Eli Kinney-lang

Expanding the (kaleido)scope: exploring current literature trends for translating electroencephalography (EEG) based brain-computer interfaces for motor rehabilitation in children.

Rehabilitation applications using brain-computer interfaces (BCI) have recently shown encouraging results for motor recovery. Effective BCI neurorehabilitation has been shown to exploit neuroplastic properties of the brain through mental imagery tasks. However, these applications and results are currently restricted to adults. A systematic search reveals there is essentially no literature describing motor rehabilitative BCI applications that use electroencephalograms (EEG) in children, despite advances in such applications with adults. Further inspection highlights limited literature pursuing research in the field, especially outside of neurofeedback paradigms. Then the question naturally arises, do current literature trends indicate that EEG based BCI motor rehabilitation applications could be translated to children? To provide further evidence beyond the available literature for this particular topic, we present an exploratory survey examining some of the indirect literature related to motor rehabilitation BCI in children. Our goal is to establish if evidence in the related literature supports research on this topic and if the related studies can help explain the dearth of current research in this area. The investigation found positive literature trends in the indirect studies which support translating these BCI applications to children and provide insight into potential pitfalls perhaps responsible for the limited literature. Careful consideration of these pitfalls in conjunction with support from the literature emphasize that fully realized motor rehabilitation BCI applications for children are feasible and would be beneficial. •xa0 BCI intervention has improved motor recovery in adult patients and offer supplementary rehabilitation options to patients. •xa0 A systematic literature search revealed that essentially no research has been conducted bringing motor rehabilitation BCI applications to children, despite advances in BCI. •xa0 Indirect studies discovered from the systematic literature search, i.e. neurorehabilitation in children via BCI for autism spectrum disorder, provide insight into translating motor rehabilitation BCI applications to children. •xa0 Translating BCI applications to children is a relevant, important area of research which is relatively barren.

Analysis of EEG networks and their correlation with cognitive impairment in preschool children with epilepsy

Objective: Cognitive impairment (CI) is common in children with epilepsy and can have devastating effects on their quality of life and that of their family. Early identification of CI is a priority to improve outcomes, but the current gold standard of detection with psychometric assessment is resource intensive and not always available. This paper proposes a novel technique of network analysis using routine clinical electroencephalography (EEG) to help identify CI in children with early-onset epilepsy (CWEOE) (0-5 y.o.). Methods: We analyzed functional networks from routinely acquired EEGs of 51 newly diagnosed CWEOE from a prospective population-based study. Combinations of connectivity metrics (e.g. phase-slope index (PSI)) with sub-network analysis (e.g. cluster-span threshold (CST)) identified significant correlations between network properties and cognition scores via rank correlation analysis with Kendall’s τ. Predictive properties were investigated using a 5-fold cross-validated K-Nearest Neighbor classification model with normal cognition, mild/moderate CI and severe CI classes. Results: Phase-dependent connectivity metrics had higher sensitivity to cognition scores, with sub-networks identifying significant functional network changes over a broad range of spectral frequencies. Approximately 70.5% of all children were appropriately classified as normal cognition, mild/moderate CI or severe CI using CST network features. CST classification predicted CI classes 55% better than chance, and reduced misclassification penalties by half. Conclusions: CI in CWEOE can be detected with sensitivity at 85% (with respect to identifying either mild/moderate or severe CI) and specificity of 84%, by EEG network analysis. Significance: This study outlines a data-driven methodology for identifying candidate biomarkers of CI in CWEOE from network features. Following additional replication, the proposed method and its use of routinely acquired EEG forms an attractive proposition for supporting clinical assessment of CI.

Tensor-driven extraction of developmental features from varying paediatric EEG datasets

OBJECTIVEnConstant changes in developing childrens brains can pose a challenge in EEG dependant technologies. Advancing signal processing methods to identify developmental differences in paediatric populations could help improve function and usability of such technologies. Taking advantage of the multi-dimensional structure of EEG data through tensor analysis may offer a framework for extracting relevant developmental features of paediatric datasets. A proof of concept is demonstrated through identifying latent developmental features in resting-state EEG.nnnAPPROACHnThree paediatric datasets ([Formula: see text]) were analyzed using a two-step constrained parallel factor (PARAFAC) tensor decomposition. Subject age was used as a proxy measure of development. Classification used support vector machines (SVM) to test if PARAFAC identified features could predict subject age. The results were cross-validated within each dataset. Classification analysis was complemented by visualization of the high-dimensional feature structures using t-distributed stochastic neighbour embedding (t-SNE) maps.nnnMAIN RESULTSnDevelopment-related features were successfully identified for the developmental conditions of each dataset. SVM classification showed the identified features could accurately predict subject at a significant level above chance for both healthy and impaired populations. t-SNE maps revealed suitable tensor factorization was key in extracting the developmental features.nnnSIGNIFICANCEnThe described methods are a promising tool for identifying latent developmental features occurring throughout childhood EEG.

Elucidating age-specific patterns from background electroencephalogram pediatric datasets via PARAFAC

Brain-computer interfaces (BCI) have the potential to provide non-muscular rehabilitation options for children. However, progressive changes in electrophysiology throughout development may pose a potential barrier in the translation of BCI rehabilitation schemes to children. Tensors and multiway analysis could provide tools which help characterize subtle developmental changes in electroencephalogram (EEG) profiles of children, thus supporting translation of BCI paradigms. Spatial, spectral and subject information of age-matched pediatric subjects in two EEG datasets were used to form 3-dimensional tensors for use in parallel factor analysis (PARAFAC) and direct projection comparison. Within dataset cross-validation results indicate PARAFAC can extract age-sensitive factors which accurately predict subject age in 90% of cases. Cross-dataset validation revealed extracted age-dependent factors correctly identified age in 3 of 4 test subjects. These findings demonstrate that tensor analysis can be applied to characterize the age-specific subtleties in EEG, which provide a means for tracking developmental changes in pediatric rehabilitation BCIs.

Multiscale dispersion entropy for the regional analysis of resting-state magnetoencephalogram complexity in Alzheimer's disease

Alzheimers disease (AD) is a progressive and irreversible brain disorder of the nervous system affecting memory, thinking, and emotion. It is the most important cause of dementia and an influential social problem in all the world. The complexity of brain recordings has been successfully used to help to characterize AD. We have recently introduced multiscale dispersion entropy (MDE) as a very fast and powerful tool to quantify the complexity of signals. The aim of this study is to assess the ability of MDE, in comparison with multiscale permutation entropy (MPE) and multiscale entropy (MSE), to discriminate 36 AD patients from 26 elderly age-matched control subjects using resting-state magnetoencephalogram (MEG) recordings. The results showed that MDE, unlike MSE, does not lead to undefined values. Moreover, the differences between the MDE values for AD palatines versus controls were more significant than their corresponding MSE- and MPE-based values. In addition, the computation time for our recently developed MDE was considerably less than that for MSE and even MPE.