Результаты поиска

Towards scalable psychological first aid training: an autoethnographic exploration of the potential of large language models in simulation-based learning.

Background: Psychological First Aid (PFA) is a widely used approach to provide psychosocial support to individuals in the aftermath of a stressful event. PFA training requires a costly, structured approach, including repetitive simulation-based training with actors. The rapid emergence of large language models (LLMs) could provide easy access to PFA simulation training, enabling trainees to practice conversations repeatedly and flexibly, learn from mistakes, and build emotional resilience. In addition, this would allow for training in geographically isolated regions where PFA training may be m…

Evaluation of Large Language Models as Tools, Models, and Partners in Creative Thinking Research: A Selective Narrative Review with the GCA Framework.

Creativity research faces three persistent bottlenecks: divergent-thinking scoring is labour-intensive, cognitive models of creativity remain underspecified, and laboratory tasks fall short of real-world creative achievement. Large language models (LLMs) offer potential solutions, but the field lacks a structured framework for evaluating them. This selective narrative review (January 2018-June 2026) applies the generation-capability-assessment (GCA) framework, whose three axes are operationalised through descriptive criteria with provisional heuristic thresholds. On the generation axis, LLMs e…

The differential role of language and executive functions in the relation between socioeconomic status and theory of mind in preschool and school-aged children.

This study examined the role of language and executive functions (EFs) as potential mediators of the relation between family socioeconomic status (SES) and Theory of Mind (ToM) in preschool and school-aged children. A total of 375 children aged 3 to 7 years completed assessments of ToM (false beliefs task), language abilities (vocabulary, syntax, and novel word learning), and EFs (inhibition and cognitive flexibility). Family SES was measured based on parental education and occupational status. Structural equation modeling revealed that language mediated the SES-ToM association, whereas EFs di…

Performance evaluation of five large language models for assisting in the interpretation of urinalysis reports for kidney diseases: a real-world study.

OBJECTIVES: Large language models (LLMs) show promise for interpreting laboratory reports, yet real-world validation remains limited. This study evaluated five advanced LLMs in interpreting urinalysis reports for kidney diseases using real-world clinical data, providing empirical evidence for the utility of LLM-assisted result interpretation. METHODS: We retrospectively collected 120 urinalysis reports from patients with primary glomerular diseases and secondary nephropathies. The testing platforms included the Sysmex UF5000 and Mindray EU8600. Five LLMs (ChatGPT-5, Claude-4.5, Gemini-2.5, De…

The influence of lesion type and lesion location on the prediction of language laterality in patients with cerebral vascular malformations using functional MRI.

OBJECTIVE: Predicting language lateralization using functional MRI (fMRI) in patients with cerebral vascular malformations close to language areas is essential for treatment decision-making and patient outcomes. Functional MRI-based prediction is challenged because of potential remodeling processes and hemodynamic phenomena. However, there is a lack of possible factors influencing laterality prediction. The authors hypothesized that there might be an impact of lesion type and location on language lateralization. METHODS: This retrospective study included 24 patients with arteriovenous malform…

Reading ability in children with comorbid developmental dyslexia and developmental language disorder: a systematic review : Reading in Children with DD and DLD.

This systematic review aimed to investigate (a) the core characteristics of reading ability in children with comorbid Developmental Dyslexia (DD) and Developmental Language Disorder (DLD), (b) the shared and distinct features of reading performance among children with DD, DLD, and comorbid DD + DLD, and (c) the linguistic and cognitive factors associated with their reading outcomes. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020) guidelines, systematic searches were conducted in Web of Science, Scopus, and PubMed between January and May 2025, and …

A Co-Produced Health Literacy Programme for Pregnant Women Whose First Language Is Not English: A Qualitative Study of Women's Experiences.

INTRODUCTION: Health literacy, the ability to access, understand and use health information to make informed decisions, is a key determinant of maternal and infant health. In the United Kingdom, approximately one-third of the 600,000 babies born annually are to mothers born overseas, many of whom have limited English proficiency. This language barrier contributes significantly to health disparities. To address this, we co-produced a 6-week health literacy course for pregnant women with limited English proficiency in East London. Designed to empower participants, the course aimed to improve the…

Addressing Competence and Educational Gaps Among Speech and Language Pathologists in Cleft Palate Care: A Cross-Sectional Study in Flanders.

BACKGROUND: The field of speech and language pathology (SLP) expanded to a wide range of specialities, leading to a global trend to decrease the time spent on specific courses on children with cleft palate, with or without cleft lip (CP±L) in SLP education programmes. The lack of CP±L courses has resulted in a global shortage of well-trained SLPs to deliver high-quality services to this population. Therefore, alternative training formats are needed. AIM: This study aimed to assess the training needs of Flemish speech and language pathologists (SLPs) working with children with CP±L by examinin…

Comparative evaluation of the quality, reliability, and readability of five large language model responses to frequently asked questions on gestational hypertension.

OBJECTIVE: This study aims to clarify the impact of Large Language Models (LLMs) and health education content categories on generated text quality (patient education appropriateness and overall quality) and readability, providing empirical evidence for the standardized application of LLMs-assisted health communication. METHODS: Five mainstream models (Doubao, Deep Seek, Wenxin Yiyan, Gemini and GPT-5) were selected to generate 100 texts (20 per model, 20 per theme) across five health education categories: disease cognition dimension, etiology and risk factors dimension, diagnosis and examinat…

A Patient-centered Approach to Analyzing the Quality, Credibility, and Readability of Spanish-language Online Patient Educational Materials on Pediatric Scoliosis.

INTRODUCTION: Ethnic, racial, and socioeconomic disparities are well-documented in orthopaedics, including pediatric scoliosis. Spanish-speaking patients face compounding disparities in accessing linguistically and culturally concordant physician-patient interactions and patient resources. This study contributes to existing literature by providing an updated and extended analysis of the quality, credibility, and readability of online Spanish-language patient educational materials on pediatric scoliosis. METHODS: A search for the top 50 results of "escoliosis en los niños" (scoliosis in childr…

Performance evaluation of five major large language models in tuberculosis Q&A systems: A multidimensional assessment of readability, quality, and reliability.

BACKGROUND: Pulmonary tuberculosis (TB) is a chronic infectious disease that burdens patients and public health systems. Limited reach of traditional education and uneven online information may undermine patients' understanding, adherence, and trust. Large language models (LLMs) show promise for TB health education, but systematic evaluation is lacking. OBJECTIVE: To evaluate five large language models in pulmonary tuberculosis Q&A (Question and Answer) scenarios and examine the effects of different large language models and TB health education themes on response quality, readability, and rel…

Semantic Radical Consistency in Incidental Chinese Vocabulary Learning: A Comparison of Native Readers and Chinese as a Foreign Language (CFL) Learners.

Semantic radicals are meaning-bearing sublexical components of Chinese characters that have been shown to facilitate incidental vocabulary learning in L1 Chinese readers. However, it remains unclear whether this sublexical mechanism extends to learners of Chinese as a foreign language (CFL), and how semantic radicals shape the online processing and learning outcomes of novel words in both populations. The present study investigated the role of semantic radical consistency in incidental vocabulary learning among L1 readers and CFL learners. Eye movements were recorded while participants read se…

Eye Tracking in Visuoperceptual Diagnostic Tasks in Health Care: A Scoping Review and Thematic Synthesis With Implications for Speech-Language Pathology.

PURPOSE: Eye tracking provides objective measurement of visuoperceptual behavior during diagnostic interpretation. Although widely used in health care research, little is known about how speech-language pathologists (SLPs) visually engage with dynamic imaging. This scoping review mapped current research on clinicians' gaze behavior during visuoperceptual diagnostic tasks and synthesized methodological trends, outcome themes, and limitations to inform future speech-language pathology-focused eye-tracking research. METHOD: Following Preferred Reporting Items for Systematic Reviews and Meta-Anal…

агитационные рамки ИИ, связывающие языковые модели с электронными медицинскими записями, и график биомедицинских знаний для реальных доказательств.

Доступ к крупномасштабным клиническим и биомедицинским базам данных по-прежнему является серьезным препятствием для клинических и научных работников, требующим значительных вычислительных знаний. Агентские системы искусственного интеллекта, в которых крупные языковые модели (МПМ) организуют многоэтапное рассмотрение и выполнение запросов под интерактивным контролем человека, открывают возможности для демократизации доступа к данным и ускорения процесса получения доказательств. MethodsWe применяли Типовой контекстный протокол (МКП) для интеграции в рамках одного агентского рабочего процесса ста

Совпадение в аннотации оригинала
BackgroundAccessing large-scale clinical and biomedical databases remains a significant barrier for clinicians and researchers, requiring substantial computational expertise. Agentic artificial intelligence frameworks, in which large language models (LLMs) orchestrate multi-step reasoning and query execution under interactive human supervision, offer the pot…

Performance of Advanced Large Language Models in Caries Risk Assessment and Preventive Decision-Making: A Multidimensional Evaluation of Five Chatbots.

INTRODUCTION: Large language models (LLMs) have recently been integrated into dental practice to support clinical reasoning and preventive decision-making. This study compared the performance of 5 advanced chatbots - ChatGPT-5, Claude 4.5 Sonnet, Gemini 2.5 Pro, LLaMA 3.1, and Mistral 7B - in providing evidence-based responses for caries risk assessment and preventive management in pediatric cases. METHODS: Twenty-five validated, case-based questions were developed in accordance with internationally recognized pediatric and preventive dentistry guidelines. Responses were evaluated by 6 pediat…

Large Language Models as Inadvertent Models of Dementia with Lewy Bodies: How a Disorder of Reality Construction Illuminates AI Hallucination.

Recent work in computational psychiatry has explored artificial agents as designed models of mental and neurological disorders, typically by introducing pathological parameters. This paper advances an inverse claim: large language models (LLMs) already instantiate a structural configuration resembling dementia with Lewy bodies (DLB). We argue that the core disturbance in DLB lies in instability of mechanisms that stabilize experience as real and contextually grounded, while generative and cognitive capacities remain relatively preserved. Hallucinations and fluctuations are thus interpreted as …

Artificial Intelligence and Generative Models in Hepatology: From Large Language Models to Digital Pathology in Liver Disease Diagnosis and Treatment.

Artificial intelligence (AI), particularly foundation and generative models, is reshaping the practice of hepatology through enhanced knowledge synthesis, quantitative and reproducible analysis of multimodal data, and personalized clinical decision support. This narrative review examines the transition from task-specific discrimination AI to large language models (LLMs), multimodal foundation models, and agentic AI. We synthesize evidence from original and validation studies, clinical evaluations, and benchmark studies, as well as expert reviews and regulatory frameworks across metabolic dysfu…

Can Large Language Models Be a Viable Tool for Consensus Working Groups? Experience of the Ventral Rectopexy Expert Consensus Group.

BACKGROUND: The Ventral Rectopexy International Expert Panel recently published a consensus update on ventral rectopexy. The ability of large language models to synthesize the literature on ventral rectopexy without an explicit knowledge base was studied before the publication of the consensus. OBJECTIVE: To compare the responses and citations of different large language models on ventral rectopexy using the expert panel consensus as the reference standard. DESIGN: ChatGPT-4o, Gemini 1.5 Pro, and OpenEvidence were compared on content appropriateness (1 = inappropriate to 5 = appropriate), re…