Результаты поиска

The impact of ChatGPT on human data collection: A case study involving typicality norming data.

Tools like ChatGPT, which allow people to unlock the potential of large language models (LLMs), have taken the world by storm. ChatGPT's ability to produce written output of remarkable quality has inspired, or forced, academics to consider its consequences for both research and education. In particular, the question of what constitutes authorship, and how to evaluate (scientific) contributions has received a lot of attention. However, its impact on (online) human data collection has mostly flown under the radar. The current paper examines how ChatGPT can be (mis)used in the context of generati…

Requirements, Barriers and Tools for Participation in an Inclusive Educational Digital Environment.

An inclusive digital environment in education is considered a cornerstone for a modern society and particularly important for learners with … tools encompassed document accessibility, onboard Windows accessibility features, AI in the form of large language models (LLM) as assistive technology, and image recognition-based assistive technologies. Results, presented in this paper, indicate that especially learners with disabilities can benefit from participation in an inclusive digital environment.

Dyslexia and the failure to form a perceptual anchor.

In a large subgroup of dyslexic individuals (D-LDs), reading difficulties are part of a broader learning and language disability. Recent studies indicate that D-LDs perform poorly in many psychoacoustic tasks compared with individuals with normal reading ability. We found that D-LDs perform as well as normal readers in speech perception in noise and in a difficult tone comparison task. However, their performance did not improve when these same tasks were performed with a smaller stimulus set. In contrast to normal readers, they did not benefit from stimulus-specific repetitions, suggesting tha

Writing is thinking: toward a neuropsychological model of scientific writing as knowledge construction.

Scientific writing has historically been conceptualized as a communicative act-the registration of knowledge elaborated through independent … cognitive training in scientific education, academic impostor syndrome, and the cognitive impact of large language models. The MNIEC proposes a neuropsychological framework for a systematic research agenda on scientific writing as metacognitive knowledge construction.

RexDrug: Reliable Multi-Drug Combination Extraction Through Reasoning-Enhanced LLMs.

Automated Drug Combination Extraction (DCE) from large-scale biomedical literature is crucial for advancing precision medicine and pharmacological research. However, existing relation extraction methods primarily focus on binary interactions and struggle to model variable-length n-ary drug combinations, where complex compatibility logic and distributed evidence need to be considered. To address these limitations, we propose RexDrug, an end-to-end reasoning-enhanced relation extraction framework for n-ary drug combination extraction based on large language models. RexDrug adopts a two-stage tra…

Скринэтон 2.0:: Проведение совместного обследования с участием человека и АИ на основе данных о состоянии здоровья пациентов.

Систематические обзоры имеют важное значение для проведения исследований, основанных на фактических данных, однако традиционный процесс отбора требует много времени и его трудно масштабировать. Скрининг, проводимый исключительно для человека, может привести к непоследовательности, в то время как полностью автоматизированные подходы с использованием моделей Большого языка зачастую не имеют контекстуального суждения, необходимого для принятия сложных решений. Для решения этой проблемы мы внедряем методологию скрининга на основе толпы, которая сочетает человеческий опыт и адаптивное машинное обуч

Совпадение в аннотации оригинала
Systematic reviews are essential for evidence-based research, yet the traditional screening process is time-consuming and difficult to scale. Human-only screening can introduce inconsistency, while fully automated approaches employing Large Language Models often lack the contextual judgement required for complex decisions. To address this, we introduce a cro…

Artificial Intelligence and Musculoskeletal Surgical Applications.

Artificial intelligence (AI) has emerged as a transformative force in orthopedic surgery. Potentially encompassing pre-, intra-, and postoperative processes, it can process complex medical imaging, provide real-time surgical guidance, and analyze large datasets for outcome prediction and optimization. AI has shown improvements in surgical precision, efficiency, and patient outcomes across orthopedic subspecialties, and large language models and agentic AI systems are expanding AI utility beyond surgical applications into areas such as clinical documentation, patient education, and autonomous d…

Экспериментальная оценка диагностической точности " ЧатгПТ-3.5 " для множественных склерозов на основе отчетов по конкретным делам.

Ограниченность моделей искусственного интеллекта (АИ) для диагностики заболеваний с точки зрения безопасности пациентов по-прежнему недостаточно изучена, и необходимо решить такие потенциальные проблемы, как диагностические ошибки и правовые проблемы. Чтобы продемонстрировать ограничения МА, мы использовали ChatGPT-3.5, разработанный OpenAI, в качестве инструмента для медицинского диагноза, используя текстовые отчеты о многочисленных склерозах (MS), которые были выбраны в качестве прототипического заболевания. Мы проанализировали 98 докладов по рецензируемым делам, отобранных на основе свободн

Совпадение в аннотации оригинала
The limitation of artificial intelligence (AI) large language models to diagnose diseases from the perspective of patient safety remains underexplored and potential challenges, such as diagnostic errors and legal challenges, need to be addressed. To demonstrate the limitations of AI, we used ChatGPT-3.5 developed by OpenAI, as a tool for medical diagnosis us…

Graph-to-Graph Inverse Design of Surfactants under Multiobjective and Structural Constraints.

Rapid, sustainable redesign of large functional molecules requires efficient exploration of vast chemical spaces subject to multiple properties and constraints. Graph neural networks have shown strong performance in molecular property prediction, yet their use for inverse design remains relatively underexplored. Meanwhile, chemical language transformers capable of learning long-range relationships have emerged as a competing paradigm. To address this gap, we propose a novel motif-based graph-to-graph framework for the inverse design of surfactants, in which latent representations are optimized

EyeGraph: A Multi-granularity Medical Vision-Language Foundation Model with Knowledge Graph Reasoning for Ophthalmic Interpretation.

The exponential growth of large vision-language models (VLMs) has created significant opportunities for advancing multimodal artificial intelligence in specialized domains such as ophthalmology. However, progress in ophthalmic VLMs remains limited, primarily due to the lack of large-scale, high-quality image-text pairs. Moreover, existing VLMs frequently generate hallucinations, leading to uncertainty and unreliability that are unacceptable in clinical practice. To address the data scarcity issue, we introduce IT-Retinal, a dedicated ophthalmic Vision Question Answering (VQA) dataset that prov

iPheno: A Novel Dual-Aware Vision-Language Model for Multi-Task Fine-Scale Crop Phenotyping.

Crop phenotyping is crucial for advancing plant breeding, yet remains a significant challenge. Manual approaches are labor-intensive and do not scale to the analysis of large datasets, while computational methods like Vision-Language Models (VLMs) lack the adaptability for fine-scale spatial reasoning and diverse phenotyping scenarios. To bridge the gaps, we present iPheno, a fully open-source, domain-specialized multimodal VLM for fine-scale crop phenotyping. A key innovation of iPheno is its dual-aware architecture. First, a spatial-aware feature extractor samples mask regions into local K-N

AI for screening in healthcare: promise and challenges.

Artificial intelligence (AI) is reshaping population screening, yet the translation from laboratory performance to population benefit remains limited. This narrative review describes current uses of AI across major screening pathways. Prospective trials in mammography demonstrate non‑inferior cancer detection with large reductions in radiologist workload. In diabetic retinopathy, the first FDA‑authorized autonomous system extends specialist‑level screening into primary care and improves uptake. During colonoscopy, real‑time computer vision improves adenoma detection without increasing removal

Машинное обучение и глубокое обучение в клинической практике: расширение диагностики нейродегенеративных заболеваний с помощью мультимодальных маркеров.

Нейродегенеративные заболевания, включая болезнь Альцгеймера, болезнь Паркинсона, болезнь Хантингтона и множественный склероз, представляют собой серьезные глобальные проблемы в области здравоохранения из-за их прогрессивной и неизлечимой природы. Ранняя и точная диагностика имеет решающее значение для медленного развития заболеваний и оптимизации терапевтического вмешательства, однако традиционные диагностические подходы, такие, как нейроимация, биомаркерирование цереброспиновой жидкости и клиническая оценка зачастую являются неадекватными на продромальной стадии. Последние достижения в облас

Совпадение в аннотации оригинала
Neurodegenerative diseases, including Alzheimer's disease, Parkinson's disease, Huntington's disease, and multiple sclerosis, present major … inal data, federated and privacy-preserving learning, and the potential of explainable AI (XAI) and large language models (LLMs) in clinical decision support.

AVP-GPT2: Prompt-conditioned fine-tuning of a GPT-2 protein language model for antiviral peptide identification.

Antiviral peptides (AVPs) are promising therapeutic candidates as it can inhibit viral replication, interfere with host-virus interactions, and provide sequence-specific antiviral activity. However, experimental screening of large peptide libraries is time-consuming and costly, creating a need for computational tools that can prioritize promising candidates before laboratory validation. Here, we present AVP-GPT2, a practical protein language model workflow for antiviral peptide identification. In this study, peptide sequences were embedded within structured task-specific prompts and optimized

Artificial intelligence-driven risk prediction of polypharmacy in older adults: current advances, clinical applications, and future perspectives.

Due to the ageing of the population, multimorbidity and polypharmacy has significantly increased, causing medication safety to become a glob … with a focus on machine learning, deep learning, natural language processing, graph neural network, large language models, and longitudinal trajectory modelling. We highlight some of the major data sources, predictive algorithms, clinical decision support systems and real-world applications, stressing mostly on patient-centred medication management, nurse-led intervent …

Literature-derived, context-aware gene regulatory networks improve biological predictions and mathematical modeling.

MOTIVATION: Complex gene regulatory networks (GRNs) underlie most disease processes, and understanding disease-specific network structures and dynamics is crucial for developing effective treatments. Yet, most database- and literature-based analyses of GRNs often treat gene regulations as context-independent interactions, overlooking how GRNs can differ depending on the disease type, cell lineage, or experimental condition. RESULTS: In an attempt to improve on existing methods for leveraging knowledge present in the scientific literature, we developed a framework to assign quantitative, conte

A multi-agent multi-modal LLM with Monte Carlo tree search for interpretable plant disease classification.

In plant disease classification tasks, existing task specific models for plant disease classification typically achieve high accuracy by employing tailored network architectures. However, these models are unable to provide reasoning chains, which reduces interpretability and undermines trustworthiness in practical applications. In addition, although multimodal large language models (MLLMs) have made significant progress in smart agriculture, their disease classification accuracy lags behind that of task-specific models due to insufficient domain knowledge. While fine-tuning can enhance domain-…

Artificial Intelligence in Vitreoretinal Surgery: A Systematic Review of Current Applications and Future Directions.

INTRODUCTION: To examine the current landscape of artificial intelligence (AI) applications in vitreoretinal (VR) diseases and surgery, with … t detection and tracking, reporting precision above 90% in experimental or early clinical settings. Large language models showed moderate-to-high agreement with expert surgical planning (80-93%) and potential utility in education and workflow support; however, across domains, most studies were retrospective and single-center, with limited external validation. CONCLUSI …

Artificial intelligence in foot and ankle surgery: Current applications, limitations and future directions.

BACKGROUND: Artificial intelligence (AI) is increasingly studied in orthopedics for image interpretation, automated measurement, risk predic … r estimating Achilles tendon loading. Perioperative prediction models remain largely retrospective. Large language models may assist with patient information but are not sufficiently reliable for unsupervised diagnosis or triage. The proposed Foot and Ankle AI Assistant remains an unvalidated research concept. CONCLUSIONS: AI may support selected aspects of foot and a …

Evaluating Adherence to Canadian Radiology Guidelines for Incidental Hepatobiliary Findings Using RAG-Enabled LLMs.

Purpose: Large language models (LLMs) have the potential to support clinical decision-making but often lack training on the latest clinical guidelines. Retrieval-augmented generation (RAG) may enhance guideline adherence by dynamically integrating external information. This study evaluates the performance of two LLMs, GPT-4o and o1-mini, with and without RAG, in adhering to Canadian radiology guidelines for incidental hepatobiliary findings. Methods: A customized RAG architecture was developed to integrate guideline-based recommendations into LLM prompts. Clinical cases were curated and used t…