Anxiety and Depression Diagnosis Method Based on Brain Networks and Convolutional Neural Networks

At present, only professional doctors can use the professional scales to diagnose depression and anxiety in clinical practice. In recent years, the problems of detecting the presence of anxiety or depression using Electroencephalography (EEG) has received attention as a way to implement assistant diagnosis, and some researchers explored that there are differences in the degree of prefrontal lateralization and functional connectivity of brain networks between patients with anxiety and depression and normal people. In this paper, we proposed a new approach that combines functional connectivity of brain networks and convolutional neural networks (CNN) for EEG-based anxiety and depression recognition. EEG data are collected from subjects consisting ten healthy controls and ten patients with anxiety or depression. In this way, we achieved 67.67% classification accuracy. It points out the way to further explore the application of functional connectivity of brain networks and deep learning technology in EEG about patients with anxiety and depression.