A Domain Adversarial Learning Framework for Major Depression Disorder Diagnosis

The prompt recognition and timely intervention for depression are vital for attaining the most favorable therapeutic results. Notwithstanding its widespread occurrence, depression continues to be poorly understood within both clinical and research frameworks. Recent progress in deep learning methodologies, especially with the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs), has significantly improved the diagnostic capabilities for Major Depressive Disorder (MDD). However, CNNs and RNNs are limited in extracting essential brain spatial-temporal data during the classification process of MDD. Moreover, cross-subject variability poses an additional challenge in MDD classification. The proposed Domain Adversarial Learning Framework for Major Depression Disorder Diagnosis (MDD-DAL) overcomes the limitations of CNNs and RNNs by incorporating a spatial-temporal transformer architecture that can extract crucial brain spatial-temporal features from electroencephalogram (EEG) signals. Additionally, domain adversarial learning techniques enhance the model’s generalizability across variations in EEG data from different subjects. The model is validated using an MDD diagnosis dataset, achieving outstanding classification performance that showcases its advanced diagnostic capability. Our code is publicly accessible at: https://github.com/shaozheliu/MDD-DAL.