Using deep learning to decode abnormal brain neural activity in MDD from single-trial EEG signals

References

• Ibrahim AK, Kelly SJ, Adams CE, et al. A systematic review of studies of depression prevalence in university students. J Psychiatr Res. 2013;47(3):391–400.
   PubMed Web of Science ®Google Scholar
• Spyrou IM, Frantzidis C, Bratsas C, et al. Geriatric depression symptoms coexisting with cognitive de-cline: a comparison of classification methodologies. Biomed Signal Process Control. 2016;25:118–129.
   Google Scholar
• World Health Organization: Depression and other common mental disorders: global health estimates. Geneva: World Health Organization; 2017.
   Google Scholar
• Malik J, Dahiya M, Kumari N. Brain wave frequency measurement in gamma wave range for ac-curate and early detection of depression. Int J Adv Manuf Technol. 2018;6:21.
   Google Scholar
• Penninx BW, Comijs HC. Depression and other common mental health disorders in old age. The epidemiology of aging. Dordrecht: Springer; 2012.
   Google Scholar
• Sharma M, Achuth PV, Deb D, et al. An automated diagnosis of depression using three-channel band-width-duration localized wavelet filter bank with EEG signals. Cognit Syst Res. 2018;52:508–520.
   Web of Science ®Google Scholar
• Liao SC, Wu CT, Huang HC, et al. Major depression detection from EEG signals using kernel eigen-filter-bank common spatial patterns. Sensors. 2017;17(6):1385.
   PubMed Web of Science ®Google Scholar
• Eshel N, Roiser JP. Reward and punishment processing in depression. Biol Psychiatry. 2010;68(2):118–124.
   PubMed Web of Science ®Google Scholar
• Becker MPI, Nitsch AM, Miltner WHR, et al. A single-trial estimation of the feedback-related negativity and its relation to BOLD responses in a time-estimation task. J Neurosci. 2014;34(8):3005–3012.
   PubMed Web of Science ®Google Scholar
• Carlson JM, Foti D, Mujica Parodi LR, et al. Ventral striatal and medial prefrontal BOLD activation is correlated with reward-related electrocortical activity: a combined ERP and fMRI study. Neuroimage. 2011;57(4):1608–1616.
   PubMed Web of Science ®Google Scholar
• Webb CA, Auerbach RP, Bondy E, et al. Reward-related neural predictors and mechanisms of symptom change in cognitive behavioral therapy for depressed adolescent girls. Biol Psychiatry Cogn Neurosci Neuroimaging. 2021;6(1):39–49.
   Google Scholar
• Webb CA, Auerbach RP, Bondy E, et al. Abnormal neural responses to feedback in depressed adolescents. J Abnorm Psychol. 2017;126(1):19–31.
   PubMed Web of Science ®Google Scholar
• Vahid A, Mückschel M, Stober S, et al. Applying deep learning to single-trial EEG data provides evidence for complementary theories on action control. Commun Biol. 2020;3(1):1–11.
   Google Scholar
• Ding Y, Chen X, Fu Q, et al. A depression recognition method for college students using deep integrated support vector algorithm. IEEE Access. 2020;8:75616–75629.
   Web of Science ®Google Scholar
• Bachmann M, Päeske L, Kalev K, et al. Methods for classifying depression in single channel EEG using linear and nonlinear signal analysis. Comput Methods Programs Biomed. 2018;155:11–17.
   Google Scholar
• Vahid A, Bluschke A, Roessner V, et al. Deep learning based on event-related EEG differentiates children with ADHD from healthy controls. JCM. 2019;8(7):1055.
   Google Scholar
• Ay B, Yildirim O, Talo M, et al. Automated depression detection using deep representation and sequence learning with EEG signals. J Med Syst. 2019;43(7):1–12.
   Google Scholar
• Sharma G, Parashar A, Joshi AM. DepHNN: a novel hybrid neural network for electroencephalogram (EEG) based screening of depression. Biomed Signal Process Control. 2021;66:102393.
   Web of Science ®Google Scholar
• Saeedi A, Saeedi M, Maghsoudi A, et al. Major depressive disorder diagnosis based on effective connectivity in EEG signals: a convolutional neural network and long short-term memory approach. Cogn Neurodyn. 2021;15(2):239–252.
   PubMedGoogle Scholar
• Li X, La R, Wang Y, et al. EEG-based mild depression recognition using convolutional neural network. Med Biol Eng Comput. 2019;57(6):1341–1352.
   PubMedGoogle Scholar
• Ancona M, Ceolini E, Öztireli C, et al. Towards better understanding of gradient based attribution methods for deep neural networks, arXiv preprint arXiv:1711.06104, 2017.
   Google Scholar
• Cavanagh JF, Bismark A, Frank MJ, et al. Larger error signals in major depression are associated with better avoidance learning. Front Psychol. 2011;2:331.
   Google Scholar
• Delorme A, Makeig S. EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods. 2004;134(1):9–21.
   PubMed Web of Science ®Google Scholar
• Lawhern VJ, Solon AJ, Waytowich NR, et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. J Neural Eng. 2018;15(5):056013.
   PubMed Web of Science ®Google Scholar
• Qian K, Kuromiya H, Zhang Z, et al. Teaching machines to know your depressive state: on physical activity in health and major depressive disorder. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE; 2019.
   Google Scholar
• Combrisson E, Jerbi K. Exceeding chance level by chance: the caveat of theoretical chance levels in brain signal classification and statistical assessment of decoding accuracy. J Neurosci Methods. 2015;250:126–136.
   PubMed Web of Science ®Google Scholar
• Carter CS, Braver TS, Barch DM, et al. Anterior cingulate cortex, error detection, and the online monitoring of performance. Science. 1998;280(5364):747–749.
   PubMed Web of Science ®Google Scholar
• Ridderinkhof KR, Ullsperger M, Crone EA, et al. The role of the medial frontal cortex in cognitive control. Science. 2004;306(5695):443–447.
   PubMed Web of Science ®Google Scholar