Automatic Eyeblink and Muscular Artifact Detection and Removal From EEG Signals Using k-Nearest Neighbor Classifier and Long Short-Term Memory Networks

Ghosh, Rajdeep; Phadikar, Souvik; Deb, Nabamita; Sinha, Nidul; Das, Pranesh; Ghaderpour, Ebrahim

doi:10.1109/jsen.2023.3237383

Cited by 43 publications

(36 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fisher’s exact test was performed to assess the matching of gender among the study groups [ 23 ]. The accuracy of the test was evaluated using the area under a Receiver Operating Characteristic (ROC) curve (AUC) [ 24 ]. A correlation matrix was performed using the Spearman correlation coefficient to analyze the association between antibody activity levels [ 25 ].…”

Section: Methodsmentioning

confidence: 99%

A Preclinical Investigation on the Role of IgG Antibodies against Coagulant Components in Multiple Sclerosis

et al. 2023

View full text Add to dashboard Cite

The coagulation-inflammation interplay has recently been identified as a critical risk factor in the early onset of multiple sclerosis (MS), and antibodies against coagulation components have been recognized as contributing factors to thrombotic and inflammatory signaling pathways in diseases with overlapping symptoms to MS, paving the way for further research into their effects on MS pathology. The current study aimed to enlighten the role of IgG antibodies against coagulation components by performing a preclinical study, analyzing the astrocytic activation by purified IgG antibodies derived from 15 MS patients, and assessing their possible pro-inflammatory effects using a bead-based multiplexed immunoassay system. The results were compared with those obtained following astrocyte treatment with samples from 14 age- and gender-matched healthy donors, negative for IgG antibody presence. Serum samples collected from 167 MS patients and 40 age- and gender-matched controls were also analyzed for pro- and anti-inflammatory factors. According to our results, astrocytic activation in response to IgG treatment caused an upregulation of various pro-inflammatory factors, including cytokines, chemokines, and interleukins. Conversely, in serum samples from patients and controls, the pro-inflammatory factors did not differ significantly; medication may lower the levels in patients. Our findings suggest that antibodies may function as effectors in neuroinflammation and serve as targets for new treatments that eventually benefit novel therapeutic approaches.

show abstract

Section: Methodsmentioning

confidence: 99%

A Preclinical Investigation on the Role of IgG Antibodies against Coagulant Components in Multiple Sclerosis

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A proper series of epidemiological indicators was computed (area under the ROC curve, sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and diagnostic odds ratio). The ROC curves were compared by using DeLong’s method [ 30 , 31 ]. A level of p < 0.05 was deemed statistically significant.…”

Section: Methodsmentioning

confidence: 99%

Swept-Source Optical Coherence Tomography Thresholds in Differentiating Clinical Outcomes in a Real-World Cohort of Treatment-Naïve Multiple Sclerosis Patients

Rzepiński¹,

Kucharczuk²,

Tkaczyńska³

et al. 2023

Brain Sciences

View full text Add to dashboard Cite

This study aimed to determine whether peripapillary retinal nerve fiber layer (pRNFL) and ganglion cell–inner plexiform layer (GCIPL) thickness thresholds for single-time-point swept-source optical coherence tomography (SS-OCT) measures can differentiate the clinical outcomes of treatment-naïve people with multiple sclerosis (pwMS). A total of 275 patients with the clinically isolated syndrome (n = 23), benign MS (n = 8), relapsing–remitting MS (n = 185), secondary progressive MS (n = 28), primary progressive MS (n = 31), and with no history of optic neuritis were included. The mean Expanded Disability Status Scale (EDSS) score was 3.0 ± 1.6. The cut-off values of pRNFL (87 µm and 88 µm) and GCIPL (70 µm) thicknesses have been adopted from previous studies using spectral-domain OCT. PwMS with pRNFL ≤87 µm and ≤88 µm had a longer disease duration, more advanced disability, and more frequently progressive MS variants compared to those with greater pRNFL thicknesses. In distinguishing pwMS with disability greater than or equal to the mean EDSS score (EDSS ≥ 3) from those with less severe disability, GCIPL thickness <70 µm had the highest sensitivity, while pRNFL thickness ≤87 µm had the greatest specificity. The optimal cut-off values differentiating patients with EDSS ≥ 3 from those with less severe disability was 63 µm for GCIPL thickness and 93.5 µm for pRNFL thickness. In conclusion, pRNFL and GCIPL thickness thresholds for single-time-point SS-OCT measurements may be helpful in differentiating the disability status of treatment-naïve pwMS.

show abstract

“…It is pretty normal that EEG signals can be corrupted by many types of artifacts, defined as any undesired signal which affects the EEG signal whose origin cannot be identified in neural activity. Generators of these undesirable signals could be physiological, such as ocular artifacts (OAs such as eye blink, saccade movement, rapid eye movements), head or facial movements, muscle contraction, or cardiac activity [ 305 , 306 ]. Power-line noise, electrode movements (due to non-properly connected electrodes), and interference with other electrical instrumentation are non-physiological artifacts [ 307 ].…”

Section: Eeg Acquisition and Pre-processingmentioning

confidence: 99%

Connectivity Analysis in EEG Data: A Tutorial Review of the State of the Art and Emerging Trends

et al. 2023

View full text Add to dashboard Cite

Understanding how different areas of the human brain communicate with each other is a crucial issue in neuroscience. The concepts of structural, functional and effective connectivity have been widely exploited to describe the human connectome, consisting of brain networks, their structural connections and functional interactions. Despite high-spatial-resolution imaging techniques such as functional magnetic resonance imaging (fMRI) being widely used to map this complex network of multiple interactions, electroencephalographic (EEG) recordings claim high temporal resolution and are thus perfectly suitable to describe either spatially distributed and temporally dynamic patterns of neural activation and connectivity. In this work, we provide a technical account and a categorization of the most-used data-driven approaches to assess brain-functional connectivity, intended as the study of the statistical dependencies between the recorded EEG signals. Different pairwise and multivariate, as well as directed and non-directed connectivity metrics are discussed with a pros–cons approach, in the time, frequency, and information-theoretic domains. The establishment of conceptual and mathematical relationships between metrics from these three frameworks, and the discussion of novel methodological approaches, will allow the reader to go deep into the problem of inferring functional connectivity in complex networks. Furthermore, emerging trends for the description of extended forms of connectivity (e.g., high-order interactions) are also discussed, along with graph-theory tools exploring the topological properties of the network of connections provided by the proposed metrics. Applications to EEG data are reviewed. In addition, the importance of source localization, and the impacts of signal acquisition and pre-processing techniques (e.g., filtering, source localization, and artifact rejection) on the connectivity estimates are recognized and discussed. By going through this review, the reader could delve deeply into the entire process of EEG pre-processing and analysis for the study of brain functional connectivity and learning, thereby exploiting novel methodologies and approaches to the problem of inferring connectivity within complex networks.

show abstract

Automatic Eyeblink and Muscular Artifact Detection and Removal From EEG Signals Using k-Nearest Neighbor Classifier and Long Short-Term Memory Networks

Cited by 43 publications

References 41 publications

A Preclinical Investigation on the Role of IgG Antibodies against Coagulant Components in Multiple Sclerosis

A Preclinical Investigation on the Role of IgG Antibodies against Coagulant Components in Multiple Sclerosis

Swept-Source Optical Coherence Tomography Thresholds in Differentiating Clinical Outcomes in a Real-World Cohort of Treatment-Naïve Multiple Sclerosis Patients

Connectivity Analysis in EEG Data: A Tutorial Review of the State of the Art and Emerging Trends

Contact Info

Product

Resources

About