Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, MB, Canada.
Med Biol Eng Comput. 2010 Nov;48(11):1087-97. doi: 10.1007/s11517-010-0674-2. Epub 2010 Aug 24.
Sleep apnea is a common respiratory disorder during sleep, which is described as a cessation of airflow to the lungs that lasts at least for 10 s and is associated with at least 4% drop in blood's oxygen saturation level (S(a)O(2)). The current gold standard method for sleep apnea assessment is full-night polysomnography (PSG). However, its high cost, inconvenience for patients, and immobility have persuaded researchers to seek simple and portable devices to detect sleep apnea. In this article, we report on developing a new method for sleep apnea detection and monitoring, which only requires two data channels: tracheal breathing sounds and the pulse oximetry (S(a)O(2) signal). It includes an automated method that uses the energy of breathing sounds signals to segment the signals into sound and silent segments. Then, the sound segments are classified into breath, snore, and noise segments. The S(a)O(2) signal is analyzed automatically to find its rises and drops. Finally, a weighted average of different features extracted from breath segments, snore segments and S(a)O(2) signal are used to detect apnea and hypopnea events. The performance of the proposed approach was evaluated on the data of 66 patients recorded simultaneously with their full-night PSG study, and the results were compared with those of the PSG. The results show high correlation (0.96, P < 0.0001) between the outcomes of our system and those of the PSG. Also, the proposed method has been found to have sensitivity and specificity values of more than 91% in differentiating simple snorers from obstructive sleep apnea patients.
睡眠呼吸暂停是一种常见的睡眠呼吸障碍，其特征是肺部气流停止至少 10 秒，并伴有至少 4%的血氧饱和度 (S(a)O(2)) 下降。目前评估睡眠呼吸暂停的金标准方法是整夜多导睡眠图 (PSG)。然而，其高昂的成本、对患者的不便和不便利性促使研究人员寻求简单便携的设备来检测睡眠呼吸暂停。在本文中，我们报告了一种新的睡眠呼吸暂停检测和监测方法的开发，该方法仅需要两个数据通道：气管呼吸音和脉搏血氧饱和度 (S(a)O(2)信号)。它包括一种自动化方法，该方法使用呼吸音信号的能量将信号分割为有声和无声段。然后，将有声段分类为呼吸、打鼾和噪声段。自动分析 S(a)O(2)信号以找到其上升和下降。最后，从呼吸段、打鼾段和 S(a)O(2)信号中提取的不同特征的加权平均值用于检测呼吸暂停和低通气事件。该方法的性能在同时记录 66 名患者的整夜 PSG 研究数据上进行了评估，并将结果与 PSG 进行了比较。结果表明，我们的系统与 PSG 的结果具有高度相关性 (0.96，P < 0.0001)。此外，该方法在区分单纯性打鼾者和阻塞性睡眠呼吸暂停患者方面具有超过 91%的灵敏度和特异性值。
