Hasil untuk "Veterinary medicine"

Rui Yang, Huitao Li, Weihao Xuan et al.

Despite continuous advances in medical technology, the global distribution of health care resources remains uneven. The development of large language models (LLMs) has transformed the landscape of medicine and holds promise for improving health care quality and expanding access to medical information globally. However, existing LLMs are primarily trained on high-resource languages, limiting their applicability in global medical scenarios. To address this gap, we constructed GlobMed, a large multilingual medical dataset, containing over 500,000 entries spanning 12 languages, including four low-resource languages. Building on this, we established GlobMed-Bench, which systematically assesses 56 state-of-the-art proprietary and open-weight LLMs across multiple multilingual medical tasks, revealing significant performance disparities across languages, particularly for low-resource languages. Additionally, we introduced GlobMed-LLMs, a suite of multilingual medical LLMs trained on GlobMed, with parameters ranging from 1.7B to 8B. GlobMed-LLMs achieved an average performance improvement of over 40% relative to baseline models, with a more than threefold increase in performance on low-resource languages. Together, these resources provide an important foundation for advancing the equitable development and application of LLMs globally, enabling broader language communities to benefit from technological advances.

Ayyüce Begüm Bektaş, Mithat Gönen

This paper claims that machine learning models deployed in high stakes domains such as medicine must be interpretable, shareable, reproducible and accountable. We argue that these principles should form the foundational design criteria for machine learning algorithms dealing with critical medical data, including survival analysis and risk prediction tasks. Black box models, while often highly accurate, struggle to gain trust and regulatory approval in health care due to a lack of transparency. We discuss how intrinsically interpretable modeling approaches (such as kernel methods with sparsity, prototype-based learning, and deep kernel models) can serve as powerful alternatives to opaque deep networks, providing insight into biomedical predictions. We then examine accountability in model development, calling for rigorous evaluation, fairness, and uncertainty quantification to ensure models reliably support clinical decisions. Finally, we explore how generative AI and collaborative learning paradigms (such as federated learning and diffusion-based data synthesis) enable reproducible research and cross-institutional integration of heterogeneous biomedical data without compromising privacy, hence shareability. By rethinking machine learning foundations along these axes, we can develop medical AI that is not only accurate but also transparent, trustworthy, and translatable to real-world clinical settings.

Zhi Liu, Tao Yang, Jing Wang et al.

Natural medicines, particularly Traditional Chinese Medicine (TCM), are gaining global recognition for their therapeutic potential in addressing human symptoms and diseases. TCM, with its systematic theories and extensive practical experience, provides abundant resources for healthcare. However, the effective application of TCM requires precise syndrome diagnosis, determination of treatment principles, and prescription formulation, which demand decades of clinical expertise. Despite advancements in TCM-based decision systems, machine learning, and deep learning research, limitations in data and single-objective constraints hinder their practical application. In recent years, large language models (LLMs) have demonstrated potential in complex tasks, but lack specialization in TCM and face significant challenges, such as too big model scale to deploy and issues with hallucination. To address these challenges, we introduce Tianyi with 7.6-billion-parameter LLM, a model scale proper and specifically designed for TCM, pre-trained and fine-tuned on diverse TCM corpora, including classical texts, expert treatises, clinical records, and knowledge graphs. Tianyi is designed to assimilate interconnected and systematic TCM knowledge through a progressive learning manner. Additionally, we establish TCMEval, a comprehensive evaluation benchmark, to assess LLMs in TCM examinations, clinical tasks, domain-specific question-answering, and real-world trials. The extensive evaluations demonstrate the significant potential of Tianyi as an AI assistant in TCM clinical practice and research, bridging the gap between TCM knowledge and practical application.

Zihan Xu, Haotian Ma, Gongbo Zhang et al.

Evidence-based medicine (EBM) is at the forefront of modern healthcare, emphasizing the use of the best available scientific evidence to guide clinical decisions. Due to the sheer volume and rapid growth of medical literature and the high cost of curation, there is a critical need to investigate Natural Language Processing (NLP) methods to identify, appraise, synthesize, summarize, and disseminate evidence in EBM. This survey presents an in-depth review of 129 research studies on leveraging NLP for EBM, illustrating its pivotal role in enhancing clinical decision-making processes. The paper systematically explores how NLP supports the five fundamental steps of EBM -- Ask, Acquire, Appraise, Apply, and Assess. The review not only identifies current limitations within the field but also proposes directions for future research, emphasizing the potential for NLP to revolutionize EBM by refining evidence extraction, evidence synthesis, appraisal, summarization, enhancing data comprehensibility, and facilitating a more efficient clinical workflow.

Tribikram Choudhury, Yacine Haddad, Michael Doser

Infrared quantum dots, operating in the near-infrared (NIR, 700-1400 nm), short-wavelength infrared (SWIR, 1400-3000 nm), mid-infrared (MIR, 3000-8000 nm) and long-wavelength infrared (LWIR, 8000-15000 nm) regions, have promising potential in optoelectronics, nanotechnology and military surveillance applications. The properties of infrared quantum dots exhibit quantum confinement effects, unlike bulk semiconductors, where their bandgap energy and emission wavelength can be precisely tuned by controlling particle size, composition, and surface chemistry. The wide tunability and unique quantum confinement effects in these infrared-emitting materials also make them attractive for both fundamental research, health and space technology. This paper focuses on the synthesis, fabrication and characterisation of polymer-based infrared quantum dots and explores the possible applications of infrared quantum dots in high-energy physics, medicine and astrophysics.

Carlos Garcia-Fernandez, Luis Felipe, Monique Shotande et al.

Large language models (LLMs) show promise in healthcare, but hallucinations remain a major barrier to clinical use. We present CHECK, a continuous-learning framework that integrates structured clinical databases with a classifier grounded in information theory to detect both factual and reasoning-based hallucinations. Evaluated on 1500 questions from 100 pivotal clinical trials, CHECK reduced LLama3.3-70B-Instruct hallucination rates from 31% to 0.3% - making an open source model state of the art. Its classifier generalized across medical benchmarks, achieving AUCs of 0.95-0.96, including on the MedQA (USMLE) benchmark and HealthBench realistic multi-turn medical questioning. By leveraging hallucination probabilities to guide GPT-4o's refinement and judiciously escalate compute, CHECK boosted its USMLE passing rate by 5 percentage points, achieving a state-of-the-art 92.1%. By suppressing hallucinations below accepted clinical error thresholds, CHECK offers a scalable foundation for safe LLM deployment in medicine and other high-stakes domains.

Yuan Tian, Min Zhou, Yitong Chen et al.

Patient face images provide a convenient mean for evaluating eye diseases, while also raising privacy concerns. Here, we introduce ROFI, a deep learning-based privacy protection framework for ophthalmology. Using weakly supervised learning and neural identity translation, ROFI anonymizes facial features while retaining disease features (over 98\% accuracy, $κ> 0.90$). It achieves 100\% diagnostic sensitivity and high agreement ($κ> 0.90$) across eleven eye diseases in three cohorts, anonymizing over 95\% of images. ROFI works with AI systems, maintaining original diagnoses ($κ> 0.80$), and supports secure image reversal (over 98\% similarity), enabling audits and long-term care. These results show ROFI's effectiveness of protecting patient privacy in the digital medicine era.

Richard Becker, Kati Haenssgen, Christina Precht et al.

Geon A Kim, Mi-Jin Lee, Eun Pyo Kim et al.

BYVET JOINT HEAL^TM (BJH) contains mucopolysaccharide protein, chondroitin sulfate, type II collagen, and omega-3 fatty acids, which protect and prevent osteoarthritis (OA)-associated tissue damage and degradation in dogs and cats. This study aimed to generate a novel dietary supplement and evaluate its prevention and therapeutic efficacy in an OA Sprague Dawley rat model induced using monosodium iodoacetate (MIA). Negative control, MIA-induced OA control (MIA), OA rats treated with BJH three weeks after (M+BJH3) and those treated two weeks before and three weeks after OA induction (BJH2+M+BJH3) groups were assigned. M+BJH3 and BJH2+M+BJH3 had similar mean body weight increases until 29 days. BJH2+M+BJH3 showed a significantly higher body weight than M+BJH3 and MIA on the final day. Interleukin-1β in BJH2+M+BJH3 was significantly lower than that in MIA. Tumor necrosis factor-α, aggrecan, matrix metalloproteinases13, and cyclooxygenase-2 levels in M+BJH3 and BJH2+M+BJH3 significantly differed compared to those in MIA. BJH administration before OA induction significantly decreased OA severity and functional recovery. Consuming a BJH supplement showed modifying and chondroprotective effects and significantly reduced cartilage degeneration and inflammation with no side effects. Hence, our findings demonstrate the potential of using BJH as a safe therapeutic and preventive supplement for OA and associated cartilage abnormalities. Also, 30 dogs diagnosed with OA by a veterinarian participated in the clinical trial, and BJH was provided for 8 weeks. Blood tests (CBC, serum chemistry) and joint assessment were performed before and after the feeding, and the effects of a BJH supplement were compared. BJH supplement was easy to administer, and no side effects were reported. Feeding BJH supplementation alone to dogs with arthritis had an overall positive effect on arthritis scores for 8 weeks without any other treatment, including non-steroidal drugs.

Samson Leta, Meskerem Mulisa Misgana, Bethel Befekadu Jaleta et al.

Abstract Arboviral diseases transmitted by mosquitoes, including dengue, Chikungunya, Zika, yellow fever, West Nile virus (WNV), and Rift Valley fever (RVF), pose a significant public health challenge globally, particularly impacting populations in low and middle-income countries. Conventional mosquito control methods, which primarily rely on insecticides, face critical challenges, including the development of insecticide resistance and environmental concerns. In this context, Wolbachia, an endosymbiotic bacterium, presents an alternative strategy due to its ability to manipulate mosquito reproduction and impede the transmission of pathogens. This study aimed to detect and assess the genetic diversity of Wolbachia and prophage WO in Ethiopian mosquitoes. Mosquitoes were collected from various ecological niches in the Great Rift Valley. Molecular analyses were performed to identify the presence of Wolbachia using PCR targeting the 16 S rRNA and wsp genes. Additionally, the presence of prophage WO was assessed by detecting the conserved orf7 capsid protein gene. To understand genetic diversity, phylogenetic and genetic diversity analyses were performed. Wolbachia was detected in 44.2% (34/77) of mosquitoes using the 16 S rRNA gene and 46.8% (36/77) using the wsp gene. The highest prevalence was observed in Cx. pipiens complex (100%, 11/11) and Ma. uniformis (92.3%, 12/13). Prophage WO was detected in 46.8% (36/77) of mosquitoes, with evidence of multiple-strain co-infections in Cx. pipiens complex. Phylogenetic analysis classified all isolates within Wolbachia pipientis Supergroup B. This study provides the first preliminary characterization of Wolbachia and prophage WO in Ethiopian mosquitoes, revealing evidence of genetic diversity. These findings lay the conceptual foundation of potential Wolbachia-based vector control strategies in Ethiopia and underscore the need for further studies on strain-specific impacts on vector competence and arboviral transmission dynamics.

Sofía Huelbes, May Gómez, Ico Martínez et al.

Microplastic pollution in the ocean is a growing problem. It affects the entire ecosystem and, therefore, the species that inhabit it. Plastics can be filtered or ingested by organisms, entering and negatively affecting individuals. Among the populations affected are crustaceans. In previous studies, fibers have been found mainly in the stomach contents of these animals, although other types, such as pellets, have also been found. This study examines the presence of microplastics in <i>Cronius ruber</i>, an invasive crab species in the Canary Islands, and investigates their potential links to nearby wastewater discharges. A total of 63 crabs were sampled from four beaches in Gran Canaria in 2021, and their stomach contents were analyzed through alkaline digestion, filtration, and micro-Fourier transform infrared spectroscopy (micro-FTIR). Microplastics were detected in 52% of individuals; the particles averaged 0.7 ± 0.5 mm in length, with an average of 1.73 ± 1.02 particles per crab. Fibers constituted 89% of the microplastics, with blue and black being the predominant colors. Rayon, commonly used in textiles, was the most frequently identified polymer (52%), highlighting the role of wastewater from laundry processes as a significant pollution source. Beaches close to unauthorized wastewater discharges, such as Anfi del Mar (<i>n</i> = 3) and El Puertillo (<i>n</i> = 32), showed the highest contamination levels, with a frequency of occurrence (FO) of microplastic particles of 67% and 58%, respectively. Playa de Las Nieves was the one with the lowest contamination level (<i>n</i> = 22), with a frequency of occurrence of microplastic particles of 41%. This is the first study to document microplastic ingestion in <i>C. ruber</i>, raising concerns about its ecological presence and the potential bioaccumulation of contaminants in marine ecosystems. Further research is essential to understand the long-term consequences of microplastic exposure on invasive species and their possible roles in pollutant transfer through food webs.

Majkić Mira, Spasojević Jovan, Nikolić Sandra et al.

Heat stress has a significant impact on the health and productivity of dairy cows, making early and accurate detection essential for effective welfare management. The aim of this study was to determine cut-off values of body surface temperature across different anatomical regions, measured by infrared thermography (IRT), to distinguish cows under heat stress from those in thermoneutral conditions. The research was conducted on a Holstein-Friesian farm in the Vojvodina region, with 200 total measurements collected during spring and summer. The identified cut-off values were as follows: 36.06 °C for the eye, 32.2 °C for the ear, 33.6 °C for the nose, 37.3 °C for the forehead, 35.8 °C for the whole head, 35.1 °C for the abdomen, 36.6 °C for the udder, 32.3 °C for the front limb, 33.5 °C for the hind limb, and 35.95 °C for the whole body. All values demonstrated satisfactory to high discriminative power (AUC = 0.71-0.95) for identifying cows under heat stress. These thresholds enable early identification of thermal load and timely interventions. Although body surface temperature is a sensitive and non-invasive indicator, its application requires contextual interpretation and integration with other physiological parameters. The results support the development of automated systems for continuous monitoring and prevention of heat stress, contributing to more sustainable dairy farming practices under changing climatic conditions.

Alexander Weinberg, Franziska Witte, Dana Carina Schubert et al.

Anthropogenic climate change is primarily caused by CO2 and CH4 emissions, with a significant portion originating from agriculture and livestock. Reducing methane emissions in ruminant husbandry has been a longstanding goal. Therefore, in this study, we aimed to influence the fermentation processes in the artificial rumen model (rumen simulation technique, RUSITEC) using five different carbons—one activated carbon (AC) and four biochars (BCs)—and one control without supplement. The carbons were included at 2% of dry matter (DM) of the basal diet, which corresponded to 0.3 g DM of the assigned additive. The treatments were conducted on 12 fermenters with two replications (n = 4/treatment) in a randomized block design. The experimental period consisted of a 7-day adaptation phase and an 8-day data and sample collection phase. Parameters included gas volume, gas composition, disappearance rates, volatile fatty acid (VFA) production, and nutrient digestion. Except for biochar (BC) 3, carbons showed no impact on gas parameters, while BC 3 decreased CO2 production (p = 0.0453), gas volume (p = 0.0255), and the ratio of CO2 (p = 0.0304), CH4 (p = 0.0304), and gas volume (p = 0.0304) to disappeared organic matter (dOM). BC 3 also showed a tendency to decrease in methane production (p = 0.0878). The effects on produced VFA were only found for BC 3, which reduced the daily production of total VFA (p = 0.0226), acetic acid (p = 0.0248), propionic acid (p = 0.0166), i-butyric acid (p = 0.0366), and the ratio of VFA to dry matter loss (p = 0.0172) and to dOM (p = 0.0304), while pH (p = 0.0309) was higher compared to the control. Only BC 3 had decreasing effects on disappearance rates (p = 0.0304). Although BC 3 reduces greenhouse gas emissions, it does so at the expense of fermentation, as indicated by its decreasing impact on digestion rate, VFA production, and the resulting increase in pH. In conclusion, biochar has the potential to affect rumen fermentation in vitro. However, general statements regarding the effects of biochars on fermentation cannot be derived from this experiment; each biochar source needs to be evaluated individually.

Sydney Anuyah, Mallika K Singh, Hope Nyavor

The integration of artificial intelligence [AI] into clinical trials has revolutionized the process of drug development and personalized medicine. Among these advancements, deep learning and predictive modelling have emerged as transformative tools for optimizing clinical trial design, patient recruitment, and real-time monitoring. This study explores the application of deep learning techniques, such as convolutional neural networks [CNNs] and transformerbased models, to stratify patients, forecast adverse events, and personalize treatment plans. Furthermore, predictive modelling approaches, including survival analysis and time-series forecasting, are employed to predict trial outcomes, enhancing efficiency and reducing trial failure rates. To address challenges in analysing unstructured clinical data, such as patient notes and trial protocols, natural language processing [NLP] techniques are utilized for extracting actionable insights. A custom dataset comprising structured patient demographics, genomic data, and unstructured text is curated for training and validating these models. Key metrics, including precision, recall, and F1 scores, are used to evaluate model performance, while trade-offs between accuracy and computational efficiency are examined to identify the optimal model for clinical deployment. This research underscores the potential of AI-driven methods to streamline clinical trial workflows, improve patient-centric outcomes, and reduce costs associated with trial inefficiencies. The findings provide a robust framework for integrating predictive analytics into precision medicine, paving the way for more adaptive and efficient clinical trials. By bridging the gap between technological innovation and real-world applications, this study contributes to advancing the role of AI in healthcare, particularly in fostering personalized care and improving overall trial success rates.

Peng Xu, Hongjin Wu, Jinle Wang et al.

This paper details a technical plan for building a clinical case database for Traditional Chinese Medicine (TCM) using web scraping. Leveraging multiple platforms, including 360doc, we gathered over 5,000 TCM clinical cases, performed data cleaning, and structured the dataset with crucial fields such as patient details, pathogenesis, syndromes, and annotations. Using the $Baidu\_ERNIE\_Speed\_128K$ API, we removed redundant information and generated the final answers through the $DeepSeekv2$ API, outputting results in standard JSON format. We optimized data recall with RAG and rerank techniques during retrieval and developed a hybrid matching scheme. By combining two-stage retrieval method with keyword matching via Jieba, we significantly enhanced the accuracy of model outputs.

Pedro Zuidberg Dos Martires, Vincent Derkinderen, Luc De Raedt et al.

Recent developments in AI have reinvigorated pursuits to advance the (life) sciences using AI techniques, thereby creating a renewed opportunity to bridge different fields and find synergies. Headlines for AI and the life sciences have been dominated by data-driven techniques, for instance, to solve protein folding with next to no expert knowledge. In contrast to this, we argue for the necessity of a formal representation of expert knowledge - either to develop explicit scientific theories or to compensate for the lack of data. Specifically, we argue that the fields of knowledge representation (KR) and systems biology (SysBio) exhibit important overlaps that have been largely ignored so far. This, in turn, means that relevant scientific questions are ready to be answered using the right domain knowledge (SysBio), encoded in the right way (SysBio/KR), and by combining it with modern automated reasoning tools (KR). Hence, the formal representation of domain knowledge is a natural meeting place for SysBio and KR. On the one hand, we argue that such an interdisciplinary approach will advance the field SysBio by exposing it to industrial-grade reasoning tools and thereby allowing novel scientific questions to be tackled. On the other hand, we see ample opportunities to move the state-of-the-art in KR by tailoring KR methods to the field of SysBio, which comes with challenging problem characteristics, e.g. scale, partial knowledge, noise, or sub-symbolic data. We stipulate that this proposed interdisciplinary research is necessary to attain a prominent long-term goal in the health sciences: precision medicine.

Yixuan Wu, Kaiyuan Hu, Danny Z. Chen et al.

With the rapid advance of computer graphics and artificial intelligence technologies, the ways we interact with the world have undergone a transformative shift. Virtual Reality (VR) technology, aided by artificial intelligence (AI), has emerged as a dominant interaction media in multiple application areas, thanks to its advantage of providing users with immersive experiences. Among those applications, medicine is considered one of the most promising areas. In this paper, we present a comprehensive examination of the burgeoning field of AI-enhanced VR applications in medical care and services. By introducing a systematic taxonomy, we meticulously classify the pertinent techniques and applications into three well-defined categories based on different phases of medical diagnosis and treatment: Visualization Enhancement, VR-related Medical Data Processing, and VR-assisted Intervention. This categorization enables a structured exploration of the diverse roles that AI-powered VR plays in the medical domain, providing a framework for a more comprehensive understanding and evaluation of these technologies. To our best knowledge, this is the first systematic survey of AI-powered VR systems in medical settings, laying a foundation for future research in this interdisciplinary domain.

Tongyue Shi, Jun Ma, Zihan Yu et al.

With the rapid development of artificial intelligence (AI), large language models (LLMs) have shown strong capabilities in natural language understanding, reasoning, and generation, attracting amounts of research interest in applying LLMs to health and medicine. Critical care medicine (CCM) provides diagnosis and treatment for critically ill patients who often require intensive monitoring and interventions in intensive care units (ICUs). Can LLMs be applied to CCM? Are LLMs just like stochastic parrots or ICU experts in assisting clinical decision-making? This scoping review aims to provide a panoramic portrait of the application of LLMs in CCM. Literature in seven databases, including PubMed, Embase, Scopus, Web of Science, CINAHL, IEEE Xplore, and ACM Digital Library, were searched from January 1, 2019, to June 10, 2024. Peer-reviewed journal and conference articles that discussed the application of LLMs in critical care settings were included. From an initial 619 articles, 24 were selected for final review. This review grouped applications of LLMs in CCM into three categories: clinical decision support, medical documentation and reporting, and medical education and doctor-patient communication. LLMs have advantages in handling unstructured data and do not require manual feature engineering. Meanwhile, applying LLMs to CCM faces challenges, including hallucinations, poor interpretability, bias and alignment challenges, and privacy and ethics issues. Future research should enhance model reliability and interpretability, integrate up-to-date medical knowledge, and strengthen privacy and ethical guidelines. As LLMs evolve, they could become key tools in CCM to help improve patient outcomes and optimize healthcare delivery. This study is the first review of LLMs in CCM, aiding researchers, clinicians, and policymakers to understand the current status and future potentials of LLMs in CCM.

Mireia Sueca-Comes, Elena Cristina Rusu, Jennifer C. Ashworth et al.

Kaitlyn M. Sarlo Davila, Rahul K. Nelli, Kruttika S. Phadke et al.

ABSTRACTThe potential infectivity of severe acute respiratory syndrome associated coronavirus-2 (SARS-CoV-2) in animals raises a public health and economic concern, particularly the high susceptibility of white-tailed deer (WTD) to SARS-CoV-2. The disparity in the disease outcome between humans and WTD is very intriguing, as the latter are often asymptomatic, subclinical carriers of SARS-CoV-2. To date, no studies have evaluated the innate immune factors responsible for the contrasting SARS-CoV-2-associated disease outcomes in these mammalian species. A comparative transcriptomic analysis in primary respiratory epithelial cells of human (HRECs) and WTD (Deer-RECs) infected with the SARS-CoV-2 WA1/2020 strain was assessed throughout 48 h post inoculation (hpi). Both HRECs and Deer-RECs were susceptible to virus infection, with significantly (P < 0.001) lower virus replication in Deer-RECs. The number of differentially expressed genes (DEG) gradually increased in Deer-RECs but decreased in HRECs throughout the infection. The ingenuity pathway analysis of DEGs further identified that genes commonly altered during SARS-CoV-2 infection mainly belong to cytokine and chemokine response pathways mediated via interleukin-17 (IL-17) and nuclear factor-κB (NF-κB) signaling pathways. Inhibition of the NF-κB signaling in the Deer-RECs pathway was predicted as early as 6 hpi. The findings from this study could explain the lack of clinical signs reported in WTD in response to SARS-CoV-2 infection as opposed to the severe clinical outcomes reported in humans.IMPORTANCEThis study demonstrated that human and white-tailed deer primary respiratory epithelial cells are susceptible to the SARS-CoV-2 WA1/2020 strain infection. However, the comparative transcriptomic analysis revealed that deer cells could limit viral replication without causing hypercytokinemia by downregulating IL-17 and NF-κB signaling pathways. Identifying differentially expressed genes in human and deer cells that modulate key innate immunity pathways during the early infection will lead to developing targeted therapies toward preventing or mitigating the “cytokine storm” often associated with severe cases of coronavirus disease 19 (COVID-19). Moreover, results from this study will aid in identifying novel prognostic biomarkers in predicting SARS-CoV-2 adaption and transmission in deer and associated cervids.