搜索结果：Biomedical and environmental sciences : BES

AI is a magnificent field that directly and profoundly touches on numerous disciplines ranging from philosophy, computer science, engineering, mathematics, decision and data science and economics, to cognitive science, neuroscience and more. The number of applications and impact of AI is second to none and the potential of AI to broadly impact future science developments is particularly thrilling. While attempts to understand knowledge, reasoning, cognition and learning go back centuries, AI remains a relatively new field. In part due to the fact it has so many wide-ranging overlaps with other disparate fields it appears to have trouble developing a robust identity and culture. Here we suggest that contrasting the fast-moving AI culture to biological and biomedical sciences is both insightful and useful way to inaugurate a healthy tradition needed to envision and manage our ascent to AGI and beyond (independent of the AI Platforms used). The co-evolution of AI and Biomedical Science offers many benefits to both fields. In a previous perspective, we suggested that biomedical laboratories or centers can usefully embrace logistic traditions in AI labs that will allow them to be highly

Artificial Intelligence (AI) is changing the world, but its impacts on the environment and human well-being remain uncertain. We conducted a systematic literature review of 1,291 studies selected from 6,655 records, identifying the main impacts of AI and how they are assessed. The evidence reveals an uneven landscape: 72% of environmental studies focus narrowly on energy use and CO2 emissions, while only 11% consider systemic effects. Well-being research is largely conceptual and overlooks subjective dimensions. Strikingly, 83% of environmental studies portray AI's impacts as positive, while well-being analyses show a near-even split overall (44% positive; 46% negative). However, this split masks differences across well-being dimensions. While the impacts of AI on income and health are expected to be positive, its impacts on inequality, social cohesion, and employment are expected to be negative. Based on our findings, we suggest several areas for future research. Environmental assessments should incorporate water, material, and biodiversity impacts, and apply a full life-cycle perspective, while well-being research should prioritise empirical analyses. Evaluating AI's overall impa

We introduce reduced order methods as an efficient strategy to solve parametrized non-linear and time dependent optimal flow control problems governed by partial differential equations. Indeed, the optimal control problems require a huge computational effort in order to be solved, most of all in physical and/or geometrical parametrized settings. Reduced order methods are a reliable and suitable approach, increasingly gaining popularity, to achieve rapid and accurate optimal solutions in several fields, such as in biomedical and environmental sciences. In this work, we employ a POD-Galerkin reduction approach over a parametrized optimality system, derived from the Karush-Kuhn-Tucker conditions. The methodology presented is tested on two boundary control problems, governed respectively by (i) time dependent Stokes equations and (ii) steady non-linear Navier-Stokes equations.

This study investigates the interconnectivity of firms and Environmental Justice Organizations (EJOs) involved in socio-environmental conflicts worldwide, using data from the Environmental Justice Atlas (EJAtlas). By constructing a multilayer network that links firms, conflicts, and EJOs, the research applies social network analysis to evaluate the simultaneous involvement of these actors across multiple disputes. Both projected networks of firms and EJOs have been analysed by aggregating nodes by categories and countries to reveal structural differences. Findings reveal a stark contrast between the interconnectedness of firms and EJOs. Multinational corporations form a cohesive global network, enabling them to coordinate strategies and exert influence across regions. Conversely, EJOs are fragmented, often operating in isolated clusters with limited interconnection but forming a robust, decentralized and self-organized global network. Firms network present a strong dependence on pertaining conflict category while EJOs network does not depend on conflict category. This structural difference suggests a risk of systemic and structural coordination for firms towards exploitative expans

Motivation: Biomedical question answering often requires evidence beyond topically retrieved literature, including gene alias resolution, database identifier normalization, and atlas-derived biological measurements. However, existing retrieval-augmented generation (RAG) systems typically follow a fixed workflow and lack an explicit mechanism for deciding when retrieved text is sufficient, when curated biomedical knowledge is required, or when executable evidence assembly over structured measurements should be invoked. This motivates a substrate-aware large language model (LLM) harness that selectively assembles sufficient evidence across literature, knowledge bases, and biological atlases. Results: We introduce BioHarness, an LLM harness for staged biomedical evidence assembly across literature retrieval, curated biomedical knowledge resources, and atlas-derived structured measurements. BioHarness first attempts to answer from reranked literature evidence and escalates through grounded cascade control to REPL-style evidence assembly only when the current evidence is uncertain, weakly grounded, or substrate-mismatched. Across 19,302 biomedical QA items spanning seven answer formats,

Physics-informed machine learning (PIML) is emerging as a potentially transformative paradigm for modeling complex biomedical systems by integrating parameterized physical laws with data-driven methods. Here, we review three main classes of PIML frameworks: physics-informed neural networks (PINNs), neural ordinary differential equations (NODEs), and neural operators (NOs), highlighting their growing role in biomedical science and engineering. We begin with PINNs, which embed governing equations into deep learning models and have been successfully applied to biosolid and biofluid mechanics, mechanobiology, and medical imaging among other areas. We then review NODEs, which offer continuous-time modeling, especially suited to dynamic physiological systems, pharmacokinetics, and cell signaling. Finally, we discuss deep NOs as powerful tools for learning mappings between function spaces, enabling efficient simulations across multiscale and spatially heterogeneous biological domains. Throughout, we emphasize applications where physical interpretability, data scarcity, or system complexity make conventional black-box learning insufficient. We conclude by identifying open challenges and fu

Biomedical Question Answering systems play a critical role in processing complex medical queries, yet they often struggle with the intricate nature of medical data and the demand for multi-hop reasoning. In this paper, we propose a model designed to effectively address both direct and sequential questions. While sequential questions are decomposed into a chain of sub-questions to perform reasoning across a chain of steps, direct questions are processed directly to ensure efficiency and minimise processing overhead. Additionally, we leverage multi-source information retrieval and in-context learning to provide rich, relevant context for generating answers. We evaluated our model on the BioCreative IX - MedHopQA Shared Task datasets. Our approach achieves an Exact Match score of 0.84, ranking second on the current leaderboard. These results highlight the model's capability to meet the challenges of Biomedical Question Answering, offering a versatile solution for advancing medical research and practice.

Given the growing use of Artificial Intelligence (AI) and machine learning (ML) methods across all aspects of environmental sciences, it is imperative that we initiate a discussion about the ethical and responsible use of AI. In fact, much can be learned from other domains where AI was introduced, often with the best of intentions, yet often led to unintended societal consequences, such as hard coding racial bias in the criminal justice system or increasing economic inequality through the financial system. A common misconception is that the environmental sciences are immune to such unintended consequences when AI is being used, as most data come from observations, and AI algorithms are based on mathematical formulas, which are often seen as objective. In this article, we argue the opposite can be the case. Using specific examples, we demonstrate many ways in which the use of AI can introduce similar consequences in the environmental sciences. This article will stimulate discussion and research efforts in this direction. As a community, we should avoid repeating any foreseeable mistakes made in other domains through the introduction of AI. In fact, with proper precautions, AI can be

Large language models often perform well on biomedical NLP tasks but may fail to link ontology terms to their correct identifiers. We investigate why these failures occur by analyzing predictions across two major ontologies, Human Phenotype Ontology and Gene Ontology, and two high-performing models, GPT-4o and LLaMa 3.1 405B. We evaluate nine candidate features related to term familiarity, identifier usage, morphology, and ontology structure. Univariate and multivariate analyses show that exposure to ontology identifiers is the strongest predictor of linking success.

The integration of AI-assisted biomedical image analysis into clinical practice demands AI-generated findings that are not only accurate but also interpretable to clinicians. However, existing biomedical AI models generally lack the ability to simultaneously generate diagnostic findings and localize corresponding biomedical objects. This limitation makes it challenging for clinicians to correlate AI-generated findings with visual evidence (e.g., tiny lesions) in images and interpret the results of AI models. To address this challenge, we introduce UniBiomed, the first universal foundation model for grounded biomedical image interpretation, which is capable of generating accurate diagnostic findings and simultaneously segmenting the corresponding biomedical targets. UniBiomed is based on a novel integration of Multi-modal Large Language Model and Segment Anything Model, which can effectively unify diverse biomedical tasks in universal training for advancing grounded interpretation. To develop UniBiomed, we curate a large-scale dataset comprising over 27 million triplets of images, region annotations, and text descriptions across ten biomedical imaging modalities. Extensive validatio

Computer-assisted diagnostic and prognostic systems of the future should be capable of simultaneously processing multimodal data. Multimodal deep learning (MDL), which involves the integration of multiple sources of data, such as images and text, has the potential to revolutionize the analysis and interpretation of biomedical data. However, it only caught researchers' attention recently. To this end, there is a critical need to conduct a systematic review on this topic, identify the limitations of current work, and explore future directions. In this scoping review, we aim to provide a comprehensive overview of the current state of the field and identify key concepts, types of studies, and research gaps with a focus on biomedical images and texts joint learning, mainly because these two were the most commonly available data types in MDL research. This study reviewed the current uses of multimodal deep learning on five tasks: (1) Report generation, (2) Visual question answering, (3) Cross-modal retrieval, (4) Computer-aided diagnosis, and (5) Semantic segmentation. Our results highlight the diverse applications and potential of MDL and suggest directions for future research in the fi

This paper provides an overview of NVIDIA NeMo's neural machine translation systems for the constrained data track of the WMT21 News and Biomedical Shared Translation Tasks. Our news task submissions for English-German (En-De) and English-Russian (En-Ru) are built on top of a baseline transformer-based sequence-to-sequence model. Specifically, we use a combination of 1) checkpoint averaging 2) model scaling 3) data augmentation with backtranslation and knowledge distillation from right-to-left factorized models 4) finetuning on test sets from previous years 5) model ensembling 6) shallow fusion decoding with transformer language models and 7) noisy channel re-ranking. Additionally, our biomedical task submission for English-Russian uses a biomedically biased vocabulary and is trained from scratch on news task data, medically relevant text curated from the news task dataset, and biomedical data provided by the shared task. Our news system achieves a sacreBLEU score of 39.5 on the WMT'20 En-De test set outperforming the best submission from last year's task of 38.8. Our biomedical task Ru-En and En-Ru systems reach BLEU scores of 43.8 and 40.3 respectively on the WMT'20 Biomedical Ta

Within clinical, biomedical, and translational science, an increasing number of projects are adopting graphs for knowledge representation. Graph-based data models elucidate the interconnectedness between core biomedical concepts, enable data structures to be easily updated, and support intuitive queries, visualizations, and inference algorithms. However, knowledge discovery across these "knowledge graphs" (KGs) has remained difficult. Data set heterogeneity and complexity; the proliferation of ad hoc data formats; poor compliance with guidelines on findability, accessibility, interoperability, and reusability; and, in particular, the lack of a universally-accepted, open-access model for standardization across biomedical KGs has left the task of reconciling data sources to downstream consumers. Biolink Model is an open source data model that can be used to formalize the relationships between data structures in translational science. It incorporates object-oriented classification and graph-oriented features. The core of the model is a set of hierarchical, interconnected classes (or categories) and relationships between them (or predicates), representing biomedical entities such as ge

Real and effective regulation of contributions to greenhouse gas emissions and pollutants requires unbiased and truthful monitoring. Blockchain has emerged not only as an approach that provides verifiable economical interactions but also as a mechanism to keep the measurement, monitoring, incentivation of environmental conservationist practices and enforcement of policy. Here, we present a survey of areas in what blockchain has been considered as a response to concerns on keeping an accurate recording of environmental practices to monitor levels of pollution and management of environmental practices. We classify the applications of blockchain into different segments of concerns, such as greenhouse gas emissions, solid waste, water, plastics, food waste, and circular economy, and show the objectives for the addressed concerns. We also classify the different blockchains and the explored and designed properties as identified for the proposed solutions. At the end, we provide a discussion about the niches and challenges that remain for future research.

Accurate histopathologic interpretation is key for clinical decision-making; however, current deep learning models for digital pathology are often overconfident and poorly calibrated in out-of-distribution (OOD) settings, which limit trust and clinical adoption. Safety-critical medical imaging workflows benefit from intrinsic uncertainty-aware properties that can accurately reject OOD input. We implement the Spectral-normalized Neural Gaussian Process (SNGP), a set of lightweight modifications that apply spectral normalization and replace the final dense layer with a Gaussian process layer to improve single-model uncertainty estimation and OOD detection. We evaluate SNGP vs. deterministic and MonteCarlo dropout on six datasets across three biomedical classification tasks: white blood cells, amyloid plaques, and colorectal histopathology. SNGP has comparable in-distribution performance while significantly improving uncertainty estimation and OOD detection. Thus, SNGP or related models offer a useful framework for uncertainty-aware classification in digital pathology, supporting safe deployment and building trust with pathologists.

Prion diseases are rare, rapidly progressive, and fatal neurodegenerative disorders that remain difficult to diagnose, particularly in their early stages because of nonspecific clinical presentations. However, to our knowledge, there is no publicly available prion-disease-focused dataset designed to capture a broad range of clinically relevant entities from the biomedical literature. We introduce PrionNER, a manually annotated named entity recognition dataset for prion disease clinical information in PubMed abstracts. The current release comprises 317 abstracts, 2,943 sentences, and 6,955 text-bound entity annotations spanning 15 coarse-grained and 31 fine-grained clinically oriented entity types covering diseases, symptoms, diagnostics, findings, anatomy, treatments, and temporal and statistical evidence. Inter-annotator agreement reaches 81.78 exact-match F1, indicating strong annotation consistency. We benchmark supervised BERT baselines, W2NER, and zero-shot extractors on PrionNER. W2NER is the strongest supervised model, and Gemma-4-31B is the strongest zero-shot model, but the benchmark remains challenging, especially for structurally complex mentions and fine-grained clinica

Large language models (LLMs) are increasingly evident for accurate question answering across various domains. However, rigorous evaluation of their performance on complex question-answering (QA) capabilities is essential before deployment in real-world biomedical and healthcare applications. This paper presents our approach to the MedHopQA track of the BioCreative IX shared task, which focuses on multi-hop biomedical question answering involving diseases, genes, and chemicals. We adopt a supervised fine-tuning strategy leveraging LLaMA 3 8B, enhanced with a curated biomedical question-answer dataset compiled from external sources including BioASQ, MedQuAD, and TREC. Three experimental setups are explored: fine-tuning on combined short and long answers, short answers only, and long answers only. While our models demonstrate strong domain understanding, achieving concept-level accuracy scores of up to 0.8, their Exact Match (EM) scores remain significantly lower, particularly in the test phase. We introduce a two-stage inference pipeline for precise short-answer extraction to mitigate verbosity and improve alignment with evaluation metrics. Despite partial improvements, challenges pe

Multiscale entropy (MSE) is a widely-used tool to analyze biomedical signals. It was proposed to overcome the deficiencies of conventional entropy methods when quantifying the complexity of time series. However, MSE is undefined for very short signals and slow for real-time applications because of the use of sample entropy (SampEn). To overcome these shortcomings, we introduce multiscale dispersion entropy (DisEn - MDE) as a very fast and powerful method to quantify the complexity of signals. MDE is based on our recently developed DisEn, which has a computation cost of O(N), compared with O(N2) for SampEn. We also propose the refined composite MDE (RCMDE) to improve the stability of MDE. We evaluate MDE, RCMDE, and refined composite MSE (RCMSE) on synthetic signals and find that these methods have similar behaviors but the MDE and RCMDE are significantly faster than MSE and RCMSE, respectively. The results also illustrate that RCMDE is more stable than MDE for short and noisy signals, which are common in biomedical applications. To evaluate the proposed methods on real signals, we employ three biomedical datasets, including focal and non-focal electroencephalograms (EEGs), blood pr

Objective: This study aims to review the recent advances in community challenges for biomedical text mining in China. Methods: We collected information of evaluation tasks released in community challenges of biomedical text mining, including task description, dataset description, data source, task type and related links. A systematic summary and comparative analysis were conducted on various biomedical natural language processing tasks, such as named entity recognition, entity normalization, attribute extraction, relation extraction, event extraction, text classification, text similarity, knowledge graph construction, question answering, text generation, and large language model evaluation. Results: We identified 39 evaluation tasks from 6 community challenges that spanned from 2017 to 2023. Our analysis revealed the diverse range of evaluation task types and data sources in biomedical text mining. We explored the potential clinical applications of these community challenge tasks from a translational biomedical informatics perspective. We compared with their English counterparts, and discussed the contributions, limitations, lessons and guidelines of these community challenges, whi