Multimodal Machine Learning Framework Combining EEG and Physiological Signals for Mental Health Diagnosis: A Review

Read full text Summarise with VIRAT
Authors: Pijush Kanti Ghosh, Rakesh Kumar, Momita Kumari, Nishant Goyal, Shalini Mahato
Cited by: 0
References: 22

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

The prevalence of mental health issues like anxiety and depression is increasing globally.An early detection can play a major role in improving treatment results.Electroencephalogram(EEG) and physiological signals are combined in multimodal machine learning frameworks to provide a strong and reliable approach for diagnosing and predicting mental health condition accurately.While physiological signals such as Heart Rate Variability (HRV), Galvanic Skin Response (GSR), and electrocardiogram (ECG) show how the body reacts to emotional states, EEG represents brain activity.A comprehensive view of both physical and mental health can be achieved by integrating these modalities.When physiological signals are combined with EEG, machine learning improves multimodal diagnosis by efficiently capturing emotional and cognitive patterns.The study shows that best networks for accurate diagnosis are SVM, CNN, and hybrid networks.This framework outperforms single-modality approaches by using classifiers like CNN and SVM, as well as time-frequency and nonlinear statistical methods for feature extraction.Effective stress predictors include physiological indicators with high explanatory power and ease of collection, such as skin response and heart rate.Study indicates that combining body and brain signals enhances diagnostic accuracy and supports objective, early detection of mental health conditions.

Fields of Study & Subjects

Emotion and Mood Recognition EEG and Brain-Computer Interfaces Heart Rate Variability and Autonomic Control

Publication details

Journal / source
Advances in engineering research/Advances in Engineering Research
Pages
357–368
Publication date
30 March 2026
Language
EN
Document type
Book chapter