Результаты поиска

Optimising large language models for clinical information extraction: a benchmarking study in the context of ulcerative colitis research.

OBJECTIVE: Closed-source large language models (LLMs) like generative pre-trained transformer 4o (GPT-4o) have shown promise for clinical information extraction but are potentially limited by cost, data security concerns and inflexibility. Open-source models are an attractive alternative with various adaptation strategies with no consensus on best practices. This study aims to rigorously identify optimal adaptation strategies for open-source models and evaluate their performance relative to closed-source alternatives. METHODS AND ANALYSIS: We studied three LLM adaptation strategies: chain-of-…

Gene therapy for children with X-linked myotubular myopathy: a plain language summary of publication for the ASPIRO study.

What is this summary about? This summary describes the results of a research study (clinical trial) called ASPIRO that was published in the Lancet Neurology in 2023. This study looked at an investigational gene therapy called resamirigene bilparvovec (also known as AT132) as a possible treatment for children with a disease called X-linked myotubular myopathy (abbreviated as XLMTM).

Empowering inclusive education: a multi-modal android application for accessible transliteration of Indian languages into Braille script.

OBJECTIVE: The primary objective of this application is to promote inclusivity in the educational environment by supporting special educators and students with visual disability in accessing, disseminating, and delivering educational resources that are accessible to all learners. This application specifically assists individuals with visual disabilities by transliterating Indian languages such as Bengali, Odia, Hindi, English, and Telugu into braille scripts, thereby enhancing access to educational content in native languages. METHODS: The Android application was developed using Android Studi…

Does learning a second or third language affect the adaptation of cognitive control in multilinguals? A longitudinal fMRI study.

UNLABELLED: Numerous studies in the bilingual literature have shown that cognitive control adapts to several factors related to second language (L2) learning. However, whether third language (L3) learning influences cognitive control remains underexplored. In this longitudinal study, we analyzed behavioral performance and functional magnetic resonance imaging (fMRI) data among Chinese-English bilinguals at resting-state and during a flanker task both prior to English (L2) or Japanese (L3) learning and one year later. During brain resting-states for these same learners, we conducted a correlati…

Speech and Language Therapy Weekend Service in Inpatient Rehabilitation: A Qualitative Study Exploring Perspectives of People With Stroke.

BACKGROUND: An allied health weekend service in subacute inpatient stroke rehabilitation can improve patient and organisational outcomes. However, there is insufficient evidence to justify the role of a speech and language therapy (SLT) weekend service in this setting. Exploring the perspectives of individuals who have received SLT services in inpatient stroke rehabilitation will assist with understanding the current role of SLT and the potential for SLT weekend services in inpatient stroke rehabilitation. AIMS: This study aimed to: (1) determine the aspects of an SLT inpatient rehabilitation…

Relative qualities of telerehabilitation compared to traditional in-person speech and language treatment for individuals with aphasia: A meta-analysis.

BACKGROUND: Stroke is a leading cause of disability and one of the primary causes of death worldwide. Stroke survivors often experience a range of symptoms, including impaired motor function, speech and language abnormalities, swallowing difficulties, cognitive deficits, visual disturbances, and sensory impairments. OBJECTIVES: This meta-analysis was conducted to assess and compare the relative effectiveness of telerehabilitation compared to traditional in-person speech and language therapy for individuals with aphasia. MATERIAL AND METHODS: A comprehensive literature search was conducted up…

АИ для научно обоснованной рекомендации в отношении лечения онкологии: ослепленная оценка крупных языковых моделей и агентских рабочих процессов.

Медицина, основанная на доказательствах, имеет решающее значение для принятия клинических решений, однако исследования свидетельствуют о том, что значительная часть решений о лечении не в полной мере учитывает последние данные. Большие языковые модели (ММЛ) говорят о том, что они способны устранить этот пробел, однако их надежность для медицинских рекомендаций остается неопределенной. five Рекомендации МЛМ в различных областях 50 клинические сценарии, связанные с множественным диагностированием миэломы, постановкой, лечением и управлением, с использованием унифицированного лимита улик по состо

Совпадение в аннотации оригинала
BackgroundEvidence-based medicine is crucial for clinical decision-making, yet studies suggest that a significant proportion of treatment decisions do not fully incorporate the latest evidence. Large Language Models (LLMs) show promise in bridging this gap, but their reliability for medical recommendations remains uncertain.MethodsWe conducted an evaluation …

Navigating the 2022 International Consensus and World Health Organization Classifications of Hematopathology: A Call for Unified Diagnostic Language.

CONTEXT.—: In 2022, 2 distinct guidelines for the diagnosis of myeloid neoplasms became available: the 5th edition of the World Health Organ … s could be a source of confusion for physicians and it highlights the need for a unified diagnostic language.

Towards Community-Based Evaluation of AI in Neurology: Development of a Headache Diagnosis Dataset for Large Language Models.

Diagnosing headache disorders remains a clinical challenge due to the heterogeneity of headache phenotypes and the absence of objective biomarkers. This study presents a curated dataset of 50 clinical headache case examples, comprising both real (n = 34) and synthetic (n = 16) cases, categorized across 20 diagnoses according to ICHD-3 criteria. The dataset enables the evaluation of large language models (LLMs) for diagnostic accuracy in headache medicine. Three GPT-based models were tested using different prompting strategies, with diagnostic performance assessed at both diagnosis and group le…

Development and validation of a natural language processing system to assess quality of physician communication in prostate cancer consultations.

BACKGROUND: AUA guidelines for shared decision making (SDM) in prostate cancer recommend discussion of five content areas in consultations: … sistent risk communication by physicians are barriers to informed SDM. We sought to develop natural language processing (NLP) models based on recorded consultations to provide key information to patients and audit quality of physician communication. METHODS: We used 50 consultation transcripts to train and validate NLP models to identify sentences related …

Cognitive, language and motor developmental patterns of extremely preterm children up to 2 years of age: a descriptive approach.

BACKGROUND: Advancements in technology and pharmacology over the past 15 years have increased the survival rates of extremely low gestationa … o 8 months of corrected age to 24-25 months of chronological age, focusing on cognitive, motor, and language development. METHODS: The study included 7 female and 10 male ELGA children with a mean GA of 26.0 weeks (SD = 1.2; range = 24-28) and mean BW of 875.8 grams (SD = 171.2; range = 560-1,150). The Bayley Scales of Infant and Toddler Development, Thir …

Telehealth Delivery of Speech-Language Pathology Services for Children with Cleft Palate and Velopharyngeal Dysfunction: A Systematic Review.

BACKGROUND/OBJECTIVES: This systematic review aimed to evaluate the effectiveness, caregiver satisfaction, and accessibility of telehealth-delivered speech-language pathology (SLP) services for children with cleft palate and/or velopharyngeal dysfunction (VPD). METHODS: Based on PRISMA 2020, we searched PubMed, CINAHL, Scopus, PsycINFO, and the Cochrane Library (2000-31 May 2025) for studies enrolling participants ≤ 18 years of age with cleft/VPD who received telehealth services (assessment, therapy, counseling/follow-up), with or without in-person comparators. Screening and data extraction w…

Deciphering the genetic basis of developmental language disorder in children without intellectual disability, autism or apraxia of speech.

BACKGROUND: Developmental language disorder (DLD) refers to children who present with language difficulties that are not due to a known biomedical condition or associated with autism spectrum disorder (ASD) or intellectual disability (ID). The clinical heterogeneity of language disorders, the frequent presence of comorbidities, and the inconsistent terminology used over the years have impeded both research and clinical practice. Identifying sub-groups of children (i.e. DLD cases without childhood apraxia of speech (CAS)) with language difficulties is essential for elucidating the underlying ge…

Utility of Large Language Models for Congenital Microtia Reconstruction Education: Comparison of the Performance of Claude, GPT, and Gemini.

BACKGROUND: Children with microtia and their parents require comprehensive information to make informed decisions about treatment options. OBJECTIVE: We evaluated the effectiveness of various large language models (LLMs) in providing preoperative education for congenital microtia reconstruction (CMR) by analyzing their responses to related inquiries. METHODS: Ten plastic surgeons developed 13 CMR-related preoperative education strategies and input 14 text commands into Claude-3-Opus, GPT-4-Turbo, and Gemini-1.5-Pro during an online session. Five experts evaluated these language model's respo…

ViTCAI: A Vision-Language Model for Automated Triage and Captioning of Postoperative Incision Images Submitted by Remote Patients.

Surgical site infections (SSIs) are common postoperative complications that increase patient morbidity, hospital stays, and healthcare costs. Early detection and precise documentation are critical for timely intervention and improved outcomes. While patients often submit images of their wounds through a patient portal for remote monitoring, manual review is challenging due to image variability, high volume, and subjectivity, underscoring the need for automated assessment tools. In this paper, we present Vision Transformer for CAptioning of Incision Images (ViTCAI), a vision-language model desi…

Delayed language access hampers but does not hinder visual statistical learning in deaf and hard of hearing children.

Statistical learning in deaf and hard of hearing (DHH) children is poorly understood and the impact of age of sign language acquisition has not been systematically investigated. In the present study, we examined visual statistical learning and transfer effects in early (age of sign language acquisition before the age of three years) and late (age of sign language acquisition after the age of three years) DHH child signers (aged 6-8 years) of German Sign Language, compared to age-matched hearing children. The children completed a visual artificial grammar learning task across three learning ses…