Depression Diagnosis Modeling With Advanced Computational Methods: Frequency-Domain eMVAR and Deep Learning

Abstract

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.

Tendencias y perspectivas en la detección de depresión mediante el análisis de señales Electroencefalográficas (EEG): una Revisión Sistemática de la Literatura.

“…Los clasificadores utilizados fueron SVM, Naive Bayes, K-vecino más cercano y análisis discriminante lineal, de los cuales Naive Bayes fue el de mayor precisión [Avots et al, 2022]. Un estudio con una muestra balanceada de 30 sujetos, desarrolló un un método híbrido utilizando la arquitectura ResNet-50 preentrenado y una memoria a corto plazo (LSTM) para capturar información específica de la depresión y posteriormente se compara con un marco de Aprendizaje Automático convencional que tiene características de conectividad eMVAR la cual descompone las señales del EEG en patrones espaciales, que se extraen de 2 clases, se construye un vector de características y se usa como entrada para el clasificador para ambos marcos obteniendo una precisión del 95.9% [Uyulan et al, 2022].…”

Design of MEG-Based Brain-Machine Interface Control Methodology Through Time-Varying Cortical Neural Connectivity & Extreme Learning Machine

“… PDC quantifies the direct influence from time-series j to time-series i , after discounting the effect of all the other time series. The square exponents enhance the accuracy and stability of the estimates while the denominator part permits the normalization of outgoing connections by the inflows [47].…”

A comprehensive review for machine learning on neuroimaging in obsessive-compulsive disorder

“…In a study conducted in 2023, structural MRI images were utilized to predict aspects of late-life depression, including anhedonia, suicidal tendencies, appetite, sleep disturbances, and anxiety (Cao et al, 2023). An EEG-based automated diagnostic system for depression has been suggested for early and accurate detection of mood disorders (Uyulan et al, 2022). In addition to artificial intelligence research in the field of neuroimaging mentioned above, studies analyzing patients' voices have also become a focal point in the diagnosis of depression due to the often pronounced changes in energy, communication abilities, and emotions seen in individuals with this condition.…”