Related Experiment Video
Updated: Jun 9, 2025
11:15
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
Published on: June 27, 2013
33.7K
A Lightweight Multi-Mental Disorders Detection Method Using Entropy-Based Matrix from Single-Channel EEG Signals.
Jiawen Li1,2, Guanyuan Feng1, Jujian Lv1
1School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China.
Brain Sciences
|October 25, 2024
Summary
This study introduces a novel Electroencephalography (EEG) analysis method for early multi-mental disorder detection. By analyzing entropy features, it achieves high accuracy with minimal data, improving diagnosis for conditions like schizophrenia, epilepsy, and depression.
Area of Science:
- Neuroscience
- Computational Psychiatry
- Biomedical Engineering
Background:
- Mental health disorders present a growing global challenge, necessitating improved diagnostic tools.
- Current diagnostic methods for mental health conditions are often subjective and time-consuming.
- There is a critical need for objective, efficient, and early detection methods for multi-mental disorders.
Purpose of the Study:
- To develop a lightweight, data-efficient method for early detection of multiple mental disorders.
- To enhance diagnostic procedures and enable timely intervention for affected individuals.
- To explore the utility of Electroencephalography (EEG) signal analysis for mental health assessment.
Main Methods:
- Utilized Electroencephalography (EEG) signals as the primary data source.
- Applied Discrete Wavelet Decomposition (DWT) to acquire brain rhythms.
- Extracted various entropy measures (approximate, fuzzy, permutation, sample entropy) to create an entropy-based matrix.
- Employed machine learning classifiers (SVM, kNN, NB, GAM, LDA, DT) for disorder detection.
- Validated the method using public datasets for schizophrenia, epilepsy, and depression.
Main Results:
- Identified representative single-channel EEG signals for each disorder (O1 for schizophrenia, F3 for epilepsy, O2 for depression).
- Achieved high classification accuracies: 88.10% for schizophrenia, 75.47% for epilepsy, and 89.92% for depression.
- Demonstrated effective multi-mental disorder detection with minimal data input.
Conclusions:
- The proposed lightweight EEG analysis method offers a reliable approach for early multi-mental disorder detection.
- The method enhances the interpretability of entropy features in EEG signals.
- This approach advances understanding of the underlying mechanisms and pathological states of mental disorders, paving the way for improved patient outcomes.
