Kim Dongyeop, Park Ji Yong, Song Young Wook, Kim Euijin, Kim Sungkean, Joo Eun Yeon
Department of Neurology, Ewha Womans University Seoul Hospital, Ewha Womans University College of Medicine, Seoul, Republic of Korea.
Department of Applied Artificial Intelligence, Hanyang University, Ansan, Republic of Korea.
Sleep Med. 2024 Dec;124:323-330. doi: 10.1016/j.sleep.2024.09.041. Epub 2024 Sep 29.
This study aimed to investigate the neurophysiological effects of obstructive sleep apnea (OSA) using multi-channel sleep electroencephalography (EEG) through machine learning methods encompassing various analysis methodologies including power spectral analysis, network analysis, and microstate analysis.
Twenty participants with apnea-hypopnea index (AHI) ≥ 15 and 18 participants with AHI <15 were recruited. Overnight polysomnography was conducted concurrently with 19-channel EEG. Preprocessed EEG data underwent computation of relative spectral power. A weighted network based on graph theory was generated; and indices of strength, path length, eigenvector centrality, and clustering coefficient were calculated. Microstate analysis was conducted to derive four topographic maps. Machine learning techniques were employed to assess EEG features capable of differentiating two groups.
Among 71 features that showed significant differences between the two groups, seven exhibited good classification performance, achieving 88.3 % accuracy, 92 % sensitivity, and 84 % specificity. These features were power at C4 theta, P3 theta, P4 theta, and F8 gamma during NREM1 sleep and at Pz gamma during REM sleep from power spectral analysis; eigenvector centrality at F7 gamma during REM sleep from network analysis; and duration of microstate 4 during NREM2 sleep from microstate analysis. These seven EEG features were significantly correlated with polysomnographic parameters reflecting the severity of OSA.
The application of machine learning techniques and various EEG analytical methods resulted in a model that showed good performance in classifying moderate to severe OSA and highlights the potential of EEG to serve as a biomarker of functional changes in OSA.
本研究旨在通过机器学习方法，运用包括功率谱分析、网络分析和微状态分析等多种分析方法，利用多通道睡眠脑电图（EEG）研究阻塞性睡眠呼吸暂停（OSA）的神经生理效应。
招募了20名呼吸暂停低通气指数（AHI）≥15的参与者和18名AHI<15的参与者。同时进行整夜多导睡眠图检查和19通道脑电图检查。对预处理后的脑电图数据进行相对谱功率计算。生成基于图论的加权网络；并计算强度、路径长度、特征向量中心性和聚类系数等指标。进行微状态分析以得出四张地形图。采用机器学习技术评估能够区分两组的脑电图特征。
在两组之间显示出显著差异的71个特征中，有7个表现出良好的分类性能，准确率达到88.3%，灵敏度为92%，特异性为84%。这些特征包括：来自功率谱分析的非快速眼动睡眠1期C4θ、P3θ、P4θ和F8γ频段的功率以及快速眼动睡眠期Pzγ频段的功率；来自网络分析的快速眼动睡眠期F7γ频段的特征向量中心性；以及来自微状态分析的非快速眼动睡眠2期微状态4的持续时间。这七个脑电图特征与反映OSA严重程度的多导睡眠图参数显著相关。
机器学习技术和各种脑电图分析方法的应用产生了一个在对中度至重度OSA进行分类方面表现良好的模型，并突出了脑电图作为OSA功能变化生物标志物的潜力。
