Furutani Naoki, Nariya Yuta, Takahashi Tetsuya, Noto Sarah, Yang Albert C, Hirosawa Tetsu, Kameya Masafumi, Minabe Yoshio, Kikuchi Mitsuru
Department of Psychiatry and Neurobiology, Graduate School of Medical Science, Kanazawa University, Kanazawa, Japan.
Faculty of Medicine, The University of Tokyo, Tokyo, Japan.
Front Psychiatry. 2020 Sep 3;11:531801. doi: 10.3389/fpsyt.2020.531801. eCollection 2020.
Despite growing evidence of aberrant neuronal complexity in Alzheimer's disease (AD), it remains unclear how this variation arises. Neural oscillations reportedly comprise different functions depending on their own properties. Therefore, in this study, we investigated details of the complexity of neural oscillations by decomposing the oscillations into frequency, amplitude, and phase for AD patients. We applied resting-state magnetoencephalography (MEG) to 17 AD patients and 21 healthy control subjects. We first decomposed the source time series of the MEG signal into five intrinsic mode functions using ensemble empirical mode decomposition. We then analyzed the temporal complexities of these time series using multiscale entropy. Results demonstrated that AD patients had lower complexity on short time scales and higher complexity on long time scales in the alpha band in temporal regions of the brain. We evaluated the alpha band complexity further by decomposing it into amplitude and phase using Hilbert spectral analysis. Consequently, we found lower amplitude complexity and higher phase complexity in AD patients. Correlation analyses between spectral complexity and decomposed complexities revealed scale-dependency. Specifically, amplitude complexity was positively correlated with spectral complexity on short time scales, whereas phase complexity was positively correlated with spectral complexity on long time scales. Regarding the relevance of cognitive function to the complexity measures, the phase complexity on the long time scale was found to be correlated significantly with the Mini-Mental State Examination score. Additionally, we examined the diagnostic utility of the complexity characteristics using machine learning (ML) methods. We prepared a feature pool using multiple sparse autoencoders (SAEs), chose some discriminating features, and applied them to a support vector machine (SVM). Compared to the simple SVM and the SVM after feature selection (FS + SVM), the SVM with multiple SAEs (SAE + FS + SVM) had improved diagnostic accuracy. Through this study, we 1) advanced the understanding of neuronal complexity in AD patients using decomposed temporal complexity analysis and 2) demonstrated the effectiveness of combining ML methods with information about signal complexity for the diagnosis of AD.
尽管越来越多的证据表明阿尔茨海默病（AD）中存在异常的神经元复杂性，但这种变化是如何产生的仍不清楚。据报道，神经振荡根据其自身特性具有不同的功能。因此，在本研究中，我们通过将振荡分解为频率、振幅和相位，对AD患者神经振荡的复杂性细节进行了研究。我们对17名AD患者和21名健康对照者进行了静息态脑磁图（MEG）检查。我们首先使用总体经验模态分解将MEG信号的源时间序列分解为五个本征模态函数。然后，我们使用多尺度熵分析这些时间序列的时间复杂性。结果表明，AD患者在大脑颞区的α波段短时间尺度上复杂性较低，长时间尺度上复杂性较高。我们使用希尔伯特谱分析将α波段复杂性进一步分解为振幅和相位，从而进行评估。结果发现，AD患者的振幅复杂性较低，相位复杂性较高。频谱复杂性与分解后的复杂性之间的相关性分析显示出尺度依赖性。具体而言，短时间尺度上振幅复杂性与频谱复杂性呈正相关，而长时间尺度上相位复杂性与频谱复杂性呈正相关。关于认知功能与复杂性测量的相关性，发现长时间尺度上的相位复杂性与简易精神状态检查表得分显著相关。此外，我们使用机器学习（ML）方法检验了复杂性特征的诊断效用。我们使用多个稀疏自编码器（SAE）准备了一个特征池，选择了一些有区分性的特征，并将其应用于支持向量机（SVM）。与简单SVM和特征选择后的SVM（FS + SVM）相比，具有多个SAE的SVM（SAE + FS + SVM）的诊断准确性有所提高。通过这项研究，我们1）利用分解后的时间复杂性分析增进了对AD患者神经元复杂性的理解，2）证明了将ML方法与信号复杂性信息相结合用于AD诊断的有效性。
