Interdisciplinary Program in Bioengineering, Seoul National University, Seoul, South Korea.
Department of Neuropsychiatry and Center for Sleep and Chronobiology, Seoul National University Hospital, Seoul, South Korea.
Comput Biol Med. 2018 Sep 1;100:123-131. doi: 10.1016/j.compbiomed.2018.06.028. Epub 2018 Jun 28.
Sleep apnea-hypopnea event detection has been widely studied using various biosignals and algorithms. However, most minute-by-minute analysis techniques have difficulty detecting accurate event start/end positions. Furthermore, they require hand-engineered feature extraction and selection processes. In this paper, we propose a new approach for real-time apnea-hypopnea event detection using convolutional neural networks and a single-channel nasal pressure signal. From 179 polysomnographic recordings, 50 were used for training, 25 for validation, and 104 for testing. Nasal pressure signals were adaptively normalized, and then segmented by sliding a 10-s window at 1-s intervals. The convolutional neural networks were trained with the data, which consisted of class-balanced segments, and were then tested to evaluate their event detection performance. According to a segment-by-segment analysis, the proposed method exhibited performance results with a Cohen's kappa coefficient of 0.82, a sensitivity of 81.1%, a specificity of 98.5%, and an accuracy of 96.6%. In addition, the Pearson's correlation coefficient between estimated apnea-hypopnea index (AHI) and reference AHI was 0.99, and the average accuracy of sleep apnea and hypopnea syndrome (SAHS) diagnosis was 94.9% for AHI cutoff values of ≥5, 15, and 30 events/h. Our approach could potentially be used as a supportive method to reduce event detection time in sleep laboratories. In addition, it can be applied to screen SAHS severity before polysomnography.
睡眠呼吸暂停低通气事件检测已经广泛研究使用各种生物信号和算法。然而，大多数逐分钟分析技术都难以检测准确的事件起始/结束位置。此外，它们需要手工设计特征提取和选择过程。在本文中，我们提出了一种使用卷积神经网络和单通道鼻压力信号进行实时呼吸暂停低通气事件检测的新方法。从 179 个多导睡眠记录中，50 个用于训练，25 个用于验证，104 个用于测试。鼻压力信号自适应归一化，然后以 1 秒间隔滑动 10 秒窗口进行分段。卷积神经网络用数据进行训练，这些数据由分段平衡的片段组成，然后进行测试以评估其事件检测性能。根据逐段分析，所提出的方法的表现结果为 Cohen's kappa 系数为 0.82，灵敏度为 81.1%，特异性为 98.5%，准确率为 96.6%。此外，估计的呼吸暂停低通气指数 (AHI) 与参考 AHI 之间的 Pearson 相关系数为 0.99，对于 AHI 截断值为≥5、15 和 30 事件/h 的睡眠呼吸暂停和低通气综合征 (SAHS) 诊断，平均准确率为 94.9%。我们的方法可以作为一种支持方法，以减少睡眠实验室中的事件检测时间。此外，它可以用于在多导睡眠图检查前筛选 SAHS 严重程度。
