学院情報理工学研究科, 教授 (20345367)
• Project Period (FY): 2020-07-30 – 2022-03-31
• Keywords: 睡眠時無呼吸症候群 / 覚醒 / 機械学習 / ランダムフォレスト / 無拘束型センサ

Outline of Final Research Achievements

This research focuses on the sleep apnea syndrome (SAS), proposes the non-contact SAS detection method based on “wake” in sleep stage instead of “respiration” during sleep in order to solve the problems of the conventional SAS detection, and shows that the proposed method succeeds to derive the high accuracy of SAS detection. This research has also revealed that the sleep stage of the healthy human subjects tends to become a “wake” when the body movement is large and tends to become a “non-REM” when the body movement is small, while the sleep stage of the SAS patients shows the opposite tendency in addition to the same tendency.

Free Research Field

知能情報学

Academic Significance and Societal Importance of the Research Achievements

学術的意義としては，SASの主たる原因である「呼吸」に着目するのではなく，睡眠中の「覚醒」に着目した新しいSAS判定法を確立し，従来手法の問題(低呼吸判定の限界と努力呼吸の誤判定)を克服したことである．社会的意義としては，無拘束型のマットセンサを用いた提案手法によってSASを早期に発見することで，糖尿病・高血圧・心筋梗塞・脳梗塞のリスクを低減させ，SASによる不眠からくるヒューマンエラーや産業・交通事故を削減し，労働生産性の低下を抑制することが可能となる．