Event-related desynchronization and synchronization in multiple sclerosis

Machine learning and clinical EEG data for multiple sclerosis: A systematic review

Multiple Sclerosis (MS) is a chronic neuroinflammatory disease of the Central Nervous System (CNS) in which the body's immune system attacks and destroys the myelin sheath that protects nerve fibers, leading to a wide range of debilitating symptoms and causing disruption of axonal signal transmission. Accurate prediction, diagnosis, monitoring and treatment (PDMT) of MS are essential to improve patient outcomes. Recent advances in neuroimaging technologies, particularly electroencephalography (EEG), combined with machine learning (ML) techniques - including Deep Learning (DL) models - offer promising avenues for enhancing MS management. This systematic review synthesizes existing research on the application of ML and DL models to EEG data for MS. It explores the methodologies used, with a focus on DL architectures such as Convolutional Neural Networks (CNNs) and hybrid models, and highlights recent advancements in ML techniques and EEG technologies that have significantly improved MS diagnosis and monitoring. The review addresses the challenges and potential biases in using ML-based EEG analysis for MS. Strategies to mitigate these challenges, including advanced preprocessing techniques, diverse training datasets, cross-validation methods, and explainable Artificial Intelligence (AI), are discussed. Finally, the paper outlines potential future applications and trends in ML for MS management. This review underscores the transformative potential of ML-enhanced EEG analysis in improving MS management, providing insights into future research directions to overcome existing limitations and further improve clinical practice.

Feasibility of source-level motor imagery classification for people with multiple sclerosis

Objective.There is limited work investigating brain-computer interface (BCI) technology in people with multiple sclerosis (pwMS), a neurodegenerative disorder of the central nervous system. Present work is limited to recordings at the scalp, which may be significantly altered by changes within the cortex due to volume conduction. The recordings obtained from the sensors, therefore, combine disease-related alterations and task-relevant neural signals, as well as signals from other regions of the brain that are not relevant. The current study aims to unmix signals affected by multiple sclerosis (MS) progression and BCI task-relevant signals using estimated source activity to improve classification accuracy.Approach.Data was collected from eight participants with a range of MS severity and ten neurotypical participants. This dataset was used to report the classification accuracy of imagined movements of the hands and feet at the sensor-level and the source-level in the current study.K-means clustering of equivalent current dipoles was conducted to unmix temporally independent signals. The location of these dipoles was compared between MS and control groups and used for classification of imagined movement. Linear discriminant analysis classification was performed at each time-frequency point to highlight differences in frequency band delay.Main Results.Source-level signal acquisition significantly improved decoding accuracy of imagined movement vs rest and movement vs movement classification in pwMS and controls. There was no significant difference found in alpha (7-13 Hz) and beta (13-30 Hz) band classification delay between the neurotypical control and MS group, including imagery of limbs with weakness or paralysis.Significance.This study is the first to demonstrate the advantages of source-level analysis for BCI applications in pwMS. The results highlight the potential for enhanced clinical outcomes and emphasize the need for longitudinal studies to assess the impact of MS progression on BCI performance, which is crucial for effective clinical translation of BCI technology.

Determining event-related desynchronization onset latency of foot dorsiflexion in people with multiple sclerosis using the cluster depth tests

Multiple sclerosis (MS) is a disorder in which the body's immune system attacks structures of the central nervous system, resulting in lesions that can occur throughout the brain and spinal cord. Cortical lesions, in particular, can contribute to motor dysfunction. Walking disability is reported as the main impairment by people with MS (pwMS), often due to limited ankle movement. This study explored the event-related desynchronization (ERD) onset latency of the sensorimotor rhythms during foot dorsiflexion in pwMS computed using an objective and independent of human criterion method, as an electroencephalogram (EEG) based biomarker. EEG signals were recorded in eight persons with neither neurological condition nor motor dysfunction and eight pwMS with relapsing-remitting, primary progressive or secondary progressive MS. Recordings were divided into three groups: control, more affected lower limb and less affected lower limb. The ERD-onset latency was determined using a method based on the percent of ERD time course and the cluster depth tests. The median and interquartile range of the ERD-onset latency were 1186.0 (1100.0, 1250.0) ms; 1064.0 (1031.0, 1127.0) ms for the more and less affected groups respectively, whereas the median and interquartile range for the control group was 656.0 (472.2, 950.0) ms. There was a significant delay in the ERD-onset latencies of the pwMS groups compared to the control group (p<0.001 for both comparisons). These findings suggest that the ERD-onset latency computed using the proposed method could be used as an EEG biomarker to evaluate disease progression or therapeutic interventions in pwMS.

The contribution of EEG to assess and treat motor disorders in multiple sclerosis

OBJECTIVE

Electroencephalography (EEG) can highlight significant changes in spontaneous electrical activity of the brain produced by altered brain network connectivity linked to inflammatory demyelinating lesions and neuronal loss occurring in multiple sclerosis (MS). In this review, we describe the main EEG findings reported in the literature to characterize motor network alteration in term of local activity or functional connectivity changes in patients with MS (pwMS).

METHODS

A comprehensive literature search was conducted to include articles with quantitative analyses of resting-state EEG recordings (spectrograms or advanced methods for assessing spatial and temporal dynamics, such as coherence, theory of graphs, recurrent quantification, microstates) or dynamic EEG recordings during a motor task, with or without connectivity analyses.

RESULTS

In this systematic review, we identified 26 original articles using EEG in the evaluation of MS-related motor disorders. Various resting or dynamic EEG parameters could serve as diagnostic biomarkers of motor control impairment to differentiate pwMS from healthy subjects or be related to a specific clinical condition (fatigue) or neuroradiological aspects (lesion load).

CONCLUSIONS

We highlight some key EEG patterns in pwMS at rest and during movement, both suggesting an alteration or disruption of brain connectivity, more specifically involving sensorimotor networks.

SIGNIFICANCE

Some of these EEG biomarkers of motor disturbance could be used to design future therapeutic strategies in MS based on neuromodulation approaches, or to predict the effects of motor training and rehabilitation in pwMS.