Mahmud Tanvir, Khan Ishtiaque Ahmed, Ibn Mahmud Talha, Fattah Shaikh Anowarul, Zhu Wei-Ping, Ahmad M Omair
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:5580-5583. doi: 10.1109/EMBC44109.2020.9176433.
The topic of automatic detection of sleep apnea which is a respiratory sleep disorder, affecting millions of patients worldwide, is continuously being explored by researchers. Electroencephalogram signal (EEG) represents a promising tool due to its direct correlation to neural activity and ease of extraction. Here, an innovative approach is proposed to automatically detect apnea by incorporating local variations of temporal features for identifying the global feature variations over a broader window. An EEG data frame is divided into smaller sub-frames to effectively extract local feature variation within one larger frame. A fully convolutional neural network (FCNN) is proposed that will take each sub-frame of a single frame individually to extract local features. Following that, a dense classifier consisting of a series of fully connected layers is trained to analyze all the local features extracted from subframes for classifying the entire frame as apnea/non-apnea. Finally, a unique post-processing technique is applied which significantly improves accuracy. Both the EEG frame length and post-processing parameters are varied to find optimal detection conditions. Large-scale experimentation is executed on publicly available data of patients with varying apnea-hypopnea indices for performance evaluation of the suggested method.
睡眠呼吸暂停是一种影响全球数百万患者的呼吸睡眠障碍，其自动检测这一主题一直受到研究人员的不断探索。脑电图信号（EEG）因其与神经活动的直接关联以及易于提取，成为一种很有前景的工具。在此，提出了一种创新方法，通过纳入时间特征的局部变化来自动检测呼吸暂停，以识别更宽窗口内的全局特征变化。将一个脑电图数据帧划分为更小的子帧，以便在一个更大的帧内有效提取局部特征变化。提出了一种全卷积神经网络（FCNN），它将单独处理单个帧的每个子帧以提取局部特征。随后，训练一个由一系列全连接层组成的密集分类器，以分析从子帧中提取的所有局部特征，从而将整个帧分类为呼吸暂停/非呼吸暂停。最后，应用一种独特的后处理技术，显著提高了准确率。改变脑电图帧长度和后处理参数以找到最佳检测条件。对具有不同呼吸暂停低通气指数的患者的公开可用数据进行大规模实验，以评估所提方法的性能。
