Multichannel EEG DeepNet for Depression Screening

There has been a marked rise in the number of cases of depression across the board in this dire COVID-19 condition. Never before have the issues of mental health, social isolation, and stress related to unemployment been so widely discussed as they are in the COVID-19 era. It is significantly more important to recognize and address intellectual disabilities at some point during pandemics since they can have severely negative consequences if left untreated.It is commonly known that 3.8% of people will experience depression, with 5.0% of adults and 5.7% of people over 60 predicted to be afflicted. Around 280 million individuals worldwide suffer from depression. Depression is a complex intellectual disability characterized by a person's poor mood and persistent feelings of hopelessness or misery. This intellectual ataxia-depression can be diagnosed with an electroencephalogram (EEG).The work focuses on using an automated EEG analysis for the primary screening of Major Depressive Disorder (MDD). The detection method that has been created relies on the combination of 1D convolution and recurrent neural networks (RNNs). The planned structure has been examined using neuroscan on 21 drug-free, symptomatic depressive patients and 24 normal people at the University of Arizona in the United States. With a false positive rate of 0.07 %, the model achieves an accuracy of 84%. RNN is incorporated into the model, which makes it easier to utilize, particularly when the length of the signal is uncertain. The suggested model has a lower temporal complexity and can be used in conjunction with other techniques for MDD screening.