AUTHOR=Li Mengqian , Liu Yuan , Liu Yan , Pu Changqin , Yin Ruocheng , Zeng Ziqiang , Deng Libin , Wang Xing TITLE=Resting-state EEG-based convolutional neural network for the diagnosis of depression and its severity JOURNAL=Frontiers in Physiology VOLUME=Volume 13 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.956254 DOI=10.3389/fphys.2022.956254 ISSN=1664-042X ABSTRACT=Purpose: To assess the value of Electroencephalogram (EEG)-based Convolutional Neural Network (CNN) method for diagnosis of depression and its severity in order to better serve depressed patients and at-risk populations. Methods: In this study, we used EEG-Based CNN to identify depression and valuated its severity. The EEG data were collected from depression patients and healthy people using the Nihon Kohden EEG-1200 system. Analytical processing of resting state EEG data using Python and Matlab software. The questionnaire included Self-Rating Anxiety Scale (SAS), Self-Rating Depression Scale (SDS), Symptom Check-List-90 (SCL-90), and Eysenck Personality Questionnaire (EPQ). Results: A total of 82 subject were included in this study, with 41 in depression group and 41 in healthy control group. The area under curve (AUC) of resting state EEG-based CNN in depression diagnosis was 0.74 (95%CI: 0.70-0.77) with an accuracy of 66.40%. In the depression group, the SDS, SAS, SCL-90 subscales, and N scores were significantly higher in major depression group than in non-major depression group (P<0.05). The AUC of the model in depression severity was 0.70 (95%CI: 0.65-0.75) with an accuracy of 66.93%. Correlation analysis revealed that major depression AI scores were significantly correlated with SAS scores (r=0.508, P=0.003) and SDS scores (r=0.765, P<0.001). Conclusion: Our model can accurately identify the depression-specific EEG signal, both in terms of depression diagnosis and in terms of its severity identification. It would eventually provide new strategies for early depression diagnosis and its severity.