Search Results (680)

The threat posed by water pollutants to aquatic ecosystems and human health cannot be overlooked, and the assessment of the toxicity of these contaminants is paramount to understanding their risks and formulating effective control measures. Luminescent bacteria-based assays, as a vital tool in evaluating contaminant toxicity, encounter a challenge in ensuring accuracy due to the phenomenon of “Hormesis” exhibited by pollutants towards biological entities, which may skew toxicity assessments. This study elucidated the specific effects of pollutants on luminescent bacteria at different concentrations, used modeling to characterize the effects and predict their toxicity trends, and explored the applicable concentration ranges for different pollutants. Research revealed that six typical pollutants, namely PAHs, endocrine disruptors, antibiotics, pesticides, heavy metals, and phytosensory substances, could promote the luminescence intensity of luminescent bacteria at low concentrations, and the promotional effect increased and then decreased. However, when the concentration of the substances reached a certain threshold, the effect changed from promotional to inhibitory, and the rate of inhibition was directly proportional to the concentration. The EC50 values of six types of substances to luminescent bacteria is as follows: endocrine disruptors > pesticides > antibiotics > heavy metals > polycyclic aromatic hydrocarbons > chemosensory agents. The effect curves were further fitted using the model to analyze the maximum point of the promotion of luminescence intensity by different substances, the threshold concentration, and the tolerance of luminescent bacteria to different substances. The maximum promotion of bacterial luminescence intensity was 29% for Bisphenol A at 0.005 mg/L and the minimum threshold concentration of chromium was 0.004 mg/L, and the maximum bacterial tolerance to erythromycin is 6.74. In addition, most of the current environmental concentrations had a positive effect on luminescent bacteria and may still be in the range of concentrations that promote luminescence as the substances continue to accumulate. These findings will enhance the accuracy and comprehensiveness of toxicity assessments, thereby facilitating more informed and effective decision-making in the realms of environmental protection and pollution management. Full article

Pituitary adenylate cyclase-activating polypeptide (PACAP) and vasoactive intestinal peptide (VIP) are two neuroprotective and anti-inflammatory molecules of the central nervous system (CNS). Both bind to three G protein-coupled receptors, namely PAC1, VPAC1 and VPAC2, to elicit their beneficial effects in various CNS diseases, including multiple sclerosis (MS). In this study, we assessed the expression and distribution of PACAP/VIP receptors in the normal-appearing white matter (NAWM) of MS donors with a clinical history of either relapsing–remitting MS (RRMS), primary MS (PPMS), secondary progressive MS (SPMS) or in aged-matched non-MS controls. Gene expression studies revealed MS-subtype specific changes in PACAP and VIP and in the receptors’ levels in the NAWM, which were partly corroborated by immunohistochemical analyses. Most PAC1 immunoreactivity was restricted to myelin-producing cells, whereas VPAC1 reactivity was diffused within the neuropil and in axonal bundles, and VPAC2 in small vessel walls. Within and around lesioned areas, glial cells were the predominant populations showing reactivity for the different PACAP/VIP receptors, with distinctive patterns across MS subtypes. Together, these data identify the differential expression patterns of PACAP/VIP receptors among the different MS clinical entities. These results may offer opportunities for the development of personalized therapeutic approaches to treating MS and/or other demyelinating disorders. Full article

Our research evaluates advanced artificial (AI) methodologies to enhance diagnostic accuracy in pulmonary radiography. Utilizing DenseNet121 and ResNet50, we analyzed 108,948 chest X-ray images from 32,717 patients and DenseNet121 achieved an area under the curve (AUC) of 94% in identifying the conditions of pneumothorax and oedema. The model’s performance surpassed that of expert radiologists, though further improvements are necessary for diagnosing complex conditions such as emphysema, effusion, and hernia. Clinical validation integrating Latent Dirichlet Allocation (LDA) and Named Entity Recognition (NER) demonstrated the potential of natural language processing (NLP) in clinical workflows. The NER system achieved a precision of 92% and a recall of 88%. Sentiment analysis using DistilBERT provided a nuanced understanding of clinical notes, which is essential for refining diagnostic decisions. XGBoost and SHapley Additive exPlanations (SHAP) enhanced feature extraction and model interpretability. Local Interpretable Model-agnostic Explanations (LIME) and occlusion sensitivity analysis further enriched transparency, enabling healthcare providers to trust AI predictions. These AI techniques reduced processing times by 60% and annotation errors by 75%, setting a new benchmark for efficiency in thoracic diagnostics. The research explored the transformative potential of AI in medical imaging, advancing traditional diagnostics and accelerating medical evaluations in clinical settings. Full article

Medication errors, which could often be detected in advance, are a significant cause of patient deaths each year, highlighting the critical importance of medication safety. The rapid advancement of data analysis technologies has made intelligent medication assistance applications possible, and these applications rely heavily on medical knowledge graphs. However, current knowledge graph construction techniques are predominantly focused on general domains, leaving a gap in specialized fields, particularly in the medical domain for medication assistance. The specialized nature of medical knowledge and the distinct distribution of vocabulary between general and biomedical texts pose challenges. Applying general natural language processing techniques directly to the medical domain often results in lower accuracy due to the inadequate utilization of contextual semantics and entity information. To address these issues and enhance knowledge graph production, this paper proposes an optimized model for named entity recognition and relationship extraction in the Chinese medical domain. Key innovations include utilizing Medical Bidirectional Encoder Representations from Transformers (MCBERT) for character-level embeddings pre-trained on Chinese biomedical corpora, employing Bi-directional Gated Recurrent Unit (BiGRU) networks for extracting enriched contextual features, integrating a Conditional Random Field (CRF) layer for optimal label sequence output, using the Piecewise Convolutional Neural Network (PCNN) to capture comprehensive semantic information and fusing it with entity features for better classification accuracy, and implementing a microservices architecture for the medication assistance review system. These enhancements significantly improve the accuracy of entity relationship classification in Chinese medical texts. The model achieved good performance in recognizing most entity types, with an accuracy of 88.3%, a recall rate of 85.8%, and an F1 score of 87.0%. In the relationship extraction stage, the accuracy reached 85.7%, the recall rate 82.5%, and the F1 score 84.0%. Full article

Named Entity Recognition (NER) is a fundamental and pivotal stage in the development of various knowledge-based support systems, including knowledge retrieval and question-answering systems. In the domain of pig diseases, Chinese NER models encounter several challenges, such as the scarcity of annotated data, domain-specific vocabulary, diverse entity categories, and ambiguous entity boundaries. To address these challenges, we propose PDCNER, a Pig Disease Chinese Named Entity Recognition method leveraging lexicon-enhanced BERT and contrastive learning. Firstly, we construct a domain-specific lexicon and pre-train word embeddings in the pig disease domain. Secondly, we integrate lexicon information of pig diseases into the lower layers of BERT using a Lexicon Adapter layer, which employs char–word pair sequences. Thirdly, to enhance feature representation, we propose a lexicon-enhanced contrastive loss layer on top of BERT. Finally, a Conditional Random Field (CRF) layer is employed as the model’s decoder. Experimental results show that our proposed model demonstrates superior performance over several mainstream models, achieving a precision of 87.76%, a recall of 86.97%, and an F1-score of 87.36%. The proposed model outperforms BERT-BiLSTM-CRF and LEBERT by 14.05% and 6.8%, respectively, with only 10% of the samples available, showcasing its robustness in data scarcity scenarios. Furthermore, the model exhibits generalizability across publicly available datasets. Our work provides reliable technical support for the information extraction of pig diseases in Chinese and can be easily extended to other domains, thereby facilitating seamless adaptation for named entity identification across diverse contexts. Full article

The deployment of large language models (LLMs) within the healthcare sector has sparked both enthusiasm and apprehension. These models exhibit the remarkable ability to provide proficient responses to free-text queries, demonstrating a nuanced understanding of professional medical knowledge. This comprehensive survey delves into the functionalities of existing LLMs designed for healthcare applications and elucidates the trajectory of their development, starting with traditional Pretrained Language Models (PLMs) and then moving to the present state of LLMs in the healthcare sector. First, we explore the potential of LLMs to amplify the efficiency and effectiveness of diverse healthcare applications, particularly focusing on clinical language understanding tasks. These tasks encompass a wide spectrum, ranging from named entity recognition and relation extraction to natural language inference, multimodal medical applications, document classification, and question-answering. Additionally, we conduct an extensive comparison of the most recent state-of-the-art LLMs in the healthcare domain, while also assessing the utilization of various open-source LLMs and highlighting their significance in healthcare applications. Furthermore, we present the essential performance metrics employed to evaluate LLMs in the biomedical domain, shedding light on their effectiveness and limitations. Finally, we summarize the prominent challenges and constraints faced by large language models in the healthcare sector by offering a holistic perspective on their potential benefits and shortcomings. This review provides a comprehensive exploration of the current landscape of LLMs in healthcare, addressing their role in transforming medical applications and the areas that warrant further research and development. Full article

To optimize the utilization and analysis of tables, it is essential to recognize and understand their semantics comprehensively. This requirement is especially critical given that many tables lack explicit annotations, necessitating the identification of column types and inter-column relationships. Such identification can significantly augment data quality, streamline data integration, and support data analysis and mining. Current table annotation models often address each subtask independently, which may result in the neglect of constraints and contextual information, causing relational ambiguities and inference errors. To address this issue, we propose a unified multi-task learning framework capable of concurrently handling multiple tasks within a single model, including column named entity recognition, column type identification, and inter-column relationship detection. By integrating these tasks, the framework exploits their interrelations, facilitating the exchange of shallow features and the sharing of representations. Their cooperation enables each task to leverage insights from the others, thereby improving the performance of individual subtasks and enhancing the model’s overall generalization capabilities. Notably, our model is designed to employ only the internal information of tabular data, avoiding reliance on external context or knowledge graphs. This design ensures robust performance even with limited input information. Extensive experiments demonstrate the superior performance of our model across various tasks, validating the effectiveness of unified multi-task learning framework in the recognition and comprehension of table semantics. Full article

Named-entity recognition (NER) is a crucial task in natural language processing, especially for extracting meaningful information from unstructured text data. In the healthcare domain, accurate NER can significantly enhance patient care by enabling efficient extraction and analysis of clinical information. This paper presents MedNER, a novel service-oriented framework designed specifically for medical NER in Chinese medical texts. MedNER leverages advanced deep learning techniques and domain-specific linguistic resources to achieve good performance in identifying diabetes-related entities such as symptoms, tests, and drugs. The framework integrates seamlessly with real-world healthcare systems, offering scalable and efficient solutions for processing large volumes of clinical data. This paper provides an in-depth discussion on the architecture and implementation of MedNER, featuring the concept of Deep Learning as a Service (DLaaS). A prototype has encapsulated BiLSTM-CRF and BERT-BiLSTM-CRF models into the core service, demonstrating its flexibility, usability, and effectiveness in addressing the unique challenges of Chinese medical text processing. Full article

Living systems (LSs) must solve the problem of adapting to their environment by identifying external states and acting appropriately to maintain external relationships and internal order for survival and reproduction. This challenge is akin to the philosophical enigma of how the self can escape solipsism. In this study, a comprehensive model is developed to address the adaptation problem. LSs are composed of material entities capable of detecting their external states. This detection is conceptualized as “cognition”, a state change in relation to its external states. This study extends the concept of cognition to include three hierarchical levels of the world: physical, chemical, and semiotic cognitions, with semiotic cognition being closest to the conventional meaning of cognition. This radical extension of the cognition concept to all levels of the world provides a monistic model named the cognizers system model, in which mind and matter are unified as a single entity, the “cognizer”. During evolution, LSs invented semiotic cognition based on physical and chemical cognitions to manage the probability distribution of events that occur to them. This study proposes a theoretical model in which semiotic cognition is an adaptive process wherein the inverse causality operation produces particular internal states as symbols that signify hidden external states. This operation makes LSs aware of the external world. Full article

In the Netherlands, there was always a clear distinction between Protestant and Catholic folklore. That is visible in witchcraft accusations, but it is also visible in ghost lore. This lore is here reconstructed applying a not always used source, to wit newspaper articles. Here, I will discuss how accounts of hoaxing on the one hand and misinterpreted experiences on the other, help to understand how, in this case people in the Netherlands of roughly a century to a century and a half ago, realized their imagination of the dead. Not in a paradisical kind of afterlife, or as rotten corpses in the ground, but as specific entities which permeated the boundaries between the living and the dead. These newspaper reports are confronted with the stories (or jokes) collected by folklorists. I will also discuss content, with a special focus on the phenomenon of the hoax. Hoaxsters, however, allow the researcher to engage with an extra dimension in the encounter, between the ghost and the observer there is now a third party interacting with both. (How this involves the researcher, is always a problem in historical research.) Was there an overall ghost picture? What was the reaction of bystanders? Moreover, this essay will move between story and history, between the past as it was experienced and as it was related to contemporaries, between ‘fact’ and ‘fiction’ to give it another name. As it will appear, the boundary between the two seems blurred but in the end turns out rather precise. Full article

In this study, a new data-sharing method is proposed that uses a private InterPlanetary File System—a decentralized storage system operated within a closed network—to distribute data to external entities while making its authenticity verifiable. Among the two operational modes of IPFS, public and private, this study focuses on the method for using private IPFS. Private IPFS is not open to the general public; although it poses a risk of data tampering when distributing data to external parties, the proposed method ensures the authenticity of the received data. In particular, this method applies a type of zero-knowledge proof, namely, the Groth16 protocol of zk-SNARKs, to ensure that the data corresponds to the content identifier in a private IPFS. Moreover, the recipient’s name is embedded into the distributed data to prevent unauthorized secondary distribution. Experiments confirmed the effectiveness of the proposed method for an image data size of up to 120 × 120 pixels. In future studies, the proposed method will be applied to larger and more diverse data types. Full article

PM742 (1), a new chemical entity, has been isolated from the sponge Discodermia du Bocage collected in the Pacific Ocean. This compound showed strong in vitro cytotoxicity against several human tumor cell lines as well as a tubulin depolymerization mechanism of action, which led us to conduct an extensive Structure-Activity-Relationship study through the synthesis of different analogs. As a result, a derivatively named PM534 (2) is currently in its first human Phase I clinical trial. Herein, we present a comprehensive review of the isolation, structural elucidation, and antitumor activities of the parent compound PM742. Full article

With the continuous exploration of space science, a large number of domain-related materials and scientific literature are constantly generated, mostly in the form of text, which contains rich and unexplored domain knowledge. Natural language processing technology has made rapid development and pre-trained language models provide promising information extraction tools. However, due to the strong professionalism of space science, there are many domain concepts and technical terms. Moreover, Chinese texts have complex language structures and word combinations, which may yield suboptimal performance by general pre-trained models such as BERT. In this work, we investigate how to adapt BERT to Chinese space science and propose the space science-aware pre-trained language model, namely, SSuieBERT. We validate it through downstream tasks such as named entity recognition, relation extraction, and event extraction, which can perform better than general models. To the best of our knowledge, our proposed SSuieBERT is the first pre-trained language model in space science, which can promote information extraction and knowledge discovery from space science texts. Full article

Using long short-term memory (LSTM) networks to build a named entity recognition model is important for the task of named entity recognition. However, traditional memory networks lack a direct connection between input information and hidden states, leading to key feature information not being fully learned during training and causing information loss. This paper designs a bidirectional variant of the long short-term memory (BiLSTM) network called Mogrifier-BiGRU, which combines the BERT pre-trained model and the conditional random field (CRF) network model. The Mogrifier gating interaction unit is set with more hyperparameters to achieve deep interaction of gating information, changing the relationship between input and hidden states so that they are no longer independent. By introducing more nonlinear transformations, the model can learn more complex input–output mapping relationships. Then, by combining Bayesian optimization with the improved Mogrifier-BiGRU network, the optimal hyperparameters of the model are automatically calculated. Experimental results show that the model method based on the gating interaction mechanism can effectively combine feature information, improving the accuracy of Chinese-named entity recognition. On the dataset, an F1-score of 85.42% was achieved, which is 7% higher than traditional methods and 10% higher for the accuracy of some entity recognition. Full article

With the development of seaborne trade, international maritime crime is becoming increasingly complex. Detecting maritime threats by fusing the physical movement data from traditional physical sensors is not sufficient. Thus, soft data, including intelligence reports and news articles, need to be incorporated into the situational awareness models of maritime threats. In this regard, this study developed an automated construction method of knowledge graphs for pirate events, which lays a foundation for subsequent maritime threat reasoning and situational awareness. First, a knowledge graph ontology model for pirate events was designed. Secondly, the BERT-BiLSTM-CRF model is proposed for named-entity recognition, and an entity linking algorithm based on distant learning and context attention mechanism is proposed to remove the conceptual ambiguity. Thirdly, based on traditional distant supervision relation extraction, which is based on sentence-level attention mechanism, bag-level and group-level attention mechanism methods are additionally proposed to further enhance the performance of distant supervision relation extraction. The proposed model demonstrated high performance in named-entity recognition, entity linking, and relation extraction tasks, with an overall F1-score of over 0.94 for NER and significant improvements in entity linking and relation extraction compared to traditional methods. The constructed knowledge graphs effectively support maritime threat reasoning and situational awareness, offering a substantial contribution to the field of maritime security. Our discussion highlights the model’s strengths and potential areas for future work, while the conclusion emphasizes the practical implications and the readiness of our approach for real-world applications. Full article