Результаты поиска

The use of non-invasive brain stimulation techniques to facilitate recovery from post-stroke aphasia.

Aphasia is a common symptom after left hemispheric stroke. Neuroimaging techniques over the last 10-15 years have described two general trends: Patients with small left hemisphere strokes tend to recruit perilesional areas, while patients with large left hemisphere lesions recruit mainly homotopic regions in the right hemisphere. Non-invasive brain stimulation techniques such as transcranial magnetic stimulation (TMS) and transcranial direct current stimulation (tDCS) have been employed to facilitate recovery by stimulating lesional and contralesional regions. The majority of these brain stimu

Imaging genetics of FOXP2 in dyslexia.

Dyslexia is a developmental disorder characterised by extensive difficulties in the acquisition of reading or spelling. Genetic influence is estimated at 50-70%. However, the link between genetic variants and phenotypic deficits is largely unknown. Our aim was to investigate a role of genetic variants of FOXP2, a prominent speech and language gene, in dyslexia using imaging genetics. This technique combines functional magnetic resonance imaging (fMRI) and genetics to investigate relevance of genetic variants on brain activation. To our knowledge, this represents the first usage of fMRI-based i

Sentence production in students with dyslexia.

BACKGROUND: While spoken language deficits have been identified in children with developmental dyslexia, microanalysis of sentence production proficiency in these children is a largely unexplored area. AIMS: The current study examines proficiency of syntactic production in children and young adults with dyslexia and typically developing age-matched controls on a constrained sentence production task targeting two advanced argument structures, theme-experiencer verbs and irregular past participles. METHODS & PROCEDURES: Participants aged between 8 and 22 years produced sentences that included

Association of Autosomal Dominant Polycystic Kidney Disease With Incident Aortic Dissection or Aneurysm.

RATIONALE & OBJECTIVE: Autosomal dominant polycystic kidney disease (ADPKD) is characterized by a broad range of extrarenal complications, yet epidemiologic data on its association with aortic dissection (AD) or aortic aneurysm (AA) remain limited. In the present study, we assessed whether ADPKD is associated with an increased risk of developing these aortic conditions. STUDY DESIGN: Observational cohort study. SETTING & PARTICIPANTS: 2,568,283 individuals without a history of AD or AA, enrolled between April 2014 and August 2023 in a nationwide Japanese epidemiological database provided by

Routine physics work efficacy and efficiency improvement through a shared-duty physicist-of-the-day model in a multi-hospital radiation oncology network.

BACKGROUND: Large multi-hospital radiation oncology networks often rely on site-exclusive physicist coverage models that can lead to imbalanced workload distribution, inconsistent task execution, communication fragmentation, and vulnerability to delayed or missed quality checks. Increasing clinical complexity and distributed staffing models necessitate operational strategies that improve efficiency, standardization, and safety across geographically separated sites. PURPOSE: To describe the implementation of a shared-duty physicist-of-the-day (POD) model supported by a real-time operational da

ChatGPT-Assisted Glaucoma Diagnosis: A Health-Equitable Multi-Ancestry Analysis Using Visual Field and Optical Coherence Tomography Data.

PURPOSE: Early glaucoma detection is challenging due to variable ocular anatomy, non-glaucomatous optic neuropathy impacting optical coherence tomography (OCT) results, and the subjective nature of visual field (VF) tests. Multimodal large language models may overcome these challenges to provide equitable and accurate screening diagnoses across ancestries and glaucoma genetic predispositions. We evaluated ChatGPT o1 Pro's accuracy in identifying glaucoma using circumpapillary retinal nerve fiber layer (RNFL) OCT and VF data, and its consistency across ancestries and glaucoma polygenic risk sco…

Может ChatGPT4-vision Идентификация радиологического развития множественного склероза на МРТ мозга?

Крупноязычная модель ChATGP теперь может принимать входные изображения GPT4-vision (GPT4V) версия. Цель заключалась в том, чтобы сравнить показатели работы GPT4V с подготовленными U-Net и ViT моделями трансформатора зрения (ViT) для идентификации развития множественных склерозов (MS) на магнитных резонансных изображениях (MRI). МЕТОДЫ: В качестве вклада в ChATGPT4V были представлены совместно зарегистрированные изображения MR с и без прогрессирования. zero- Эксперимент по выявлению радиологической прогрессии. Его показатели были сопоставлены с предварительно подготовленными моделями U-Net и VI

Совпадение в полном тексте источника
… Large language models (LLMs) such as ChatGPT are also based on transformer architecture and have shown remarkable breakthrough achievements [ 8 , 9 ]. …

Design and Evaluation of a Source-Grounded Medical LLM for Clinical Decision Support and Patient Care in Trustworthy Diagnostic Systems.

Background/Objectives: Large language models (LLMs) are increasingly explored for clinical decision support and digital health applications. However, reliable diagnostic assistance remains challenging for low-resource medical languages such as Turkish due to limited source grounding, transparency, clinical safety, and localized medical knowledge. This study presents TurkishMedLLM, a source-grounded and safety-aware Turkish medical LLM designed for clinician-supervised diagnostic decision support, symptom interpretation, and patient care. Methods: The methodology integrates multi-source Turkish…

Artificial Intelligence-enhanced cardiac MRI reporting: expert validation and patient-centered outcomes.

As patients increasingly access their own electronic health records, the dense technical language of cardiac magnetic resonance (CMR) reports has become a barrier both to patient comprehension and to decision-making by non-imaging physicians. We evaluated whether ChatGPT-4o can enhance the accessibility of CMR reports and generate clinical recommendations, and we quantified the accuracy, safety, and patient reception of these outputs. We prospectively enrolled 75 consecutive outpatients undergoing CMR at two Italian tertiary centres. Each physician-dictated report was processed with ChatGPT-4o

Navigating Child Oral Health in Western Australia: A Caregiver's Perspective.

BACKGROUND: Early childhood caries (ECC) is the most common chronic health condition among Australian preschool-aged children. Untreated, ECC can affect children's physical and emotional health and future social opportunities. ECC is largely preventable through primary caregivers' correct understanding of oral health promoting diets, oral hygiene practices and dental service engagement. The study aim is to explore Western Australian (WA) primary caregivers' child oral health knowledge, experience and practices. The Fisher-Owens socioecological model of child oral health was applied across the

Sex Education in the Age of Artificial Intelligence: A Qualitative Analysis of ChatGPT-3.5 Responses to Adolescents' Questions on Romantic Relationships and Sexuality.

Large language model chatbots, such as ChatGPT, have garnered increasing attention in the field of education, due to its versatility, processing speed, and widespread accessibility. However, its application to sexual education remains understudied, highlighting the need for more research into its potential to support informed decision-making among youth. The current study aimed to document ChatGPT-3.5 responses to adolescents' questions about romantic relationships and sexuality, using a more-than-human netnography approach. To obtain these responses, 393 anonymized emails written in French an

Agentic Automation of BT-RADS Scoring Using an End-to-End System for Standardized Glioma Follow-up Assessment.

The Brain Tumor Reporting and Data System (BT-RADS) standardizes posttreatment MRI response assessment in patients with diffuse gliomas but requires complex integration of imaging trends, medication effects, and radiation timing. An end-to-end multiagent large language model and convolutional neural network system for automated BTRADS classification was developed and evaluated. Five hundred nine consecutive posttreatment glioma MRI examinations (March 2017-July 2021) from a single center were retrospectively evaluated. An extractor agent identified clinical variables from notes using gpt-oss (

Skill-guided agentic reasoning enables longitudinal synthesis of myeloma records at expert-level concordance.

Patients with multiple myeloma accumulate hundreds of clinical documents over years of sequential therapy, and every treatment decision depends on synthesis across that history. Whether large language model-based systems can match expert agreement on this task, and where they fail, has not been established. On longitudinal records of 811 patients treated over 25 years (44,962 documents and 1,334,677 laboratory values), an agentic reasoning system guided by an indexed clinical skill library was compared against single-pass retrieval-augmented generation (RAG), iterative RAG, iterative RAG augme

PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views.

Single-view 3D shape retrieval is a fundamental yet challenging task that is increasingly important with the growth of available 3D data. Existing approaches largely fall into two categories: those using contrastive learning to map point cloud features into existing vision-language spaces and those that learn a common embedding space for 2D images and 3D shapes. However, these feed-forward, holistic alignments are often difficult to interpret, which in turn limits their robustness and generalization to real-world applications. To address this problem, we propose Pose-Aware 3D Shape Retrieval (

Semantic Scene Graphs for Creating a Localization-Ready Internet of Things.

Controlling devices connected to the Internet of Things often requires juggling multiple smartphone apps or physical remote controls, creating a fragmented user experience. Augmented Reality (AR) can afford superior control by automatically presenting virtual user interfaces that are spatially aligned with networked devices. However, before such user interfaces can be delivered, physical devices must be localized in the environment. This paper introduces LORIOT (LOcalization-Ready Internet Of Things), a novel end-to-end system that uses a semantic scene graph and a large language model to map

Disrupting integrator complex subunit INTS6 causes neurodevelopmental disorders and impairs neurogenesis and synapse development.

The Integrator complex plays essential roles in RNA polymerase II (RNAPII) transcription termination and RNA processing. Here, we identify INTS6, a subunit of the Integrator complex, as a novel gene associated with neurodevelopmental disorders (NDDs). Through analysis of large NDD cohorts and international collaborations, we identified 23 families harboring monoallelic likely gene-disruptive or de novo missense variants in INTS6. Phenotypic characterization revealed shared features, including language and motor delays, autism, intellectual disability, and sleep disturbances. Using a nervous-sy

Unveiling the cognitive burden: The impact of stigma on distorted thinking among individuals living with hepatitis B.

Hepatitis B (HBV) is a prevalent chronic illness affecting approximately 254 million individuals worldwide, with China accounting for nearly one-third of cases. Despite its widespread impact, stigma associated with HBV significantly hinders access to testing, diagnosis, and treatment. This study investigates the relationship between HBV stigma and cognitive distortions among individuals living with HBV by analyzing 35,697 posts from Yiyou Forum, China's largest HBV online community. Utilizing a large language model (LLM) for stigma classification, posts were categorized into stigma-related (S-

Creating accessible browser-based interactive content for teaching physiology and pharmacology: options for nonprogrammers.

Although interactive software has long been employed to complement traditional lecture and laboratory classes, instructors have typically been limited to premade programs produced by others with significant programming experience. Furthermore, many existing programs have limited platform cross-compatibility, with few compatible with the most ubiquitous and accessible device in a typical classroom, the mobile phone. In addition to advances in large language model-assisted programming, there has been a boom in the popularity of HTML5/JavaScript-based video game development software targeted towa

Food allergies in older people: Protocol for a systematic review and meta-analysis.

Background: Although the global prevalence of food allergies has been reported as increasing, its study is still largely confined to children and young adults. Nevertheless, several age-related factors (e.g., gastrointestinal changes, inflammation, and immunosenescence), responsible for the so-called 'anorexia of aging', may potentially mask, mediate, and/or enhance food allergies symptoms in older people. Although still neglected, the topic is critical for older persons who might be exposed to the risk of nutritional deficiencies and undernutrition if the primary and safest strategy for the f

Analysis of Research Trends in Cleft Lip and Palate: A Topic Modeling Study.

ObjectiveThe objective of this study was to systematically analyze the cleft lip and/or palate (CL/P) literature published between 2000 and 2025 to identify dominant research themes, temporal trends, and potential gaps by applying a natural language processing-based topic modeling approach.DesignWe analyzed articles retrieved from the Scopus database and identified thematic clusters using the BERTopic algorithm, which integrates BERT embeddings, Uniform Manifold Approximation and Projection dimensionality reduction, and Hierarchical Density-Based Spatial Clustering of Applications with Noise c