Electroencephalogram (EEG)-based automated depression diagnosis systems have been suggested for early and accurate detection of mood disorders. EEG signals are highly irregular, nonlinear, and nonstationary in nature and are traditionally studied from a linear viewpoint by means of statistical and frequency features. Since, linear metrics present certain limitations and nonlinear methods have proven to be an efficient tool in understanding the complexities of the brain in the identification of underlying behavior of biological signals, such as electrocardiogram, EEG and magnetoencephalogram and thus, can be applied to all nonstationary signals. Various nonlinear algorithms can be used in the analysis of EEG signals. In this research paper, we aim to develop a novel methodology for EEG-based depression diagnosis utilizing 2 advanced computational techniques: frequency-domain extended multivariate autoregressive (eMVAR) and deep learning (DL). We proposed a hybrid method comprising a pretrained ResNet-50 and long-short term memory (LSTM) to capture depression-specific information and compared with a strong conventional machine learning (ML) framework having eMVAR connectivity features. The following 8 causality measures, which interpret the interaction mechanisms among spectrally decomposed oscillations, were used to extract features from multivariate EEG time series: directed coherence (DC), directed transfer function (DTF), partial DC (PDC), generalized PDC (gPDC), extended DC (eDC), delayed DC (dDC), extended PDC (ePDC), and delayed PDC (dPDC). The classification accuracies were 84% with DC, 85% with DTF, 95.3% with PDC, 95.1% with gPDC, 84.8% with eDC, 84.6% with dDC, 84.2% with ePDC, and 95.9% with dPDC for the eMVAR framework. Through a DL framework (ResNet-50 + LSTM), the classification accuracy was achieved as 90.22%. The results demonstrate that our DL methodology is a competitive alternative to the strong feature extraction-based ML methods in depression classification.

基于脑电图 (EEG) 的自动抑郁症诊断系统已被建议用于早期准确检测情绪障碍。EEG 信号本质上是高度不规则、非线性和非平稳的，传统上通过统计和频率特征从线性角度进行研究。由于线性度量存在某些局限性，并且非线性方法已被证明是了解大脑在识别生物信号（例如心电图、EEG 和脑磁图）的潜在行为方面的复杂性的有效工具，因此可以应用于所有非平稳信号。各种非线性算法可用于分析 EEG 信号。在这篇研究论文中，我们的目标是利用 2 种先进的计算技术开发一种基于 EEG 的抑郁症诊断的新方法：频域扩展多元自回归 (eMVAR) 和深度学习 (DL)。我们提出了一种混合方法，包括预训练的 ResNet-50 和长短期记忆 (LSTM) 以捕获特定于抑郁症的信息，并与具有 eMVAR 连接功能的强大的传统机器学习 (ML) 框架进行比较。以下 8 种因果关系度量解释了频谱分解振荡之间的相互作用机制，用于从多元 EEG 时间序列中提取特征：定向相干 (DC)、定向传递函数 (DTF)、部分 DC (PDC)、广义 PDC (gPDC) )、扩展 DC (eDC)、延迟 DC (dDC)、扩展 PDC (ePDC) 和延迟 PDC (dPDC)。对于 eMVAR 框架，分类准确率为 DC 84%、DTF 85%、PDC 95.3%、gPDC 95.1%、eDC 84.8%、dDC 84.6%、ePDC 84.2% 和 dPDC 95.9%。通过深度学习框架（ResNet-50 + LSTM），分类准确率达到了 90.22%。结果表明，我们的 DL 方法是抑郁症分类中基于强特征提取的 ML 方法的一种有竞争力的替代方法。