Analysis of Electroencephalography (EEG) Signals Based on the Haar Wavelet Transformation

Contoyiannis, Yiannis; Papadopoulos, P.; Potirakis, Stelios M.; Kampitakis, Myron; Matiadou, Niki-Lina; Kosmidis, Efstratios K.

doi:10.1007/978-3-030-84122-5_10

Cited by 2 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multivariate multi-scale methodologies will also be employed, if indicated. Additionally, a criticality-based approach will also be investigated using the method of critical fluctuations and Haar-wavelet analysis (21).…”

Section: Must Predict Conceptual Frameworkmentioning

confidence: 99%

Multiple Sclerosis Treatment Strategy Optimization by PREdicting DIsease Progression through Linear and Non-linear Dynamics of Eeg Time-Series: The “MuST Predict” Conceptual Framework

Tseriotis

2023

Preprint

View full text Add to dashboard Cite

Gradual disability worsening in Multiple Sclerosis (MS) is indicative of confirmed progression that mostly involves progression independent of relapse activity (PIRA) and is associated with neurodegeneration. Insights from pathology reveal grey matter involvement (neocortex, hippocampus, spinal cord, and deep grey matter structures) and microglia activation in early stages of MS. Cortical lesions result in thinning and atrophy and are considered accurate predictors of disability progression and cognitive decline.Neuroimaging biomarkers, such as high-resolution 7T MR images and TSPO-PET, have been examined for the detection of cortical pathology linked to cognitive deficits and thus progression, but are limited in clinical practice due to availability, time constraints, and cost.Electroencephalography (EEG) emerges as a non-invasive, cost-effective tool that reflects cortical activity in MS. Its potential in monitoring cognitive impairment is explored by focusing on nonlinear EEG analysis. The MuST PREDICTTM project aims to extract linear and nonlinear EEG features, investigating their role in predicting disease progression and optimizing treatment. The study employs retrospective, cross-sectional, and prospective designs, utilizing EEGs from various MS forms, cognitive assessments, serum/cerebrospinal fluid biomarkers and neuroimaging. The methodology involves time-based and spectral feature extraction, employing artificial intelligence classifiers and brain criticality-based approaches.The conceptual framework of an innovative modality is herein presented, that would EEG for early MS progression detection. Standardization of the methodology could lead to the creation of a digital tool for better prognostication and treatment strategy optimization.

show abstract

Section: Must Predict Conceptual Frameworkmentioning

confidence: 99%