Citation

Kim T, Park U, Kang SW. Front. Psychiatry 2022; 13.

Copyright

(Copyright © 2022, Frontiers Media)

DOI

10.3389/fpsyt.2022.913890

PMID

unavailable

Abstract

Depression is a prevalent mental disorder in modern society, causing many people to suffer or even commit suicide. Psychiatrists and psychologists typically diagnose depression using representative tests, such as the Beck's Depression Inventory (BDI) and the Hamilton Depression Rating Scale (HDRS), in conjunction with patient consultations. Traditional tests, however, are time-consuming, can be trained on patients, and entailed a lot of clinician subjectivity. In the present study, we trained the machine learning models using sex and age-reflected z-score values of quantitative EEG (QEEG) indicators based on data from the National Standard Reference Data Center for Korean EEG, with 116 potential depression subjects and 80 healthy controls. The classification model has distinguished potential depression groups and normal groups, with a test accuracy of up to 92.31% and a 10-cross-validation loss of 0.13. This performance proposes a model with z-score QEEG metrics, considering sex and age as objective and reliable biomarkers for early screening for the potential depression. Copyright © 2022 Kim, Park and Kang.

Language: en

Keywords

adult; human; classification; age; female; male; training; depression; EEG; prediction; sex; mental disease; controlled study; psychiatrist; consultation; middle aged; sensitivity and specificity; diagnostic accuracy; electroencephalogram; Beck Depression Inventory; Article; biological marker; diagnostic test accuracy study; Hamilton Depression Rating Scale; machine learning; biomarker; independent component analysis