Computer Aided Diagnosis of Depression Using EEG Signal Processing

Major depressive disorder (MDD) emerges as a prominent factor leading to disability on a global scale and contributes significantly to the global burden of illness overall. The traditional method of detecting MDD is by continuous medical examination by a psychologist or psychiatrist. Our objective is to develop a non-invasive device which collects brain signals from the head and gets interfaced with a computer. The purpose of this paper is to develop a computer-aided diagnosis system that can identify depression in real time. The proposed system comprises three main components: the ADS1299 Front-End (FE) Printed Development Kit (PDK) evaluation board, a wearable electrode, and a desktop application. The primary approach involves the utilization of electroencephalogram (EEG) signal processing, along with the ADS1299 FE PDK evaluation board and deep learning techniques. This paper involves the utilisation of a publicly available dataset for training the deep learning model. The convolutional Neural Network (CNN) algorithm is used for the classification process. Absolute and relative powers are computed, and an asymmetry image matrix is generated based on the relative power values. By analysing the image matrix, the system can classify a patient as healthy or suffering from major depression based on higher or lower relative power, respectively. This paper seeks to make a valuable contribution to the academic sphere of the study of mental health diagnosis by leveraging advanced signal processing techniques and deep learning models for more accurate and efficient detection of depression.