A simplified method for relapsing-remitting multiple sclerosis detection: Insights from resting EEG signals

Area of Science:

• Neuroscience
• Medical Diagnostics
• Signal Processing

Background:

• Multiple sclerosis (MS) is a debilitating autoimmune disease impacting the central nervous system.
• Early MS detection is crucial to mitigate neurological damage.
• Current diagnostic methods like MRI can be resource-intensive.

Purpose of the Study:

• To evaluate the feasibility of using electroencephalography (EEG) signals for detecting MS.
• To explore EEG as an accessible and non-invasive alternative to MRI for MS diagnosis.

Main Methods:

• Analysis of resting-state EEG signals from 17 MS patients and 27 healthy controls.
• Extraction of Power Spectral Density (PSD) features from 32-channel EEG data.
• Application of machine learning classifiers including LDA, SVM, CART, and kNN.

Main Results:

• Achieved 100% accuracy in MS detection using "Fp1" and "Pz" EEG channels with the LDA classifier.
• Identified significant differences in PSD features between MS patients and healthy individuals.
• Demonstrated effective MS detection using features from only two EEG channels.

Conclusions:

• EEG signal analysis, particularly PSD features from "Fp1" and "Pz" channels, provides an efficient method for MS detection.
• This approach offers a straightforward, non-invasive, and accessible diagnostic tool for MS.
• Further research is warranted to explore the full potential of EEG in MS diagnostics.