Hybrid Deep Shallow Network for Assessment of Depression Using Electroencephalogram Signals

Abstract

Depression is a mental health disorder characterised by persistently depressed mood or loss of interest in activities resulting impairment in daily life significantly. Electroencephalography (EEG) can assist with the accurate diagnosis of depression. In this paper, we present two different hybrid deep learning models for classification and assessment of patient suffering with depression. We have combined convolutional neural network with Gated recurrent units (RGUs), thus the proposed network is shallow and much smaller in size in comparison to its counter LSTM network. In addition to this, proposed approach is less sensitive to parameter settings. Extensive experiments on EEG dataset shows that the proposed hybrid model achieve highest accuracy, f1 score 99.66%, 99.93% and 98.87%, 99.12% for eye open and eye close dataset respectively in comparison to state of the art methods. Based on high performance, the proposed hybrid approach can be used for assessment of depression for clinical applications and can deployed remotely in hospital or private clinics for clinical evaluation.