Jiao Meng, Song Changyue, Xian Xiaochen, Yang Shihao, Liu Feng
Department of Systems and EnterprisesStevens Institute of Technology Hoboken NJ 07030 USA.
Independent Researcher Irvine CA 92602 USA.
IEEE Open J Eng Med Biol. 2024 May 27;5:792-802. doi: 10.1109/OJEMB.2024.3405666. eCollection 2024.
Sleep Apnea (SA) is a prevalent sleep disorder with multifaceted etiologies that can have severe consequences for patients. Diagnosing SA traditionally relies on the in-laboratory polysomnogram (PSG), which records various human physiological activities overnight. SA diagnosis involves manual scoring by qualified physicians. Traditional machine learning methods for SA detection depend on hand-crafted features, making feature selection pivotal for downstream classification tasks. In recent years, deep learning has gained popularity in SA detection due to its capability for automatic feature extraction and superior classification accuracy. This study introduces a Deep Attention Network with Multi-Temporal Information Fusion (DAN-MTIF) for SA detection using single-lead electrocardiogram (ECG) signals. This framework utilizes three 1D convolutional neural network (CNN) blocks to extract features from R-R intervals and R-peak amplitudes using segments of varying lengths. Recognizing that features derived from different temporal scales vary in their contribution to classification, we integrate a multi-head attention module with a self-attention mechanism to learn the weights for each feature vector. Comprehensive experiments and comparisons between two paradigms of classical machine learning approaches and deep learning approaches are conducted. Our experiment results demonstrate that (1) compared with benchmark methods, the proposed DAN-MTIF exhibits excellent performance with 0.9106 accuracy, 0.9396 precision, 0.8470 sensitivity, 0.9588 specificity, and 0.8909 [Formula: see text] score at per-segment level; (2) DAN-MTIF can effectively extract features with a higher degree of discrimination from ECG segments of multiple timescales than those with a single time scale, ensuring a better SA detection performance; (3) the overall performance of deep learning methods is better than the classical machine learning algorithms, highlighting the superior performance of deep learning approaches for SA detection.
睡眠呼吸暂停（SA）是一种普遍存在的睡眠障碍，病因多方面，会给患者带来严重后果。传统上，SA的诊断依赖于实验室多导睡眠图（PSG），它会在夜间记录各种人体生理活动。SA诊断需要合格医生进行手动评分。传统的用于SA检测的机器学习方法依赖手工特征，这使得特征选择对于下游分类任务至关重要。近年来，深度学习因其自动特征提取能力和卓越的分类准确率在SA检测中受到欢迎。本研究引入了一种具有多时间信息融合的深度注意力网络（DAN-MTIF），用于使用单导联心电图（ECG）信号进行SA检测。该框架利用三个一维卷积神经网络（CNN）块，通过不同长度的片段从R-R间期和R波峰值幅度中提取特征。认识到从不同时间尺度导出的特征对分类的贡献不同，我们将多头注意力模块与自注意力机制相结合，以学习每个特征向量的权重。对经典机器学习方法和深度学习方法的两种范式进行了全面的实验和比较。我们的实验结果表明：（1）与基准方法相比，所提出的DAN-MTIF在每段水平上表现出色，准确率为0.9106，精确率为0.9396，灵敏度为0.8470，特异性为0.9588，F1分数为0.8909；（2）DAN-MTIF能够比单时间尺度更有效地从多个时间尺度的ECG片段中提取具有更高区分度的特征，确保更好的SA检测性能；（3）深度学习方法的整体性能优于经典机器学习算法，突出了深度学习方法在SA检测中的卓越性能。
