Alterations in Patients With First-Episode Depression in the Eyes-Open and Eyes-Closed Conditions: A Resting-State EEG Study

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 30; pp. 1019 - 1029
• Main Authors: Liu, Shuang, Liu, Xiaoya, Yan, Danfeng, Chen, Sitong, Liu, Yanli, Hao, Xinyu, Ou, Wenwen, Huang, Zhenni, Su, Fangyue, He, Feng, Ming, Dong
• Format: Journal Article
• Language: English
• Published: United States IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biomarkers; Classification; Complexity; Complexity theory; Depression; Depressive Disorder, Major - diagnosis; Discriminant analysis; EEG; Electroencephalography; eyes-closed; eyes-open; Feature extraction; high-frequency oscillation; Hospitals; Humans; Mental depression; Oscillators; Resting EEG; Support Vector Machine; Support vector machines
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2022.3166824

Altered resting-state EEG activity has been repeatedly reported in major depressive disorder (MDD), but no robust biomarkers have been identified until now. The poor consistency of EEG alterations may be due to inconsistent resting conditions; that is, the eyes-open (EO) and eyes-closed (EC) conditions. Here, we explored the effect of the EO and EC conditions on EEG biomarkers for discriminating MDD subjects and healthy control (HC) subjects. EEG data were recorded from 30 first-episode MDD and 26 HC subjects during an 8-min resting-state session. The features were extracted using spectral power, Lempel-Ziv complexity, and detrended fluctuation analysis. Significant features were further selected via the sequential backward feature selection algorithm. Support vector machine (SVM), logistic regression, and linear discriminate analysis were used to determine a better resting condition to provide more reliable estimates for identifying MDD. Compared with the HC group, we found that the MDD group exhibited widespread increased <inline-formula> <tex-math notation="LaTeX">\beta </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">\gamma </tex-math></inline-formula> powers (<inline-formula> <tex-math notation="LaTeX">{p} < 0.01 </tex-math></inline-formula>) in both conditions. In the EO condition, the MDD group showed increased complexity and scaling exponents in the <inline-formula> <tex-math notation="LaTeX">\alpha </tex-math></inline-formula> band relative to HC subjects (<inline-formula> <tex-math notation="LaTeX">{p} < 0.05 </tex-math></inline-formula>). The best classification performance of the combined feature sets was found in the EO condition, with the leave-one-out classification accuracy of 89.29%, sensitivity of 90.00%, and specificity of 88.46% using SVM with the linear kernel classifier when the threshold was set to 0.7, followed by the <inline-formula> <tex-math notation="LaTeX">\beta </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">\gamma </tex-math></inline-formula> spectral features with an average accuracy of 83.93%. Overall, EO and EC conditions indeed affected the between-group variance, and the EO condition is suggested as the more separable resting condition to identify depression. Specially, the <inline-formula> <tex-math notation="LaTeX">\beta </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">\gamma </tex-math></inline-formula> powers are suggested as potential biomarkers for first-episode MDD.