Empirical mode decomposition processing to improve multifocal-visual-evoked-potential signal analysis in multiple sclerosis

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.

Individual differences in visual evoked potential latency are associated with variance in brain tissue volume in people with multiple sclerosis: An analysis of brain function-structure correlates

Visual evoked potentials (VEP) index visual pathway functioning, and are often used for clinical assessment and as outcome measures in people with multiple sclerosis (PwMS). VEPs may also reflect broader neural disturbances that extend beyond the visual system, but this possibility requires further investigation. In the present study, we examined the hypothesis that delayed latency of the P100 component of the VEP would be associated with broader structural changes in the brain in PwMS. We obtained VEP latency for a standard pattern-reversal checkerboard stimulus paradigm, in addition to Magnetic Resonance Imaging (MRI) measures of whole brain volume (WBV), gray matter volume (GMV), white matter volume (WMV), and T2-weighted fluid attenuated inversion recovery (FLAIR) white matter lesion volume (FLV). Correlation analyses indicated that prolonged VEP latency was significantly associated with lower WBV, GMV, and WMV, and greater FLV. VEP latency remained significantly associated with WBV, GMV, and WMV even after controlling for the variance associated with inter-ocular latency, age, time between VEP and MRI assessments, and other MRI variables. VEP latency delays were most pronounced in PwMS that exhibited low volume in both white and gray matter simultaneously. Furthermore, PwMS that had delayed VEP latency based on a clinically relevant cutoff (VEP latency ≥ 113 ms) in both eyes had lower WBV, GMV, and WMV and greater FLV in comparison to PwMS that had normal VEP latency in one or both eyes. The findings suggest that PwMS that have delayed latency in both eyes may be particularly at risk for exhibiting greater brain atrophy and lesion volume. These analyses also indicate that VEP latency may index combined gray matter and white matter disturbances, and therefore broader network connectivity and efficiency. VEP latency may therefore provide a surrogate marker of broader structural disturbances in the brain in MS.

Brain Microtubule Electrical Oscillations-Empirical Mode Decomposition Analysis

Microtubules (MTs) are essential cytoskeletal polymers of eukaryote cells implicated in various cell functions, including cell division, cargo transfer, and cell signaling. MTs also are highly charged polymers that generate electrical oscillations that may underlie their ability to act as nonlinear transmission lines. However, the oscillatory composition and time-frequency differences of the MT electrical oscillations have not been identified. Here, we applied the Empirical Mode Decomposition (EMD) to bovine brain MT sheet recordings to determine the number and fundamental frequencies of the Intrinsic Modes Functions (IMF) and evaluate their energetic contribution to the electrical signal. As previously reported, raw signals were obtained from cow brain MTs (Cantero et al. Sci Rep 6:27143, 2016), sampled, filtered, and subjected to signal decomposition from representative experiments. Filtered signals (200 Hz) allowed us to identify either six or seven IMFs. The reconstructed tracings faithfully resembled the original signals, with identifiable frequency peaks. To extend the analysis to obtain time-frequency information and the energy implicated in each IMF, we applied the Hilbert-Huang Transform (HHT) and the Continuous Wavelet Transform (CWT) to the same samples. The analyses disclosed the presence of more fundamental frequency peaks than initially reported and evidenced the advantages and disadvantages of each transform. The study indicates that the EMD is a robust approach to quantifying signal decomposition of brain MT oscillations and suggests novel similarities with human brain wave electroencephalogram (EEG) recordings. The evidence points to the potentially fundamental role of MT oscillations in brain electrical activity.

Comparison of Machine Learning Approaches to Improve Diagnosis of Optic Neuropathy Using Photopic Negative Response Measured Using a Handheld Device

The photopic negative response of the full-field electroretinogram (ERG) is reduced in optic neuropathies. However, technical requirements for measurement and poor classification performance have limited widespread clinical application. Recent advances in hardware facilitate efficient clinic-based recording of the full-field ERG. Time series classification, a machine learning approach, may improve classification by using the entire ERG waveform as the input. In this study, full-field ERGs were recorded in 217 eyes (109 optic neuropathy and 108 controls) of 155 subjects. User-defined ERG features including photopic negative response were reduced in optic neuropathy eyes (p < 0.0005, generalized estimating equation models accounting for age). However, classification of optic neuropathy based on user-defined features was only fair with receiver operating characteristic area under the curve ranging between 0.62 and 0.68 and F1 score at the optimal cutoff ranging between 0.30 and 0.33. In comparison, machine learning classifiers using a variety of time series analysis approaches had F1 scores of 0.58–0.76 on a test data set. Time series classifications are promising for improving optic neuropathy diagnosis using ERG waveforms. Larger sample sizes will be important to refine the models.

Changing Paradigms and Unmet Needs in Multiple Sclerosis: The Role of Clinical Neurophysiology

SUMMARY

Our increasing understanding of the immunopathogenesis of multiple sclerosis has led to the development of many disease-modifying therapies that have revolutionized the care of patients with relapsing forms of the disease. Our understanding of the pathophysiologic basis of progressive forms of the disease is much more limited but has dramatically changed over the past several decades. We are now on the verge of developing therapies that promote remyelination, reduce axonal loss, and restore axonal function. This progress is challenged by inadequate animal models of progressive disease and incomplete biomarkers of progression. In measuring central nervous system function, evoked potentials may have an advantage over biomarkers, which measure only pathologic change. Monitoring multifocal visual evoked potential amplitude may be one possible means of monitoring disease progression in multiple sclerosis. Additional clinical studies are required to document whether evoked potentials can adequately serve as effective biomarkers of progression.

Using advanced analysis of multifocal visual-evoked potentials to evaluate the risk of clinical progression in patients with radiologically isolated syndrome

This study aimed to assess the role of multifocal visual-evoked potentials (mfVEPs) as a guiding factor for clinical conversion of radiologically isolated syndrome (RIS). We longitudinally followed a cohort of 15 patients diagnosed with RIS. All subjects underwent thorough ophthalmological, neurological and imaging examinations. The mfVEP signals were analysed to obtain features in the time domain (SNR_min: amplitude, Lat_max: monocular latency) and in the continuous wavelet transform (CWT) domain (b_max: instant in which the CWT function maximum appears, N_max: number of CWT function maximums). The best features were used as inputs to a RUSBoost boosting-based sampling algorithm to improve the mfVEP diagnostic performance. Five of the 15 patients developed an objective clinical symptom consistent with an inflammatory demyelinating central nervous system syndrome during follow-up (mean time: 13.40 months). The (SNR_min) variable decreased significantly in the group that converted (2.74 ± 0.92 vs. 4.07 ± 0.95, p = 0.01). Similarly, the (b_max) feature increased significantly in RIS patients who converted (169.44 ± 24.81 vs. 139.03 ± 11.95 (ms), p = 0.02). The area under the curve analysis produced SNR_min and b_max values of 0.92 and 0.88, respectively. These results provide a set of new mfVEP features that can be potentially useful for predicting prognosis in RIS patients.

Empirical Mode Decomposition-Based Filter Applied to Multifocal Electroretinograms in Multiple Sclerosis Diagnosis

As multiple sclerosis (MS) usually affects the visual pathway, visual electrophysiological tests can be used to diagnose it. The objective of this paper is to research methods for processing multifocal electroretinogram (mfERG) recordings to improve the capacity to diagnose MS. MfERG recordings from 15 early-stage MS patients without a history of optic neuritis and from 6 control subjects were examined. A normative database was built from the control subject signals. The mfERG recordings were filtered using empirical mode decomposition (EMD). The correlation with the signals in a normative database was used as the classification feature. Using EMD-based filtering and performance correlation, the mean area under the curve (AUC) value was 0.90. The greatest discriminant capacity was obtained in ring 4 and in the inferior nasal quadrant (AUC values of 0.96 and 0.94, respectively). Our results suggest that the combination of filtering mfERG recordings using EMD and calculating the correlation with a normative database would make mfERG waveform analysis applicable to assessment of multiple sclerosis in early-stage patients.

A computer-aided diagnosis of multiple sclerosis based on mfVEP recordings

Introduction

The aim of this study is to develop a computer-aided diagnosis system to identify subjects at differing stages of development of multiple sclerosis (MS) using multifocal visual-evoked potentials (mfVEPs). Using an automatic classifier, diagnosis is performed first on the eyes and then on the subjects.

Patients

MfVEP signals were obtained from patients with Radiologically Isolated Syndrome (RIS) (n = 30 eyes), patients with Clinically Isolated Syndrome (CIS) (n = 62 eyes), patients with definite MS (n = 56 eyes) and 22 control subjects (n = 44 eyes). The CIS and MS groups were divided into two subgroups: those with eyes affected by optic neuritis (ON) and those without (non-ON).

Methods

For individual eye diagnosis, a feature vector was formed with information about the intensity, latency and singular values of the mfVEP signals. A flat multiclass classifier (FMC) and a hierarchical classifier (HC) were tested and both were implemented using the k-Nearest Neighbour (k-NN) algorithm. The output of the best eye classifier was used to classify the subjects. In the event of divergence, the eye with the best mfVEP recording was selected.

Results

In the eye classifier, the HC performed better than the FMC (accuracy = 0.74 and extended Matthew Correlation Coefficient (MCC) = 0.68). In the subject classification, accuracy = 0.95 and MCC = 0.93, confirming that it may be a promising tool for MS diagnosis.

Conclusion

In addition to amplitude (axonal loss) and latency (demyelination), it has shown that the singular values of the mfVEP signals provide discriminatory information that may be used to identify subjects with differing degrees of the disease.