No abstract

The human brain is characterized by complex structural, functional connections that integrate unique cognitive characteristics. There is a fundamental hurdle for the evaluation of both structural and functional connections of the brain and the effects in the diagnosis and treatment of neurodegenerative diseases. Currently, there is no clinically specific diagnostic biomarker capable of confirming the diagnosis of major depressive disorder (MDD). Therefore, exploring translational biomarkers of mood disorders based on deep learning (DL) has valuable potential with its recently underlined promising outcomes. In this article, an electroencephalography (EEG)-based diagnosis model for MDD is built through advanced computational neuroscience methodology coupled with a deep convolutional neural network (CNN) approach. EEG recordings are analyzed by modeling 3 different deep CNN structure, namely, ResNet-50, MobileNet, Inception-v3, in order to dichotomize MDD patients and healthy controls. EEG data are collected for 4 main frequency bands (Δ, θ, α, and β, accompanying spatial resolution with location information by collecting data from 19 electrodes. Following the pre-processing step, different DL architectures were employed to underline discrimination performance by comparing classification accuracies. The classification performance of models based on location data, MobileNet architecture generated 89.33% and 92.66% classification accuracy. As to the frequency bands, delta frequency band outperformed compared to other bands with 90.22% predictive accuracy and area under curve (AUC) value of 0.9 for ResNet-50 architecture. The main contribution of the study is the delineation of distinctive spatial and temporal features using various DL architectures to dichotomize 46 MDD subjects from 46 healthy subjects. Exploring translational biomarkers of mood disorders based on DL perspective is the main focus of this study and, though it is challenging, with its promising potential to improve our understanding of the psychiatric disorders, computational methods are highly worthy for the diagnosis process and valuable in terms of both speed and accuracy compared with classical approaches.

Multiple sclerosis (MS) is an inflammatory and neurodegenerative disease characterized with autoimmune response against myelin proteins and progressive axonal loss. The heterogeneity of the clinical course and low concordance rates in monozygotic twins have indicated the involvement of complex heritable and environmental factors in MS pathogenesis. MS is more often transmitted to the next generation by mothers than fathers suggesting an epigenetic influence. One of the possible reasons of this parent-of-origin effect might be the human leukocyte antigen-DRB1*15 allele, which is the major risk factor for MS and regulated by epigenetic mechanisms such as DNA methylation and histone deacetylation. Moreover, major environmental risk factors for MS, vitamin D deficiency, smoking and Ebstein-Barr virus are all known to exert epigenetic changes. In the last few decades, compelling evidence implicating the role of epigenetics in MS has accumulated. Increased or decreased acetylation, methylation and citrullination of genes regulating the expression of inflammation and myelination factors appear to be particularly involved in the epigenetics of MS. Although much less is known about epigenetic factors causing neurodegeneration, epigenetic mechanisms regulating axonal loss, apoptosis and mitochondrial dysfunction in MS are in the process of identification. Additionally, expression levels of several microRNAs (miRNAs) (e.g., miR-155 and miR-326) are increased in MS brains and potential mechanisms by which these factors might influence MS pathogenesis have been described. Certain miRNAs may also be potentially used as diagnostic biomarkers in MS. Several reagents, especially histone deacetylase inhibitors have been shown to ameliorate the symptoms of experimental allergic encephalomyelitis. Ongoing efforts in this field are expected to result in characterization of epigenetic factors that can be used in prediction of treatment responsive MS patients, diagnostic screening panels and treatment methods with specific mechanism of action.

No abstract

The COST is a valid and reliable screening battery for detection of dementia both in the illiterate and the literate Alzheimer patients.