A New Feature with the Potential to Detect the Severity of Obstructive Sleep Apnoea via Snoring Sound Analysis
A New Feature with the Potential to Detect the Severity of Obstructive Sleep Apnoea via Snoring Sound Analysis
复制标题
DOI：
10.3390/ijerph17082951
复制
发表时间：
2020-04-01
影响因子：
--
通讯作者：
Miyazaki, Yasunari
中科院分区：
文献类型：
--
作者：
Hayashi, Shota;Tamaoka, Meiyo;Miyazaki, Yasunari
阻塞性睡眠呼吸暂停（OSA）的严重程度通过多导睡眠图（PSG）进行诊断，在此期间，患者通过20多个生理传感器进行夜间监测。这些传感器经常打扰患者，并可能影响患者的睡眠和呼吸暂停。本研究旨在探讨一种通过分析患者鼾声来检测OSA严重程度的方法。使用放置在患者床边的麦克风，记录22名参与者的鼾声和呼吸声，同时接受PSG治疗。我们检查了打鼾和呼吸声音的一些特征，并检查了这些特征与打鼾特异性呼吸暂停低通气指数（ssAHI）之间的相关性，ssAHI定义为打鼾发作前一小时内呼吸暂停和低通气事件的次数。统计分析表明，ssAHI与Mel频率倒谱系数（MFCC）和体积信息（VI）呈正相关。根据聚类结果，将轻度OSA患者的轻度鼾声发作和轻度OSA患者的鼾声发作主要分为聚类1。重度OSA患者重度鼾音发作和重度OSA患者重度鼾音发作的聚类结果主要分为聚类2。我们识别的打鼾声音的特征有可能检测出阻塞性睡眠呼吸暂停综合症的严重程度。
The severity of obstructive sleep apnoea (OSA) is diagnosed with polysomnography (PSG), during which patients are monitored by over 20 physiological sensors overnight. These sensors often bother patients and may affect patients' sleep and OSA. This study aimed to investigate a method for analyzing patient snore sounds to detect the severity of OSA. Using a microphone placed at the patient's bedside, the snoring and breathing sounds of 22 participants were recorded while they simultaneously underwent PSG. We examined some features from the snoring and breathing sounds and examined the correlation between these features and the snore-specific apnoea-hypopnea index (ssAHI), defined as the number of apnoea and hypopnea events during the hour before a snore episode. Statistical analyses revealed that the ssAHI was positively correlated with the Mel frequency cepstral coefficients (MFCC) and volume information (VI). Based on clustering results, mild snore sound episodes and snore sound episodes from mild OSA patients were mainly classified into cluster 1. The results of clustering severe snore sound episodes and snore sound episodes from severe OSA patients were mainly classified into cluster 2. The features of snoring sounds that we identified have the potential to detect the severity of OSA.