Analysis of Obstructive Sleep Apnea based on Visualization and Summarization of Massive Snoring Sound Data

2017 Fiscal Year Final Research Report

• Project/Area Number: 26330338
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Life / Health / Medical informatics
• Research Institution: Tomakomai National College of Technology
• Principal Investigator: Mikami Tsuyoshi 苫小牧工業高等専門学校, 創造工学科, 准教授 (40321369)
• Co-Investigator(Kenkyū-buntansha): 米澤 一也 独立行政法人国立病院機構函館病院(臨床研究部), 臨床研究部, その他 (20301955)
• Research Collaborator: TAKAHASHI Hirotaka ; KOJIMA Yohichiro ; ARAKI Tsuyoshi ; HORIGUCHI Sakura
• Project Period (FY): 2014-04-01 – 2018-03-31
• Keywords: いびき / 睡眠時無呼吸症候群 / 機械学習 / 非定常性

Outline of Final Research Achievements

This study clarified the sound properties of all-night snores for the development of simple diagnosis tool for Sleep Apnea Syndrome (SAS). Many conventional studies have analyzed only partial data in all-night snores, and thus the results were different from each other.
In this study, a data clustering method is applied to the FFT spectra of snoring sounds to extract the representative properties intrinsic to SAS.
As a result, snoring sounds are quite various than expected in advance and thus it is difficult to discuss the acoustic properties of snoring sounds in SAS patients. On the other hand, it is also found that nonstationarity of post-apneic snoring sounds is higher than that of non-apneic snoring sounds.

Free Research Field

生体情報工学