| 独盟盟*,史周晰*,齐晓英**,陈学莹*,王顺增***.重度抑郁症患者脑电动态特征及其复杂性研究[J].高技术通讯(中文),2025,35(4):403~408 |
| 重度抑郁症患者脑电动态特征及其复杂性研究 |
| Research on the electroencephalogram dynamic characteristics and complexity of patients with major depressive disorder |
| |
| DOI： |
| 中文关键词: 抑郁症； 静息态脑电； 微状态； 熵； 机器学习 |
| 英文关键词: major depressive disorder, resting-state electroencephalogram, microstate, entropy, machine learning |
| 基金项目: |
| 作者 | 单位 | | 独盟盟* | (* 陕西科技大学数学与数据科学学院西安 710021)
( ** 延安大学医学院延安 716000)
( *** 南阳理工学院智能制造学院南阳 473004) | | 史周晰* | | | 齐晓英** | | | 陈学莹* | | | 王顺增*** | |
|
| 摘要点击次数: 6 |
| 全文下载次数: 5 |
| 中文摘要: |
| 重度抑郁症(major depressive disorder，MDD）患者大脑神经动态特性已发生异常，但其复杂特性尚未研究清楚。本文基于抑郁症患者和正常人的脑电数据，采用脑电微状态分析方法，提取脑电微状态特征和微状态时间序列的非线性复杂度特征（样本熵、排列熵等），探索抑郁症患者脑电时空特征和大脑功能异常变化。结果表明，MDD患者的脑电微状态存在明显异常。同时，抑郁症患者微状态序列的复杂性特征值均显著高于正常人。此外，基于微状态时间参数和复杂度的融合数据，本文方法的分类准确率达到82.7%，优于单一特征预测抑郁症。研究结果表明，脑电图(electroencephalogram，EEG)微状态参数和微状态序列的非线性复杂度特征可作为早期辅助诊断抑郁症的神经生理学标志物。 |
| 英文摘要: |
| The dynamic characteristics of brain neural activity in patients with major depressive disorder (MDD) have been found to be abnormal, but their complex characteristics have not been clearly studied. Based on the electroencephalogram（EEG） data of MDD patients and normal individuals, this paper uses the brain microstate analysis method to extract the features of brain microstates and the nonlinear complexity features of microstate time series (such as sample entropy, permutation entropy), exploring the spatiotemporal characteristics of EEG and abnormal changes in brain function in MDD patients. The results indicate that MDD patients have significant abnormalities in brain microstates. At the same time, the complexity characteristics of microstate sequences in MDD patients are significantly higher than those in normal individuals. Furthermore, based on the fusion data of microstate temporal parameters and complexity, the classification accuracy of the method proposed in this paper reached 82.7%, outperforming the prediction of depression using single features. The research results indicate that the nonlinear complexity features of EEG microstate parameters and microstate sequences can serve as neurophysiological markers for early auxiliary diagnosis of depression. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
