A Hybrid Meta-Learning Model in Depression Classification of EEG

Read full text Summarise with VIRAT
Authors: M. Prathmesh, A. Nithis Kanna, K. Suruthika
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Depression is one of the most widespread mental wellbeing problems, which, being untreated, may lead to severe social, psychological and actual working issues.The most important aspect of DAC is early diagnosis, through which appropriate medical care, treatment, and planning is achieved.This paper introduces an offline machine learning-based depression detector using electroencephalogram (EEG) brainwave signals that were recorded in advance.The developed framework, unlike the traditional methods, where it is necessary to invoke the living user to provide a stimulus at the time of prediction (as in case of the BCI paradigms) analyzed previously obtained EEG data and, therefore, could predict them repeatably and effectively under clinical and research conditions.Using this system, researchers managed to identify key patterns and biomarkers in the brain in relation to a depressed state.Decision trees and artificial neural networks (ANNs) were trained and learned as some of the machine learning models to demonstrate strong classification results and to enhance the accuracy of the prediction.The findings indicated that the system could differentiate between depressed and non-depressed subjects with high accuracy which is an advantage to psychometric test as well as offering an objective and data-driven tool to complement a traditional psychiatrist diagnostic work.This structure can help the doctors diagnose depression earlier, which results in faster treatment interventions and favorable prognoses of the patient through accurate predictions in an offline fashion.

Fields of Study & Subjects

EEG and Brain-Computer Interfaces Emotion and Mood Recognition Artificial Intelligence in Healthcare

Publication details

Journal / source
Advances in intelligent systems research/Advances in Intelligent Systems Research
Pages
799–811
Publication date
1 April 2026
Language
EN
Document type
Book chapter