Search

Objective. Extracting reliable information from electroencephalogram (EEG) is difficult because the low signal-to-noise ratio and significant intersubject variability seriously hinder statistical analyses. However, recent advances in explainable machine learning open a new strategy to address this problem. Approach. The current study evaluates this approach using results from the classification and decoding of electrical brain activity associated with information retention. We designed four neural network models differing in architecture, training strategies, and input representation to classify single experimental trials of a working memory task. Main results. Our best models achieved an accuracy (ACC) of 65.29 ± 0.76 and Matthews correlation coefficient of 0.288 ± 0.018, outperforming the reference model trained on the same data. The highest correlation between classification score and behavioral performance was 0.36 ( p = 0.0007). Using analysis of input perturbation, we estimated the importance of EEG channels and frequency bands in the task at hand. The set of essential features identified for each network varies. We identified a subset of features common to all models that identified brain regions and frequency bands consistent with current neurophysiological knowledge of the processes critical to attention and working memory. Finally, we proposed sanity checks to examine further the robustness of each model's set of features. Significance. Our results indicate that explainable deep learning is a powerful tool for decoding information from EEG signals. It is crucial to train and analyze a range of models to identify stable and reliable features. Our results highlight the need for explainable modeling as the model with the highest ACC appeared to use residual artifactual activity., (Creative Commons Attribution license.)

Objective/Purpose . Evaluation of efficacy and safety of autologous adipose-derived regenerative cells (ADRCs) treatment in autoimmune refractory epilepsy. Patients . Six patients with proven or probable autoimmune refractory epilepsy (2 with Rasmussen encephalitis, 2 with antineuronal autoantibodies in serum, and 2 with possible FIRES) were included in the project with approval of the Bioethics Committee., Method: Intrathecal injection of autologous ADRC acquired through liposuction followed by enzymatic isolation was performed. The procedure was repeated 3 times every 3 months with each patient. Neurological status, brain MRI, cognitive function, and antiepileptic effect were monitored during 12 months., Results: Immediately after the procedure, all patients were in good condition. In some cases, transient mildly elevated body temperature, pain in regions of liposuction, and slight increasing number of seizures during 24 hours were observed. During the next months, some improvements in school, social functioning, and manual performance were observed in all patients. One patient has been seizure free up to the end of trial. In other patients, frequency of seizures was different: from reduced number to the lack of improvement (3-year follow-up)., Conclusion: Autologous ADRC therapy may emerge as a promising option for some patients with autoimmune refractory epilepsy. Based on our trial and other clinical data, the therapy appears to be safe and feasible. Antiepileptic efficacy proved to be various; however, some abilities improved in all children. No signs of psychomotor regression were observed during the first year following the treatment., Competing Interests: The authors declare that there is no a competing financial interest or conflict of interest regarding the publication of this paper., (Copyright © 2020 Elzbieta Szczepanik et al.)

Malformations of cortical development (MCDs) manifest with structural brain anomalies that lead to neurologic sequelae, including epilepsy, cerebral palsy, developmental delay, and intellectual disability. To investigate the underlying genetic architecture of patients with disorders of cerebral cortical development, a cohort of 54 patients demonstrating neuroradiologic signs of MCDs was investigated. Individual genomes were interrogated for single-nucleotide variants (SNV) and copy number variants (CNV) with whole-exome sequencing and chromosomal microarray studies. Variation affecting known MCDs-associated genes was found in 16/54 cases, including 11 patients with SNV, 2 patients with CNV, and 3 patients with both CNV and SNV, at distinct loci. Diagnostic pathogenic SNV and potentially damaging variants of unknown significance (VUS) were identified in two groups of seven individuals each. We demonstrated that de novo variants are important among patients with MCDs as they were identified in 10/16 individuals with a molecular diagnosis. Three patients showed changes in known MCDs genes  and a clinical phenotype beyond the usual characteristics observed, i.e., phenotypic expansion, for a particular known disease gene clinical entity. We also discovered 2 likely candidate genes, CDH4, and ASTN1, with human and animal studies supporting their roles in brain development, and 5 potential candidate genes. Our findings emphasize genetic heterogeneity of MCDs disorders and postulate potential novel candidate genes involved in cerebral cortical development.

Epilepsy in females with mental retardation (EFMR) is a rare early infantile epileptic encephalopathy (EIEE), phenotypically resembling Dravet syndrome (DS). It is characterised by a variable degree of intellectual deficits and epilepsy. EFMR is caused by heterozygous mutations in the PCDH19 gene (locus Xq22.1) encoding protocadherin-19, a protein that is highly expressed during brain development. The protein is involved in cell adhesion and probably plays an important role in neuronal migration and formation of synaptic connections. EFMR is considered X-linked of variable mutations' penetrance. Mutations in the PCDH19 gene mainly arise de novo, but if inherited, they show a unique pattern of transmission. Females with heterozygous mutations are affected, while hemizygous males are not, regardless of mutation carriage. This singular mode might be explained by cell interference as a pathogenic molecular mechanism leading to neuronal dysfunction. Recently, PCDH19-related EIEE turned out to be more frequent than initially thought, contributing to around 16% of cases (25% in female groups) in the SCN1A-negative DS-like patients. Therefore, the PCDH19 gene is now estimated to be the second, after SCN1A, most clinically relevant gene in epilepsy.

Objective: The aim of this study was to analyze the intra-/interfamilial phenotypic heterogeneity due to variants at the highly evolutionary conservative p.Arg1596 residue in the Nav1.1 subunit., Materials/participants: Among patients referred for analysis of the SCN1A gene one recurrent, heritable mutation was found in families enrolled into the study. Probands from those families even clinically diagnosed with atypical Dravet syndrome (DS), generalized epilepsy with febrile seizures plus (GEFS+), and focal epilepsy, had heterozygous p.Arg1596 His/Cys missense substitutions, c.4787G>T and c.4786C>T in the SCN1A gene., Method: Full clinical evaluation, including cognitive development, neurological examination, EEGs, MRI was performed in probands and affected family members in developmental age. The whole SCN1A gene sequencing was performed for all probands. The exon 25, where the identified missense substitutions are localized, was directly analyzed for the other family members., Results: Mutation of the SCN1A p.1596Arg was identified in three families, in one case substitution p.Arg1596Cys and in two cases p.Arg1596His. Both mutations were previously described as pathogenic and causative for DS, GEFS+ and focal epilepsy. Spectrum of phenotypes among presented families with p.Arg1596 mutations shows heterogeneity ranged from asymptomatic cases, through FS and FS+ to GEFS+/Panayiotopoulos syndrome and epilepsies with and without febrile seizures, and epileptic encephalopathy such as DS. Phenotypes differ among patients displaying both focal and generalized epilepsies. Some patients demonstrated additionally Asperger syndrome and ataxia., Conclusion: Clinical picture heterogeneity of the patients carrying mutation of the same residue indicates the involvement of the other factors influencing the SCN1A gene mutations' penetrance., (Copyright © 2015 Polish Neurological Society. Published by Elsevier Urban & Partner Sp. z o.o. All rights reserved.)