Sleep Disorders Centre, National Hospital Organization Fukuoka National Hospital, Yakatabaru, Minmi-ku, Fukuoka City, Japan.
Department of Public Health, Graduate School of Medicine, Juntendo University, Hongo, Bunkyo-ku, Tokyo, Japan.
J Clin Sleep Med. 2019 Aug 15;15(8):1125-1133. doi: 10.5664/jcsm.7804.
Portable devices for home sleep apnea testing are often limited by their inability to discriminate sleep/wake status, possibly resulting in underestimations. Tracheal sound (TS), which can be visualized as a spectrogram, carries information about apnea/hypopnea and sleep/wake status. We hypothesized that image analysis of all-night TS recordings by a deep neural network (DNN) would be capable of detecting breathing events and classifying sleep/wake status. The aim of this study is to develop a DNN-based system for sleep apnea testing and validate it using a large sampling of polysomnography (PSG) data.
PSG examinations for the evaluation of sleep-disordered breathing (SDB) were performed for 1,852 patients: 1,548 PSG records were used to develop the system, and the remaining 304 records were used for validation. TS spectrogram images were obtained every 60 seconds and labeled with the PSG scoring results (breathing event and sleep/wake status), then introduced to DNN learning. Two different DNNs were trained for breathing status and sleep/wake status, respectively.
A DNN with convolutional layers showed the best performance for discriminating breathing status. The same DNN structure was trained for sleep/wake discrimination. In the validation study, the DNN analysis was capable of discriminating the sleep/wake status with reasonable accuracy. The diagnostic sensitivity, specificity, and area under the receiver operating characteristic curves for diagnosis of SDB with apnea-hypopnea index of > 5, 15, and 30 were 0.98, 0.76, and 0.99; 0.97, 0.90, and 0.99; and 0.92, 0.94, and 0.98, respectively.
The developed system using the TS DNN analysis has a good performance for SDB testing.
Nakano H, Furukawa T, Tanigawa T. Tracheal sound analysis using a deep neural network to detect sleep apnea. J Clin Sleep Med. 2019;15(8): 1125-1133.
家用睡眠呼吸暂停检测便携设备常因无法区分睡眠/觉醒状态而受到限制，这可能导致低估检测结果。气管音（TS）可被可视化作为声谱图，其携带关于呼吸暂停/低通气和睡眠/觉醒状态的信息。我们假设，通过深度神经网络（DNN）对整晚的 TS 记录进行图像分析，将能够检测呼吸事件并对睡眠/觉醒状态进行分类。本研究旨在开发一种基于 DNN 的睡眠呼吸暂停检测系统，并使用大量睡眠多导图（PSG）数据对其进行验证。
对 1852 名患有睡眠呼吸障碍（SDB）的患者进行了 PSG 检查：使用 1548 份 PSG 记录来开发系统，剩余的 304 份记录用于验证。每 60 秒获取一次 TS 声谱图图像，并根据 PSG 评分结果（呼吸事件和睡眠/觉醒状态）进行标记，然后引入 DNN 学习。分别为呼吸状态和睡眠/觉醒状态训练了两个不同的 DNN。
具有卷积层的 DNN 在区分呼吸状态方面表现最佳。使用相同的 DNN 结构对睡眠/觉醒状态进行分类。在验证研究中，DNN 分析能够以合理的准确度区分睡眠/觉醒状态。对于以呼吸暂停低通气指数 > 5、15 和 30 为诊断标准的 SDB 诊断，DNN 分析的诊断灵敏度、特异性和受试者工作特征曲线下面积分别为 0.98、0.76 和 0.99；0.97、0.90 和 0.99；0.92、0.94 和 0.98。
使用 TS DNN 分析开发的系统具有良好的睡眠呼吸暂停检测性能。
Nakano H, Furukawa T, Tanigawa T. Tracheal sound analysis using a deep neural network to detect sleep apnea. J Clin Sleep Med. 2019;15(8): 1125-1133.
