文献类型：期刊文献

英文题名：Research on the Method of Depression Detection by Single-Channel Electroencephalography Sensor

作者：Lei, Xue[1];Ji, Weidong[2,3];Guo, Jingzhou[1];Wu, Xiaoyue[1];Wang, Huilin[4];Zhu, Lina[1];Chen, Liang[1]

机构：[1]East China Univ Sci & Technol, Sch Business, Shanghai, Peoples R China;[2]East China Normal Univ, Mental Hlth Ctr, Shanghai, Peoples R China;[3]Shanghai Changning Mental Hlth Ctr, Shanghai, Peoples R China;[4]Shanghai Fujia Cultural Dev Co Ltd, Shanghai, Peoples R China

年份：2022

卷号：13

外文期刊名：FRONTIERS IN PSYCHOLOGY

收录：;WOS:【SSCI(收录号:WOS:000832920000001)】；

基金：Funding This research was supported by the Research Project of Shanghai Science and Technology Commission (20dz2260300), Fundamental Research Funds for the Central Universities, and Research Funds for Shanghai Health Commission for Academic Leader Training (Grant No. GWV-10.2-XD30).

语种：英文

外文关键词：depression detection; state depression; EEG sensor; PHQ-9; HAM-D; house-tree-person (HTP) drawing test

摘要：Depression is a common mental health illness worldwide that affects our quality of life and ability to work. Although prior research has used EEG signals to increase the accuracy to identify depression, the rates of underdiagnosis remain high, and novel methods are required to identify depression. In this study, we built a model based on single-channel, dry-electrode EEG sensor technology to detect state depression, which measures the intensity of depressive feelings and cognitions at a particular time. To test the accuracy of our model, we compared the results of our model with other commonly used methods for depression diagnosis, including the PHQ-9, Hamilton Depression Rating Scale (HAM-D), and House-Tree-Person (HTP) drawing test, in three different studies. In study 1, we compared the results of our model with PHQ-9 in a sample of 158 senior high students. The results showed that the consistency rate of the two methods was 61.4%. In study 2, the results of our model were compared with HAM-D among 71 adults. We found that the consistency rate of state-depression identification by the two methods was 63.38% when a HAM-D score above 7 was considered depression, while the consistency rate increased to 83.10% when subjects showed at least one depressive symptom (including depressed mood, guilt, suicide, lack of interest, retardation). In study 3, 68 adults participated in the study, and the results revealed that the consistency rate of our model and HTP drawing test was 91.2%. The results showed that our model is an effective means to identify state depression. Our study demonstrates that using our model, people with state depression could be identified in a timely manner and receive interventions or treatments, which may be helpful for the early detection of depression.