Machine learning approaches in Detecting the Depression from Resting-state Electroencephalogram (EEG): A Review Study

TL;DR

This review examines machine learning methods applied to resting-state EEG data for detecting depression, highlighting recent advances, challenges, and guidelines for improving diagnostic accuracy in mental healthcare.

Contribution

It provides a comprehensive overview of EEG-based machine learning approaches for depression detection and discusses guidelines to enhance model reliability.

Findings

EEG-based machine learning shows promise for depression diagnosis

Resting-state EEG features can differentiate depressed from healthy individuals

Guidelines are proposed to improve model reliability and clinical applicability.

Abstract

In this paper, we aimed at reviewing several different approaches present today in the search for more accurate diagnostic and treatment management in mental healthcare. Our focus is on mood disorders, and in particular on the major depressive disorder (MDD). We are reviewing and discussing findings based on neuroimaging studies (MRI and fMRI) first to get the impression of the body of knowledge about the anatomical and functional differences in depression. Then, we are focusing on less expensive data-driven approach, applicable for everyday clinical practice, in particular, those based on electroencephalographic (EEG) recordings. Among those studies utilizing EEG, we are discussing a group of applications used for detecting of depression based on the resting state EEG (detection studies) and interventional studies (using stimulus in their protocols or aiming to predict the outcome of therapy). We conclude with a discussion and review of guidelines to improve the reliability of developed models that could serve improvement of diagnostic of depression in psychiatry.