[Retracted] Classification of Bioinformatics EEG Data Signals to Identify Depressed Brain State Using CNN Model

Abstract

Patients suffering from severe depression may be precisely assessed using online EEG categorization and their progress tracked over time, minimizing the risk of danger and suicide. Online EEG categorization systems, on the other hand, suffer additional challenges in the absence of empirical oversight. A lack of effective decoupling between brain regions and neural networks occurs during brain disease attacks, resulting in EEG data with poor signal intensity, high noise, and nonstationary characteristics. CNN employs momentum SGD optimization. By using a tiny momentum decay factor, the literature’s starting strategy, and the same batch normalization, this work attempts to decrease model error. Before being utilized to form a training set, samples are shuffled, followed by validation and testing on the new samples in the set. An online EEG categorization system driven by a convolution neural network has been developed to do this. The approach is applied directly to the EEG input and is able to accurately and quickly identify depressed states without the need for preprocessing or feature extraction. The healthy control group and the depression control group had accuracy, sensitivity, and specificity of 99.08 percent, 98.77 percent, and 99.42 percent, respectively, in experiments on depression evaluation based on publicly accessible data. The machine learning technique based on feature extraction is often getting more and more complex, making it only suited for offline EEG categorization. While neural networks have become increasingly important in the study of artificial intelligence in recent years, they are still essentially black-box function approximations with limited interpretability. In addition, quantitative study of the neural network shows that depressed patients and healthy persons have remarkable dissimilarity between the right and left temporal lobe brain regions.

A Framework for Systematically Evaluating the Representations Learned by A Deep Learning Classifier from Raw Multi-Channel Electroencephalogram Data

“…Relative to previous studies performing automated diagnosis of MDD using raw EEG data with robust cross-validation techniques, our model obtained higher performance [78], and relative to studies using extracted features with traditional machine learning approaches and robust cross-validation techniques, our model obtained comparable or higher performance [27]. There were some studies that obtained higher test performance than our model using either raw EEG data [80], [81] or extracted features [3], [21], [24], [26]. However, it appears based on the descriptions of their cross-validation approaches that those studies allowed data from the same study participants to leak across training, validation, and test sets within the same folds.…”

Improving Multichannel Raw Electroencephalography-based Diagnosis of Major Depressive Disorder via Transfer Learning with Single Channel Sleep Stage Data*

“…Additionally, relative to [27], a study that used a robust cross-validation approach and manually engineered features, we also demonstrated an improvement. A number of studies using raw EEG [28], [29] and manually engineered features [30]–[33] did obtain higher classification performance than our approach. However, their cross-validation approaches are either not clearly described, or it seems that they employed cross-validation approaches that allowed data leakage between the training and test sets.…”

Identifying EEG Biomarkers of Depression with Novel Explainable Deep Learning Architectures

“…However, there was not a significant difference between M2 and M3 performance, which suggested that M3 was able to learn linearly separable features without dropping performance below that of M2. Many studies trained models that outperformed all three of our architectures for MDD classification [25,31,57,[64][65][66]. However, most of those studies used more traditional cross-validation approaches that allowed samples from the same recording to be distributed across training, validation, and test sets.…”