Deciphering Post-Stroke Sleep Disorders: Unveiling Neurological Mechanisms in the Realm of Brain Science.

Sleep disorders are the most widespread mental disorders after stroke and hurt survivors' functional prognosis, response to restoration, and quality of life. This review will address an overview of the progress of research on the biological mechanisms associated with stroke-complicating sleep disorders. Extensive research has investigated the negative impact of stroke on sleep. However, a bidirectional association between sleep disorders and stroke exists; while stroke elevates the risk of sleep disorders, these disorders also independently contribute as a risk factor for stroke. This review aims to elucidate the mechanisms of stroke-induced sleep disorders. Possible influences were examined, including functional changes in brain regions, cerebrovascular hemodynamics, neurological deficits, sleep ion regulation, neurotransmitters, and inflammation. The results provide valuable insights into the mechanisms of stroke complicating sleep disorders.

A Biological Immunity-Based Neuro Prototype for Few-Shot Anomaly Detection with Character Embedding.

Anomaly detection has wide applications to help people recognize false, intrusion, flaw, equipment failure, etc. In most practical scenarios, the amount of the annotated data and the trusted labels is low, resulting in poor performance of the detection. In this paper, we focus on the anomaly detection for the text type data and propose a detection network based on biological immunity for few-shot detection, by imitating the working mechanism of the immune system of biological organisms. This network enabling the protected system to distinguish the aggressive behavior of "nonself" from the legitimate behavior of "self" by embedding characters. First, it constructs episodic task sets and extracts data representations at the character level. Then, in the pretraining phase, Word2Vec is used to embed the representations. In the meta-learning phase, a dynamic prototype containing encoder, routing, and relation is designed to identify the data traffic. Compare to the mean-based prototype, the proposed prototype applies a dynamic routing algorithm that assigns different weights to samples in the support set through multiple iterations to obtain a prototype that combines the distribution of samples. The proposed method is validated on 2 real traffic datasets. The experimental results indicate that (a) the proposed anomaly detection prototype outperforms state-of-the-art few-shot techniques with 1.3% to 4.48% accuracy and 0.18% to 4.55% recall; (b) under the premise of ensuring the accuracy and recall, the number of training samples is reduced to 5 or 10; (c) ablation experiments are designed for each module, and the results show that more accurate prototypes can be obtained by using the dynamic routing algorithm.

Pterostilbene alleviated cerebral ischemia/reperfusion-induced blood-brain barrier dysfunction via inhibiting early endothelial cytoskeleton reorganization and late basement membrane degradation.

Pterostilbene, an important analogue of the star molecule resveratrol and a novel compound naturally occurring in blueberries and grapes, exerts a significant neuroprotective effect on cerebral ischemia/reperfusion (I/R), but its mechanism is still unclear. This study aimed to follow the molecular mechanisms behind the potential protective effect of pterostilbene against I/R induced injury. For fulfilment of our aim, we investigated the protective effects of pterostilbene on I/R injury caused by middle cerebral artery occlusion (MCAO) in vivo and oxygen-glucose deprivation (OGD) in vitro. Machine learning models and molecular docking were used for target exploration and validated by western blotting. Pterostilbene significantly reduced the cerebral infarction volume, improved neurological deficits, increased cerebral microcirculation and improved blood-brain barrier (BBB) leakage. Machine learning models confirmed that the stroke target MMP-9 bound to pterostilbene, and molecular docking demonstrated the strong binding activity. We further found that pterostilbene could depolymerize stress fibers and maintain the cytoskeleton by effectively increasing the expression of the non-phosphorylated actin depolymerizing factor (ADF) in the early stage of I/R. In the late stage of I/R, pterostilbene could activate the Wnt pathway and inhibit the expression of MMP-9 to decrease the degradation of the extracellular basement membrane (BM) and increase the expression of junction proteins. In this study, we explored the protective mechanisms of pterostilbene in terms of both endothelial cytoskeleton and extracellular matrix. The early and late protective effects jointly maintain BBB stability and attenuate I/R injury, showing its potential to be a promising drug candidate for the treatment of ischemic stroke.

PSNSleep: a self-supervised learning method for sleep staging based on Siamese networks with only positive sample pairs.

Traditional supervised learning methods require large quantities of labeled data. However, labeling sleep data according to polysomnography by well-trained sleep experts is a very tedious job. In the present day, the development of self-supervised learning methods is making significant progress in many fields. It is also possible to apply some of these methods to sleep staging. This is to remove the dependency on labeled data at the stage of representation extraction. Nevertheless, they often rely too much on negative samples for sample selection and construction. Therefore, we propose PSNSleep, a novel self-supervised learning method for sleep staging based on Siamese networks. The crucial step to the success of our method is to select appropriate data augmentations (the time shift block) to construct the positive sample pair. PSNSleep achieves satisfactory results without relying on any negative samples. We evaluate PSNSleep on Sleep-EDF and ISRUC-Sleep and achieve accuracy of 80.0% and 74.4%. The source code is publicly available at https://github.com/arthurxl/PSNSleep.

The Devastating Effects of Sleep Deprivation on Memory: Lessons from Rodent Models.

In this narrative review article, we discuss the role of sleep deprivation (SD) in memory processing in rodent models. Numerous studies have examined the effects of SD on memory, with the majority showing that sleep disorders negatively affect memory. Currently, a consensus has not been established on which damage mechanism is the most appropriate. This critical issue in the neuroscience of sleep remains largely unknown. This review article aims to elucidate the mechanisms that underlie the damaging effects of SD on memory. It also proposes a scientific solution that might explain some findings. We have chosen to summarize literature that is both representative and comprehensive, as well as innovative in its approach. We examined the effects of SD on memory, including synaptic plasticity, neuritis, oxidative stress, and neurotransmitters. Results provide valuable insights into the mechanisms by which SD impairs memory function.

A Siamese Network-Based Method for Improving the Performance of Sleep Staging with Single-Channel EEG.

Sleep staging is of critical significance to the diagnosis of sleep disorders, and the electroencephalogram (EEG), which is used for monitoring brain activity, is commonly employed in sleep staging. In this paper, we propose a novel method for improving the performance of sleep staging models based on Siamese networks, based on single-channel EEG. Our proposed method consists of a Siamese network architecture and a redesigned loss with distance metrics. Two encoders are used in the Siamese network to generate latent features of the EEG epochs, and the contrastive loss, which is also a distance metric, is used to compare the similarity or differences between EEG epochs from the same or different sleep stages. We evaluated our method on single-channel EEGs from different channels (Fpz-Cz and F4-EOG (left)) from two public datasets SleepEDF and MASS-SS3 and achieved the overall accuracies MF1 and Cohen's kappa coefficient of 85.2%, 78.3% and 0.79 on SleepEDF and 87.2%, 82.1% and 0.81 on MASS-SS3. The results show that our method can significantly improve the performance of sleep staging models and outperform the state-of-the-art sleep staging methods. The performance of our method also confirms that the features captured by Siamese networks and distance metrics are useful for sleep staging.

A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance.

In this study, generative adversarial networks named SleepGAN are proposed to expand the training set for automatic sleep stage classification tasks by generating both electroencephalogram (EEG) epochs and sequence relationships of sleep stages. In order to reach high accuracy, most existing classification methods require substantial amounts of training data, but obtaining such quantities of real EEG epochs is expensive and time-consuming. We introduce few-shot learning, which is a method of training a GAN using a very small set of training data. This paper presents progressive Wasserstein divergence generative adversarial networks (GANs) and a relational memory generator to generate EEG epochs and stage transition sequences, respectively. For the evaluation of our generated data, we use single-channel EEGs from the public dataset Sleep-EDF. The addition of our augmented data and sequence to the training set was shown to improve the performance of the classification model. The accuracy of the model increased by approximately 1% after incorporating generated EEG epochs. Adding both the augmented data and sequence to the training set resulted in a further increase of 3%, from the original accuracy of 79.40% to 83.06%. The result proves that SleepGAN is a set of GANs capable of generating realistic EEG epochs and transition sequences under the condition of insufficient training data and can be used to enlarge the training dataset and improve the performance of sleep stage classification models in clinical practice.

Imaging Technologies for Cerebral Pharmacokinetic Studies: Progress and Perspectives.

Pharmacokinetic assessment of drug disposition processes in vivo is critical in predicting pharmacodynamics and toxicology to reduce the risk of inappropriate drug development. The blood-brain barrier (BBB), a special physiological structure in brain tissue, hinders the entry of targeted drugs into the central nervous system (CNS), making the drug concentrations in target tissue correlate poorly with the blood drug concentrations. Additionally, once non-CNS drugs act directly on the fragile and important brain tissue, they may produce extra-therapeutic effects that may impair CNS function. Thus, an intracerebral pharmacokinetic study was developed to reflect the disposition and course of action of drugs following intracerebral absorption. Through an increasing understanding of the fine structure in the brain and the rapid development of analytical techniques, cerebral pharmacokinetic techniques have developed into non-invasive imaging techniques. Through non-invasive imaging techniques, molecules can be tracked and visualized in the entire BBB, visualizing how they enter the BBB, allowing quantitative tools to be combined with the imaging system to derive reliable pharmacokinetic profiles. The advent of imaging-based pharmacokinetic techniques in the brain has made the field of intracerebral pharmacokinetics more complete and reliable, paving the way for elucidating the dynamics of drug action in the brain and predicting its course. The paper reviews the development and application of imaging technologies for cerebral pharmacokinetic study, represented by optical imaging, radiographic autoradiography, radionuclide imaging and mass spectrometry imaging, and objectively evaluates the advantages and limitations of these methods for predicting the pharmacodynamic and toxic effects of drugs in brain tissues.

Advanced Research in Cellular Pharmacokinetics and its Cutting-edge Technologies.

Pharmacokinetics (PK), as a significant part of pharmacology, runs through the overall process of the preclinical and clinical research on drugs and plays a significant role in determining the material basis of efficacy and mechanism research. However, due to the limitations of classical PK, cellular PK was put forward and developed rapidly. Many novel and original technologies have been innovatively applied to cellular PK research, thereby providing powerful technical support. As a novel field of PK research, cellular PK expands the research object and enriches the theoretical framework of PK. It provides a new perspective for elucidating the mechanism of drug action and the dynamic process of drug in the body. Furthermore, it provides a scientific basis and guiding significance for the development of new drugs and clinical rational drug use. Cellular PK can explain the dynamic process of certain drugs (e.g., antineoplastic drugs and antibiotics) and the disposition kinetics characteristics in some specific tissues (e.g., brain and tumor) in a clearer and more accurate manner. It is a beneficial supplement and the perfection of traditional PK. In the future, traditional and cellular PKs will complement each other well and improve into an all-around research system in drug developments. Briefly, this paper reviews the conceptual development of cellular PK and key associated technologies, explores its main functions and applications, and looks forward to the important pioneering significance and promising value for the development of PK.

An attention-based temporal convolutional network for rodent sleep stage classification across species, mutants and experimental environments with single-channel electroencephalogram.

Objective.Sleep perturbation by environment, medical procedure and genetic background is under continuous study in biomedical research. Analyzing brain states in animal models such as rodents relies on categorizing electroencephalogram (EEG) recordings. Traditionally, sleep experts have classified these states by visual inspection of EEG signatures, which is laborious. The heterogeneity of sleep patterns complicates the development of a generalizable solution across different species, genotypes and experimental environments.Approach.To realize a generalizable solution, we proposed a cross-species rodent sleep scoring network called CSSleep, a robust deep-learning model based on single-channel EEG. CSSleep starts with a local time-invariant information learning convolutional neural network. The second module is the global transition rules learning temporal convolutional network (TRTCN), stacked with bidirectional attention-based temporal convolutional network modules. The TRTCN simultaneously captures positive and negative time direction information and highlights relevant in-sequence features. The dataset for model evaluation comprises the single-EEG signatures of four cohorts of 16 mice and 8 rats from three laboratories.Main results.In leave-one-cohort-out cross-validation, our model achieved an accuracy of 91.33%. CSSleep performed well on generalization across experimental environments, mutants and rodent species by using single-channel EEG.Significance.This study aims to promote well-standardized cross-laboratory sleep studies to improve our understanding of sleep. Our source codes and supplementary materials will be disclosed later.

Automatic sleep stage classification: A light and efficient deep neural network model based on time, frequency and fractional Fourier transform domain features.

This work proposed a novel method for automatic sleep stage classification based on the time, frequency, and fractional Fourier transform (FRFT) domain features extracted from a single-channel electroencephalogram (EEG). Bidirectional long short-term memory was applied to the proposed model to train it to learn the sleep stage transition rules according to the American Academy of Sleep Medicine's manual for automatic sleep stage classification. Results indicated that the features extracted from the fractional Fourier-transformed single-channel EEG may improve the performance of sleep stage classification. For the Fpz-Cz EEG of Sleep-EDF with 30 s epochs, the overall accuracy of the model increased by circa 1% with the help of the FRFT domain features and even reached 81.6%. This work thus made the application of FRFT to automatic sleep stage classification possible. The parameters of the proposed model measured 0.31 MB, which are 5% of those of DeepSleepNet, but its performance is similar to that of DeepSleepNet. Hence, the proposed model is a light and efficient model based on deep neural networks, which also has a prospect for on-device machine learning.

FASSNet: fast apnea syndrome screening neural network based on single-lead electrocardiogram for wearable devices.

Objective. Sleep apnea (SA) is a chronic condition that fragments sleep and results in intermittent hypoxemia, which in long run leads to cardiovascular diseases like stroke. Diagnosis of SA through polysomnography is costly, inconvenient, and has long waiting list. Wearable devices provide a low-cost solution to the ambulatory detection of SA syndrome for undiagnosed patients. One of the wearables are the ones based on minute-by-minute analysis of single-lead electrocardiogram (ECG) signal. Processing ECG segments online at wearables contributes to memory conservation and privacy protection in long-term SA monitoring, and light-weight models are required due to stringent computation resource.Approach.We propose fast apnea syndrome screening neural network (FASSNet), an effective end-to-end neural network to perform minute-apnea event detection. Low-frequency components of filtered ECG spectrogram are selected as input. The model initially processes the spectrogram via convolution blocks. Bidirectional long-short-term memory blocks are used along the frequency axis to complement position information of frequency bands. Layer normalisation is implemented to retain in-epoch information since apnea periods have variable lengths. Experiments were carried out on 70 recordings of Apnea-ECG database, where each 60 s ECG segment is manually labelled as an apnea or normal minute by technician. Both ten-fold and patient-agnostic validation protocols are adopted.Main results.FASSNet is light-weighted, since its value of model parameters and multiply accumulates are 0.06% and 28.33% of those of an AlexNet benchmark, respectively. Meanwhile, FASSNet achieves an accuracy of 87.09%, a sensitivity of 77.96%, a specificity of 91.74%, and an F1 score of 81.61% in apnea event detection. Its accuracy of diagnosing SA syndrome severity exceeds 90% under the patient-agnostic protocol.Significance:FASSNet is a computationally efficient and accurate neural network for wearables to detect SA events and estimate SA severity based on minute-level diagnosis.

Recent Advances in Synthesis, Bioactivity, and Pharmacokinetics of Pterostilbene, an Important Analog of Resveratrol.

Pterostilbene is a natural 3,5-dimethoxy analog of resveratrol. This stilbene compound has a strong bioactivity and exists widely in Dalbergia and Vaccinium spp. Besides natural extraction, pterostilbene can be obtained by biosynthesis. Pterostilbene has become popular because of its remarkable pharmacological activities, such as anti-tumor, anti-oxidation, anti-inflammation, and neuroprotection. Pterostilbene can be rapidly absorbed and is widely distributed in tissues, but it does not seriously accumulate in the body. Pterostilbene can easily pass through the blood-brain barrier because of its low molecular weight and good liposolubility. In this review, the studies performed in the last three years on resources, synthesis, bioactivity, and pharmacokinetics of pterostilbene are summarized. This review focuses on the effects of pterostilbene on certain diseases to explore its targets, explain the possible mechanism, and look for potential therapeutic applications.