Search

Background and purpose: Sleep disorders are increasingly implicated as risk factors for stroke, as well as a determinant of stroke outcome. They can also occur secondary to the stroke itself. In this review, we describe the variety of different sleep disorders associated with stroke and analyze their effect on stroke risk and outcome. Methods: A search term-based literature review ("sleep," "insomnia," "narcolepsy," "restless legs syndrome," "periodic limb movements during sleep," "excessive daytime sleepiness" AND "stroke" OR "cerebrovascular" in PubMed; "stroke" and "sleep" in ClinicalTrials.gov) was performed. English articles from 1990 to March 2023 were considered. Results: Increasing evidence suggests that sleep disorders are risk factors for stroke. In addition, sleep disturbance has been reported in half of all stroke sufferers; specifically, an increase is not only sleep-related breathing disorders but also periodic limb movements during sleep, narcolepsy, rapid eye movement (REM) sleep behavior disorder, insomnia, sleep duration, and circadian rhythm sleep–wake disorders. Poststroke sleep disturbance has been associated with worse outcome. Conclusion: Sleep disorders are risk factors for stroke and associated with worse stroke outcome. They are also a common consequence of stroke. Recent guidelines suggest screening for sleep disorders after stroke. It is possible that treatment of sleep disorders could both reduce stroke risk and improve stroke outcome, although further data from clinical trials are required. [ABSTRACT FROM AUTHOR]

Social media platforms have surpassed cultural and linguistic boundaries, thus enabling online communication worldwide. However, the expanded use of various languages has intensified the challenge of online detection of hate speech content. Despite the release of multiple Natural Language Processing (NLP) solutions implementing cutting-edge machine learning techniques, the scarcity of data, especially labeled data, remains a considerable obstacle, which further requires the use of semisupervised approaches along with Generative Artificial Intelligence (Generative AI) techniques. This paper introduces an innovative approach, a multilingual semisupervised model combining Generative Adversarial Networks (GANs) and Pretrained Language Models (PLMs), more precisely mBERT and XLM-RoBERTa. Our approach proves its effectiveness in the detection of hate speech and offensive language in Indo-European languages (in English, German, and Hindi) when employing only 20% annotated data from the HASOC2019 dataset, thereby presenting significantly high performances in each of multilingual, zero-shot crosslingual, and monolingual training scenarios. Our study provides a robust mBERT-based semisupervised GAN model (SS-GAN-mBERT) that outperformed the XLM-RoBERTa-based model (SS-GAN-XLM) and reached an average F1 score boost of 9.23% and an accuracy increase of 5.75% over the baseline semisupervised mBERT model. [ABSTRACT FROM AUTHOR]

Natural language processing (NLP) has significantly transformed in the last decade, especially in the field of language modeling. Large language models (LLMs) have achieved SOTA performances on natural language understanding (NLU) and natural language generation (NLG) tasks by learning language representation in self-supervised ways. This paper provides a comprehensive survey to capture the progression of advances in language models. In this paper, we examine the different aspects of language models, which started with a few million parameters but have reached the size of a trillion in a very short time. We also look at how these LLMs transitioned from task-specific to task-independent to task-and-language-independent architectures. This paper extensively discusses different pretraining objectives, benchmarks, and transfer learning methods used in LLMs. It also examines different finetuning and in-context learning techniques used in downstream tasks. Moreover, it explores how LLMs can perform well across many domains and datasets if sufficiently trained on a large and diverse dataset. Next, it discusses how, over time, the availability of cheap computational power and large datasets have improved LLM's capabilities and raised new challenges. As part of our study, we also inspect LLMs from the perspective of scalability to see how their performance is affected by the model's depth, width, and data size. Lastly, we provide an empirical comparison of existing trends and techniques and a comprehensive analysis of where the field of LLM currently stands. [ABSTRACT FROM AUTHOR]

BackgroundPeriodic limb movement disorder (PLMD) and obstructive sleep apnea (OSA) are overlapping clinical syndromes with common risk factors. However, current literature has failed to establish a clear pathophysiological link between them. Thus, little is known about periodic limb movements (PLM) in otherwise healthy patients with suspected OSA.MethodsWe performed a retrospective analysis of 112 patients (age: 44.5 ± 12.0 years, 14.3% female) with suspected OSA who underwent full night polysomnography for the first time. Patients with chronic diseases of any kind, recent infections, malignancies, or daily or regular use of any type of medication were excluded. Group comparisons were made based on the severity of OSA (using the apnea hypopnea index, AHI) or the periodic limb movement index (PLMI).ResultsBoth, PLMI and the total number of periodic limb movements during sleep (PLMS), showed a significant increase in patients with severe OSA. In addition, AHI and apnea index (AI) were significantly higher in patients with PLMI >15/h, with a similar trend for hypopnea index (HI) (p 0.05, respectively). PLMI was significantly positive correlated with AHI, AI, and HI (r = 0.392, p 15/h were significantly older (p 15/h.ConclusionWe found a significant association between the severity of OSA and PLM in our study population with suspected OSA but without other comorbidities. PLMI and PLMS were significantly increased in patients with severe OSA. Future prospective studies with larger collectives should verify the presented results and should include mechanistic aspects in their evaluation.

Social media platforms have surpassed cultural and linguistic boundaries, thus enabling online communication worldwide. However, the expanded use of various languages has intensified the challenge of online detection of hate speech content. Despite the release of multiple Natural Language Processing (NLP) solutions implementing cutting-edge machine learning techniques, the scarcity of data, especially labeled data, remains a considerable obstacle, which further requires the use of semisupervised approaches along with Generative Artificial Intelligence (Generative AI) techniques. This paper introduces an innovative approach, a multilingual semisupervised model combining Generative Adversarial Networks (GANs) and Pretrained Language Models (PLMs), more precisely mBERT and XLM-RoBERTa. Our approach proves its effectiveness in the detection of hate speech and offensive language in Indo-European languages (in English, German, and Hindi) when employing only 20% annotated data from the HASOC2019 dataset, thereby presenting significantly high performances in each of multilingual, zero-shot crosslingual, and monolingual training scenarios. Our study provides a robust mBERT-based semisupervised GAN model (SS-GAN-mBERT) that outperformed the XLM-RoBERTa-based model (SS-GAN-XLM) and reached an average F1 score boost of 9.23% and an accuracy increase of 5.75% over the baseline semisupervised mBERT model.

Natural language processing (NLP) has significantly transformed in the last decade, especially in the field of language modeling. Large language models (LLMs) have achieved SOTA performances on natural language understanding (NLU) and natural language generation (NLG) tasks by learning language representation in self-supervised ways. This paper provides a comprehensive survey to capture the progression of advances in language models. In this paper, we examine the different aspects of language models, which started with a few million parameters but have reached the size of a trillion in a very short time. We also look at how these LLMs transitioned from task-specific to task-independent to task-and-language-independent architectures. This paper extensively discusses different pretraining objectives, benchmarks, and transfer learning methods used in LLMs. It also examines different finetuning and in-context learning techniques used in downstream tasks. Moreover, it explores how LLMs can perform well across many domains and datasets if sufficiently trained on a large and diverse dataset. Next, it discusses how, over time, the availability of cheap computational power and large datasets have improved LLM’s capabilities and raised new challenges. As part of our study, we also inspect LLMs from the perspective of scalability to see how their performance is affected by the model’s depth, width, and data size. Lastly, we provide an empirical comparison of existing trends and techniques and a comprehensive analysis of where the field of LLM currently stands.

N-Linked glycosylation is crucial for various biological processes such as protein folding, immune response, and cellular transport. Traditional experimental methods for determining N-linked glycosylation sites entail substantial time and labor investment, which has led to the development of computational approaches as a more efficient alternative. However, due to the limited availability of 3D structural data, existing prediction methods often struggle to fully utilize structural information and fall short in integrating sequence and structural information effectively. Motivated by the progress of protein pretrained language models (pLMs) and the breakthrough in protein structure prediction, we introduced a high-accuracy model called CoNglyPred. Having compared various pLMs, we opt for the large-scale pLM ESM-2 to extract sequence embeddings, thus mitigating certain limitations associated with manual feature extraction. Meanwhile, our approach employs a graph transformer network to process the 3D protein structures predicted by AlphaFold2. The final graph output and ESM-2 embedding are intricately integrated through a co-attention mechanism. Among a series of comprehensive experiments on the independent test dataset, CoNglyPred outperforms state-of-the-art models and demonstrates exceptional performance in case study. In addition, we are the first to report the uncertainty of N-linked glycosylation predictors using expected calibration error and expected uncertainty calibration error., (© 2024 Wiley‐VCH GmbH.)

Depression and periodic limb movement disease are both common disorders which frequently co-exist. Furthermore, antidepressants are known to cause and worsen periodic limb movements in sleep, which can worsen the quality of sleep and subsequently daytime symptoms. However, the effect of antidepressants on periodic limb movements is not uniform and depends on their mechanism of action. In this review we summarise the knowledge on the mechanism of periodic limb movements in sleep, and how changes in the concentration of neurotransmitters can contribute to them. We comprehensively evaluate the literature on antidepressants induced periodic limb movement in sleep. Based on this, we suggest clinical implications and further focus on research., Competing Interests: Declaration of competing interest None., (Copyright © 2024 Elsevier Ltd. All rights reserved.)

Background: Periodic limb movement disorder (PLMD) and obstructive sleep apnea (OSA) are overlapping clinical syndromes with common risk factors. However, current literature has failed to establish a clear pathophysiological link between them. Thus, little is known about periodic limb movements (PLM) in otherwise healthy patients with suspected OSA., Methods: We performed a retrospective analysis of 112 patients (age: 44.5 ± 12.0 years, 14.3% female) with suspected OSA who underwent full night polysomnography for the first time. Patients with chronic diseases of any kind, recent infections, malignancies, or daily or regular use of any type of medication were excluded. Group comparisons were made based on the severity of OSA (using the apnea hypopnea index, AHI) or the periodic limb movement index (PLMI)., Results: Both, PLMI and the total number of periodic limb movements during sleep (PLMS), showed a significant increase in patients with severe OSA. In addition, AHI and apnea index (AI) were significantly higher in patients with PLMI >15/h, with a similar trend for hypopnea index (HI) ( p  < 0.001, p  < 0.001, and p  > 0.05, respectively). PLMI was significantly positive correlated with AHI, AI, and HI ( r  = 0.392, p  < 0.001; r  = 0.361, p  < 0.001; and r  = 0.212, p  < 0.05, respectively). Patients with PLMI >15/h were significantly older ( p  < 0.001). There was no significant association between body mass index (BMI) and PLMI >15/h., Conclusion: We found a significant association between the severity of OSA and PLM in our study population with suspected OSA but without other comorbidities. PLMI and PLMS were significantly increased in patients with severe OSA. Future prospective studies with larger collectives should verify the presented results and should include mechanistic aspects in their evaluation., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Seifen, Herrmann, Pordzik, Matthias and Gouveris.)