Biomedical Domain Research Articles

Artificial intelligence and microbiome research: Evolution of hotspots, research trends, and thematic-based narrative review.

Artificial intelligence (AI) and microbiome have emerged in recent years as transformative fields with far-reaching implications for various biomedical domains. This paper presents a comprehensive bibliometric analysis examining the intersection of AI and the microbiome (AIM). The study aims to provide information on this interdisciplinary field's research landscape, trends, and emerging topics. Using a systematic approach, data-driven studies were extracted from the Scopus database on 23 November 2023 and analyzed using the VOSviewer and Bibliometrix applications. The regression coefficient of 0.94 and the yearly growth rate of 7.46% in AIM production indicate a consistent increase over time. Identification of essential contributors, organizations, and nations illuminated cooperative networks and research hotspots. The trend themes are the gut microbiome, disease prediction, machine learning, transfer learning, categorization, big data, artificial neural networks, chronic rhinosinusitis, epidemiology, COPD, and bronchoalveolar lavage. These hot issues in AIM reflect the present emphasis on research and developments in our knowledge of the microbiome's function in health, sickness, and individualized treatment. The findings give researchers, policymakers, and industry experts a thorough picture of the research environment and guide future paths in AIM's fascinating and promising subject.

Clustering-based topic modeling for biomedical documents extractive text summarization

The increasing volume of electronic text, especially in the biomedical domain, requires automatic text summarization (ATS) to help researchers navigate and find relevant information. This study proposes an unsupervised extractive ATS method to improve the quality of biomedical document summaries by focusing on subtopic diversity. The method integrates topic modeling and clustering with bidirectional encoder representation from transformers (BERT). To evaluate the effectiveness of the proposed study, it tested on a new corpus of 200 biomedical research papers from Biomed Central. The results were evaluated using the ROUGE metric and qualitative evaluation by medical experts. The ROUGE metric yielded scores of 0.4838 (Rouge-1), 0.2174 (Rouge-2), and 0.2206 (Rouge-L), while the qualitative evaluation achieved an average score of 4.10, 4.06, 3.55, 4.0, and 4.0 for completeness, relevance, conciseness, informativity, and readability, respectively. The results demonstrate the effectiveness of the proposed method in summarizing long medical documents.

A review on deep learning methods for heart sound signal analysis.

Application of Deep Learning (DL) methods is being increasingly appreciated by researchers from the biomedical engineering domain in which heart sound analysis is an important topic of study. Diversity in methodology, results, and complexity causes uncertainties in obtaining a realistic picture of the methodological performance from the reported methods. This survey paper provides the results of a broad retrospective study on the recent advances in heart sound analysis using DL methods. Representation of the results is performed according to both methodological and applicative taxonomies. The study method covers a wide span of related keywords using well-known search engines. Implementation of the observed methods along with the related results is pervasively represented and compared. It is observed that convolutional neural networks and recurrent neural networks are the most commonly used ones for discriminating abnormal heart sounds and localization of heart sounds with 67.97% and 33.33% of the related papers, respectively. The convolutional neural network and the autoencoder network show a perfect accuracy of 100% in the case studies on the classification of abnormal from normal heart sounds. Nevertheless, this superiority against other methods with lower accuracy is not conclusive due to the inconsistency in evaluation.

The Optical Forces and Torques Exerted by Airy Light-Sheet on Magnetic Particles Utilized for Targeted Drug Delivery.

The remarkable properties of magnetic nanostructures have sparked considerable interest within the biomedical domain, owing to their potential for diverse applications. In targeted drug delivery systems, therapeutic molecules can be loaded onto magnetic nanocarriers and precisely guided and released within the body with the assistance of an externally applied magnetic field. However, conventional external magnetic fields generated by permanent magnets or electromagnets are limited by finite magnetic field gradients, shallow penetration depths, and low precision. The novel structured light field known as the Airy light-sheet possesses unique characteristics such as non-diffraction, self-healing, and self-acceleration, which can potentially overcome the limitations of traditional magnetic fields to some extent. While existing studies have primarily focused on the manipulation of dielectric particles by Airy light-sheet, comprehensive analyses exploring the intricate interplay between Airy light-sheet and magnetic nanostructures are currently lacking in the literature, with only preliminary theoretical discussions available. This study systematically explores the mechanical response of magnetic spherical particles under the influence of Airy light-sheet, including radiation forces and spin torques. Furthermore, we provide an in-depth analysis of the effects of particle size, permittivity, permeability, and incident light-sheet parameters on the mechanical effects. Our research findings not only offer new theoretical guidance and practical references for the application of magnetic nanoparticles in biomedicine but also provide valuable insights for the manipulation of other types of micro/nanoparticles using structured light fields.

Alginate Formulation for Wound Healing Applications.

Significance: Alginate, sourced from seaweed, holds significant importance in industrial and biomedical domains due to its versatile properties. Its chemical composition, primarily comprising β-D-mannuronic acid and α-L-guluronic acid, governs its physical and biological attributes. This polysaccharide, extracted from brown algae and bacteria, offers diverse compositions impacting key factors such as molecular weight, flexibility, solubility, and stability. Recent Advances: Commercial extraction methods yield soluble sodium alginate essential for various biomedical applications. Extraction processes involve chemical treatments converting insoluble alginic acid salts into soluble forms. While biosynthesis pathways in bacteria and algae share similarities, differences in enzyme utilization and product characteristics are noted. Critical Issues: Despite its widespread applicability, challenges persist regarding alginate's stability, biodegradability, and bioactivity. Further understanding of its interactions in complex biological environments and the optimization of extraction and synthesis processes are imperative. Additionally, concerns regarding immune responses to alginate-based implants necessitate thorough investigation. Future Directions: Future research endeavors aim to enhance alginate's stability and bioactivity, facilitating its broader utilization in regenerative medicine and therapeutic interventions. Novel approaches focusing on tailored hydrogel formations, advanced drug delivery systems, and optimized cellular encapsulation techniques hold promise. Continued exploration of alginate's potential in tissue engineering and wound healing, alongside efforts to address critical issues, will drive advancements in biomedical applications.

A context-enhanced neural network model for biomedical event trigger detection

As an important component of biomedical event extraction, biomedical event trigger detection has received extensive research attention in recent years. Most studies focus on designing various models or features according to the original text itself, but fail to leverage contextual information of the original text from external knowledge base such as Wikipedia, which is publicly available. To address the issue, we propose a context-enhanced neural network model that automatically integrates the related information from external knowledge base for biomedical event trigger detection. Specifically, the proposed model first extracts the related context of the original text from external knowledge base. Then the original text and its context are sequentially fed into the BERT embedding layer and Transformer convolution layer to learn high-level semantic representation. Finally, the probability of possible tags is calculated using the CRF layer. Experimental results on the MLEE dataset show our proposed model achieves 86.83% F1 score, outperforming the existing methods and context-enhanced baseline systems significantly. Experimental analysis also indicates the effectiveness of contextual information for trigger detection in biomedical domain.

Biomedical Information Retrieval with Positive-Unlabeled Learning and Knowledge Graphs

The rapid growth of biomedical publications has presented significant challenges in the field of information retrieval. Most existing work focuses on document retrieval given explicit queries. However, in real applications such as curated biomedical database maintenance, explicit queries are missing. In this paper, we propose a two-step model for biomedical information retrieval in the case that only a small set of example documents is available without explicit queries. Initially, we extract keywords from the observed documents using large pre-trained language models and biomedical knowledge graphs. These keywords are then enriched with domain-specific entities. Information retrieval techniques can subsequently use the collected entities to rank the documents. Following this, we introduce an iterative Positive-Unlabeled learning method to classify all unlabeled documents. Experiments conducted on the PubMed dataset demonstrate that the proposed technique outperforms the state-of-the-art positive-unlabeled learning methods. The results underscore the effectiveness of integrating large language models and biomedical knowledge graphs in improving zero-shot information retrieval performance in the biomedical domain.

R2D2-GAN: Robust Dual Discriminator Generative Adversarial Network for Microscopy Hyperspectral Image Super-Resolution.

High-resolution microscopy hyperspectral (HS) images can provide highly detailed spatial and spectral information, enabling the identification and analysis of biological tissues at a microscale level. Recently, significant efforts have been devoted to enhancing the resolution of HS images by leveraging high spatial resolution multispectral (MS) images. However, the inherent hardware constraints lead to a significant distribution gap between HS and MS images, posing challenges for image super-resolution within biomedical domains. This discrepancy may arise from various factors, including variations in camera imaging principles (e.g., snapshot and push-broom imaging), shooting positions, and the presence of noise interference. To address these challenges, we introduced a unique unsupervised super-resolution framework named R2D2-GAN. This framework utilizes a generative adversarial network (GAN) to efficiently merge the two data modalities and improve the resolution of microscopy HS images. Traditionally, supervised approaches have relied on intuitive and sensitive loss functions, such as mean squared error (MSE). Our method, trained in a real-world unsupervised setting, benefits from exploiting consistent information across the two modalities. It employs a game-theoretic strategy and dynamic adversarial loss, rather than relying solely on fixed training strategies for reconstruction loss. Furthermore, we have augmented our proposed model with a central consistency regularization (CCR) module, aiming to further enhance the robustness of the R2D2-GAN. Our experimental results show that the proposed method is accurate and robust for super-resolution images. We specifically tested our proposed method on both a real and a synthetic dataset, obtaining promising results in comparison to other state-of-the-art methods.

A multimodal approach for few-shot biomedical named entity recognition in low-resource languages

In this study, we revisit named entity recognition (NER) in the biomedical domain from a multimodal perspective, with a particular focus on applications in low-resource languages. Existing research primarily relies on unimodal methods for NER, which limits the potential for capturing diverse information. To address this limitation, we propose a novel method that integrates a cross-modal generation module to transform unimodal data into multimodal data, thereby enabling the use of enriched multimodal information for NER. Additionally, we design a cross-modal filtering module to mitigate the adverse effects of text-image mismatches in multimodal NER. We validate our proposed method on two biomedical datasets specifically curated for low-resource languages. Experimental results demonstrate that our method significantly enhances the performance of NER, highlighting its effectiveness and potential for broader applications in biomedical research and low-resource language contexts.

Deformation-Resistant Underwater Adhesion in a Wide Salinity Range.

Conventional adhesives experience reduced adhesion when exposed to aqueous environments. The development of underwater adhesives capable of forming strong and durable bonds across various wet substrates is crucial in biomedical and engineering domains. Nonetheless, limited emphasis placed on retaining high adhesion strengths in different saline environments, addressing challenges such as elevated osmotic pressure and spontaneous dimensional alterations. Herein, a series of ionogel-based underwater adhesives are developed using a copolymerization approach that incorporates "dynamic complementary cross-linking" networks. Synergistic engineering of building blocks, cross-linking networks, pendant groups and counterions within ionogels ensures their adhesion and cohesion in brine spanning a wide salinity range. A high adhesion strength of ≈3.6MPa is attained in freshwater. Gratifyingly, steady adhesion strengths exceeding 3.3MPa are retained in hypersaline solutions with salinity ranging from 50 to 200gkg-1, delivering one of the best-performing underwater adhesives suitable for diverse saline solutions. A combination of outstanding durability, reliability, deformation resistance, salt tolerance, and self-healing properties showcases the "self-contained" underwater adhesion. This study shines light on the facile fabrication of catechol-free ionogel-based adhesives, not merely boosting adhesion strengths in freshwater, but also broadening their applicability across various saline environments.

From pre-training to fine-tuning: An in-depth analysis of Large Language Models in the biomedical domain

In this study, we delve into the adaptation and effectiveness of Transformer-based, pre-trained Large Language Models (LLMs) within the biomedical domain, a field that poses unique challenges due to its complexity and the specialized nature of its data. Building on the foundation laid by the transformative architecture of Transformers, we investigate the nuanced dynamics of LLMs through a multifaceted lens, focusing on two domain-specific tasks, i.e., Natural Language Inference (NLI) and Named Entity Recognition (NER). Our objective is to bridge the knowledge gap regarding how these models’ downstream performances correlate with their capacity to encapsulate task-relevant information. To achieve this goal, we probed and analyzed the inner encoding and attention mechanisms in LLMs, both encoder- and decoder-based, tailored for either general or biomedical-specific applications. This examination occurs before and after the models are fine-tuned across various data volumes. Our findings reveal that the models’ downstream effectiveness is intricately linked to specific patterns within their internal mechanisms, shedding light on the nuanced ways in which LLMs process and apply knowledge in the biomedical context. The source code for this paper is available at https://github.com/agnesebonfigli99/LLMs-in-the-Biomedical-Domain.

PLRTE: Progressive learning for biomedical relation triplet extraction using large language models

Document-level relation triplet extraction is crucial in biomedical text mining, aiding in drug discovery and the construction of biomedical knowledge graphs. Current language models face challenges in generalizing to unseen datasets and relation types in biomedical relation triplet extraction, which limits their effectiveness in these crucial tasks. To address this challenge, our study optimizes models from two critical dimensions: data-task relevance and granularity of relations, aiming to enhance their generalization capabilities significantly. We introduce a novel progressive learning strategy to obtain the PLRTE model. This strategy not only enhances the model’s capability to comprehend diverse relation types in the biomedical domain but also implements a structured four-level progressive learning process through semantic relation augmentation, compositional instruction, and dual-axis level learning. Our experiments on the DDI and BC5CDR document-level biomedical relation triplet datasets demonstrate a significant performance improvement of 5% to 20% over the current state-of-the-art baselines. Furthermore, our model exhibits exceptional generalization capabilities on the unseen Chemprot and GDA datasets, further validating the effectiveness of optimizing data-task association and relation granularity for enhancing model generalizability.

BI‐LAVA: Biocuration With Hierarchical Image Labelling Through Active Learning and Visual Analytics

AbstractIn the biomedical domain, taxonomies organize the acquisition modalities of scientific images in hierarchical structures. Such taxonomies leverage large sets of correct image labels and provide essential information about the importance of a scientific publication, which could then be used in biocuration tasks. However, the hierarchical nature of the labels, the overhead of processing images, the absence or incompleteness of labelled data and the expertise required to label this type of data impede the creation of useful datasets for biocuration. From a multi‐year collaboration with biocurators and text‐mining researchers, we derive an iterative visual analytics and active learning (AL) strategy to address these challenges. We implement this strategy in a system called BI‐LAVA—Biocuration with Hierarchical Image Labelling through Active Learning and Visual Analytics. BI‐LAVA leverages a small set of image labels, a hierarchical set of image classifiers and AL to help model builders deal with incomplete ground‐truth labels, target a hierarchical taxonomy of image modalities and classify a large pool of unlabelled images. BI‐LAVA's front end uses custom encodings to represent data distributions, taxonomies, image projections and neighbourhoods of image thumbnails, which help model builders explore an unfamiliar image dataset and taxonomy and correct and generate labels. An evaluation with machine learning practitioners shows that our mixed human–machine approach successfully supports domain experts in understanding the characteristics of classes within the taxonomy, as well as validating and improving data quality in labelled and unlabelled collections.

A comprehensive review of existing corpora and methods for creating annotated corpora for event extraction tasks

Abstract Purpose The purpose of this study is to serve as a comprehensive review of the existing annotated corpora. This review study aims to provide information on the existing annotated corpora for event extraction, which are limited but essential for training and improving the existing event extraction algorithms. In addition to the primary goal of this study, it provides guidelines for preparing an annotated corpus and suggests suitable tools for the annotation task. Design/methodology/approach This study employs an analytical approach to examine available corpus that is suitable for event extraction tasks. It offers an in-depth analysis of existing event extraction corpora and provides systematic guidelines for researchers to develop accurate, high-quality corpora. This ensures the reliability of the created corpus and its suitability for training machine learning algorithms. Findings Our exploration reveals a scarcity of annotated corpora for event extraction tasks. In particular, the English corpora are mainly focused on the biomedical and general domains. Despite the issue of annotated corpora scarcity, there are several high-quality corpora available and widely used as benchmark datasets. However, access to some of these corpora might be limited owing to closed-access policies or discontinued maintenance after being initially released, rendering them inaccessible owing to broken links. Therefore, this study documents the available corpora for event extraction tasks. Research limitations Our study focuses only on well-known corpora available in English and Chinese. Nevertheless, this study places a strong emphasis on the English corpora due to its status as a global lingua franca, making it widely understood compared to other languages. Practical implications We genuinely believe that this study provides valuable knowledge that can serve as a guiding framework for preparing and accurately annotating events from text corpora. It provides comprehensive guidelines for researchers to improve the quality of corpus annotations, especially for event extraction tasks across various domains. Originality/value This study comprehensively compiled information on the existing annotated corpora for event extraction tasks and provided preparation guidelines.

Spatial Computing Opportunities in Biomedical Decision Support: The Atlas-EHR Vision

We consider the problem of reducing the time that healthcare professionals need to understand the patient’s medical history through the next generation of biomedical decision support. This problem is societally important because it has the potential to improve healthcare quality and patient outcomes. However, navigating electronic health records (EHR) is challenging due to high patient-doctor ratios, potentially long medical histories, urgency of treatment for some medical conditions, and patient variability. The current EHR systems provide only a longitudinal view of patient medical history, which is time-consuming to browse, and doctors often need to engage nurses, residents, and others for initial analysis. To overcome this limitation, we envision an alternative spatial representation of patient histories (e.g., electronic health records) and other biomedical data in the form of Atlas-EHR. Just like Google Maps, which allows a global, national, regional, and local view, Atlas-EHR can start with an overview of the patient’s anatomy and history before drilling down to spatially anatomical subsystems, their individual components, or subcomponents. Atlas-EHR presents a compelling opportunity for spatial computing since healthcare is almost a fifth of the US economy. However, traditional spatial computing designed for geographic use cases (e.g., navigation, land survey, and mapping) faces many hurdles in the biomedical domain. This article presents several open research questions under this theme in five broad areas of spatial computing.

A qualitative interview study exploring continuity within a community integrated palliative care model and the influence of remote and digital approaches to care.

Demand for palliative care is rising. Recent UK policy approaches promote integrated care models - collaborations between generalist practitioners and multidisciplinary specialists - and remote and digital practices. The extent to which different forms of continuity are supported within this evolving context is currently unclear. To explore the experience of continuity and impact of remote and digital practices within an integrated palliative care model. A qualitative interview study of patients and bereaved relatives recruited from a GP practice list and healthcare professionals delivering the integrated palliative care service for that population. 20 narrative and semi-structured interviews were conducted with 22 patients, relatives, and professionals between May 2022 and November 2023. They explored how care was delivered or received, focusing on coherency and the use of remote and digital practices. Data were theorized using a novel framework that considered psychodynamic, biomedical, sociotechnical, and sociopolitical domains of continuity. The need for human care and connection were of primary importance and affected by intersubjective, biomedical, sociotechnical, and sociopolitical factors that influenced continuity of care. Despite the logistical ease of remote and digital practices, professionals had to work harder or around technologies to provide a 'caring' service. This was exacerbated by a lack of co-localisation, loss of longitudinal relationships, and reduction in tacit knowledge. Numerous complex factors and the exacerbating effects of remote and digital practices influence continuity and coherency within an integrated palliative care model.

Chiral fluorescent carbon dots for tyrosine enantiomers: Discrimination, mechanism and cell imaging

The development of chiral analytical methods for tyrosine enantiomers, characterized by superior recognition performance and selectivity, holds significant potential for application in the biochemical and biomedical domains associated with tyrosine. Herein, a straightforward and effective strategy for tyrosine enantiomers identification and purity analysis by chiral carbon dots (CDs) fluorescence sensor were reported. The chiral CDs were designed by using L-cysteine and 2,4-diaminophenol hydrochloride through a gentle one-step synthesis strategy at room temperature. The resulting chiral CDs exhibited completely different fluorescence response to L-tyrosine and D-tyrosine, that is, L-tyrosine could enhance the fluorescence of the chiral CDs, but D-tyrosine made no difference. The fluorescent differential recognition factor for enantiomers was as high as 23.2, which was the highest be achievement to our best knowledge so far. The varying discriminatory capabilities of chiral CDs towards tyrosine enantiomers were also applicable to HeLa cells. To confirm the recognition mechanism of chiral CDs to tyrosine enantiomers, the chiral CDs-modified SiO2 stationary phase were synthesized and applied to separate the tyrosine enantiomers in reverse-phase HPLC mode. Furthermore, density functional theory was combined with the fluorescence spectroscopy and chromatographic results to verify that the recognition ability was related to the difference of weak interaction energy and Gibbs free energy between the precursor molecule of the chiral CDs and the tyrosine enantiomers. This cost-effective and highly selectivity assay not only provided a valuable tool for tyrosine enantiomers identification and purity analysis, but also delivered an important reference for the recognition and purity identification of other chiral drugs.

An effective framework for measuring the novelty of scientific articles through integrated topic modeling and cloud model

Novelty is a critical characteristic of innovative scientific articles, and accurately identifying novelty can facilitate the early detection of scientific breakthroughs. However, existing methods for measuring novelty have two main limitations: (1) Metadata-based approaches, such as citation analysis, are retrospective and do not alleviate the pressures of the peer review process or enable timely tracking of scientific progress; (2) Content-based methods have not adequately addressed the inherent uncertainty between the qualitative concept of novelty and the textual representation of papers. To address these issues, we propose a practical and effective framework for measuring the novelty of scientific articles through integrated topic modeling and cloud model, referred to as MNSA-ITMCM. In this framework, papers are represented as topic combinations, and novelty is reflected in the organic reorganization of these topics. We use the BERTopic model to generate semantically informed topics, and then apply a topic selection algorithm based on maximum marginal relevance to obtain a topic combination that balances similarity and diversity. Furthermore, we leverage the cloud model from fuzzy mathematics to quantify novelty, overcoming the uncertainty inherent in natural language expression and topic modeling to improve the accuracy of novelty measurement. To validate the effectiveness of our framework, we conducted empirical evaluations on papers from the Cell 2021 journal (biomedical domain) and the ICLR 2023 conference (computer science domain). Through correlation analysis and prediction error analysis, our framework demonstrated the ability to identify different types of novel papers and accurately predict their novelty levels. The proposed framework is applicable across diverse scientific disciplines and publication venues, benefiting researchers, librarians, science evaluation agencies, policymakers, and funding organizations by improving the efficiency and comprehensiveness of identifying novelty research.

VADIS: A Visual Analytics Pipeline for Dynamic Document Representation and Information-Seeking.

In the biomedical domain, visualizing the document embeddings of an extensive corpus has been widely used in informationseeking tasks. However, three key challenges with existing visualizations make it difficult for clinicians to find information efficiently. First, the document embeddings used in these visualizations are generated statically by pretrained language models, which cannot adapt to the user's evolving interest. Second, existing document visualization techniques cannot effectively display how the documents are relevant to users' interest, making it difficult for users to identify the most pertinent information. Third, existing embedding generation and visualization processes suffer from a lack of interpretability, making it difficult to understand, trust and use the result for decision-making. In this paper, we present a novel visual analytics pipeline for user-driven document representation and iterative information seeking (VADIS). VADIS introduces a prompt-based attention model (PAM) that generates dynamic document embedding and document relevance adjusted to the user's query. To effectively visualize these two pieces of information, we design a new document map that leverages a circular grid layout to display documents based on both their relevance to the query and the semantic similarity. Additionally, to improve the interpretability, we introduce a corpus-level attention visualization method to improve the user's understanding of the model focus and to enable the users to identify potential oversight. This visualization, in turn, empowers users to refine, update and introduce new queries, thereby facilitating a dynamic and iterative information-seeking experience. We evaluated VADIS quantitatively and qualitatively on a real-world dataset of biomedical research papers to demonstrate its effectiveness.

Skip-AttSeqNet: Leveraging skip connection and attention-driven Seq2seq model to enhance eye movement event detection in Parkinson’s disease

To address the limitations of traditional algorithms in detecting eye movement events, particularly in Parkinson’s disease (PD) patients, this study introduces Skip-AttSeqNet. It presents an innovative approach combining skip-connected, one-dimensional convolutional neural networks with an attention-enhanced, bidirectional long short-term memory network. This hybrid architecture significantly advances smooth pursuit (SP) event detection, as evidenced by its performance on both the GazeCom dataset and a unique dataset of PD patient eye movements. Key innovations in this work include the utilization of skip connections and attention mechanisms, along with optimized training–validation set division, collectively enhancing the model’s accuracy while mitigating overfitting. Skip-AttSeqNet outperforms existing algorithms, achieving a 3.2% higher sample-level F1 score and a notable 6.2% increase in event-level F1 scores for SP detection. Furthermore, we established a smooth-pursuit experimental paradigm and identified significant differences in saccade and SP features between PD patients and healthy older adults through statistical analysis using the Mann–Whitney test. These findings underscore the potential of eye movement metrics as biomarkers for PD, thereby not only strengthening PD diagnosis but also enriching the intersection of computer vision and biomedical research domains.