A Hybrid Approach for MS Diagnosis Through Nonlinear EEG Descriptors and Metaheuristic Optimized Classification Learning

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

BACKGROUND AND OBJECTIVE

Multiple sclerosis (MS) is a neurodegenerative autoimmune disease affecting the central nervous system, leading to various neurological symptoms. Early detection is paramount to prevent enduring damage during MS episodes. Although magnetic resonance imaging (MRI) is a common diagnostic tool, this study aims to explore the feasibility of using electroencephalography (EEG) signals for MS detection, considering their accessibility and ease of application compared to MRI.

METHODS

The study involved the analysis of EEG signals during rest from 17 MS patients and 27 healthy volunteers to investigate MS-healthy patterns. Power spectral density features (PSD) were extracted from the 32-channel EEG signals. The study employed Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Classification and Regression Trees (CART), and k-Nearest Neighbor (kNN) classifiers to identify channels with the highest accuracy. Notably, the study achieved 100% accuracy in MS detection using the "Fp1" and "Pz" channels with the LDA classifier. A statistical analysis, utilizing the independent sample t-test, was conducted to explore whether PSD features of these channels differed significantly between healthy individuals and those with MS.

RESULTS

The results of the study demonstrate that effective detection of MS can be achieved using PSD features from only two channels of the EEG signal. Specifically, the "Fp1" and "Pz" channels exhibited 100% accuracy in MS detection with the LDA classifier. The statistical analysis further explored and confirmed the significant differences in PSD features between healthy individuals and MS patients.

CONCLUSION

The study concludes that the proposed method, utilizing PSD features from specific EEG channels, offers a straightforward and efficient diagnostic approach for the effective detection of MS. The findings suggest the potential utility of EEG signals as a non-invasive and accessible alternative for MS detection, highlighting the importance of further research in this direction.

Examining electroencephalogram signatures of people with multiple sclerosis using a nonlinear dynamics approach: a systematic review and bibliographic analysis

Background

Considering that brain activity involves communication between millions of neurons in a complex network, nonlinear analysis is a viable tool for studying electroencephalography (EEG). The main objective of this review was to collate studies that utilized chaotic measures and nonlinear dynamical analysis in EEG of multiple sclerosis (MS) patients and to discuss the contributions of chaos theory techniques to understanding, diagnosing, and treating MS.

Methods

Using the preferred reporting items for systematic reviews and meta-analysis (PRISMA), the databases EbscoHost, IEEE, ProQuest, PubMed, Science Direct, Web of Science, and Google Scholar were searched for publications that applied chaos theory in EEG analysis of MS patients.

Results

A bibliographic analysis was performed using VOSviewer software keyword co-occurrence analysis indicated that MS was the focus of the research and that research on MS diagnosis has shifted from conventional methods, such as magnetic resonance imaging, to EEG techniques in recent years. A total of 17 studies were included in this review. Among the included articles, nine studies examined resting-state, and eight examined task-based conditions.

Conclusion

Although nonlinear EEG analysis of MS is a relatively novel area of research, the findings have been demonstrated to be informative and effective. The most frequently used nonlinear dynamics analyses were fractal dimension, recurrence quantification analysis, mutual information, and coherence. Each analysis selected provided a unique assessment to fulfill the objective of this review. While considering the limitations discussed, there is a promising path forward using nonlinear analyses with MS data.

Multiple Sclerosis Diagnosis Using Machine Learning and Deep Learning: Challenges and Opportunities

Multiple Sclerosis (MS) is a disease that impacts the central nervous system (CNS), which can lead to brain, spinal cord, and optic nerve problems. A total of 2.8 million are estimated to suffer from MS. Globally, a new case of MS is reported every five minutes. In this review, we discuss the proposed approaches to diagnosing MS using machine learning (ML) published between 2011 and 2022. Numerous models have been developed using different types of data, including magnetic resonance imaging (MRI) and clinical data. We identified the methods that achieved the best results in diagnosing MS. The most implemented approaches are SVM, RF, and CNN. Moreover, we discussed the challenges and opportunities in MS diagnosis to improve AI systems to enable researchers and practitioners to enhance their approaches and improve the automated diagnosis of MS. The challenges faced by automated MS diagnosis include difficulty distinguishing the disease from other diseases showing similar symptoms, protecting the confidentiality of the patients' data, achieving reliable ML models that are also easily understood by non-experts, and the difficulty of collecting a large reliable dataset. Moreover, we discussed several opportunities in the field such as the implementation of secure platforms, employing better AI solutions, developing better disease prognosis systems, combining more than one data type for better MS prediction and using OCT data for diagnosis, utilizing larger, multi-center datasets to improve the reliability of the developed models, and commercialization.