Результаты поиска

LLM-Based Unknown Function Automated Modeling in Sensor-Driven Systems for Multi-Language Software Security Verification.

The rapid expansion of the Internet of Things (IoT) has made software security and reliability a critical concern. With multi-language programs running on edge computing, embedded systems, and sensors, each connected device represents a potential attack vector, threatening data integrity and privacy. Symbolic execution is a key technique for automated vulnerability detection. However, unknown function interfaces, such as sensor interactions, limit traditional concrete or concolic execution due to uncertain function returns and missing symbolic expressions. Compared with system simulation, the …

Comprehensive intervention combining group and personalized language therapy in primary progressive aphasia: Quantitative and qualitative findings.

INTRODUCTION: Increasingly, studies are demonstrating language and communication improvement after behavioral interventions for primary progressive aphasia (PPA), and the caregiver perspective has been highlighted as critically important to determining treatment success in this population. This is an exploratory study investigating a comprehensive, person-centered intervention promoting everyday communication, functional independence, and quality of life for people with PPA (PwPPA) and their caregivers. METHODS: Four intervention programs were run separately in 6 to 8 week blocks with a total…

Embedding Social-Emotional Learning in Elementary School-Based Speech-Language Therapy: A Pilot Randomized Controlled Trial.

PURPOSE: Many students with communication disorders have unique social-emotional needs, yet school speech-language pathologists (SLPs) are not typically trained in how to address those needs. We developed a new training (STIRS [SLP Training to Increase Resilience in Students]) to equip elementary school SLPs to embed social-emotional learning (SEL) practices within their routine speech-language sessions with K-3 students with communication disorders. The primary objective of this pilot trial was to evaluate the preliminary effects and feasibility of STIRS. METHOD: This was a single-blind, par…

Learning from caregivers: Insights into pediatric speech and language services delivered via telepractice during COVID-19.

This article describes the development and administration of the Caregiver Insights of Pediatric Speech and Language Services Delivered via Telepractice During COVID-19 survey. Caregivers of children who began receiving speech and/or language services delivered via telepractice during COVID-19 were recruited to participate in this study. Participants were invited to share their impressions of telepractice during COVID-19 and why they chose to continue or discontinue this service delivery model when a return to in-person therapy became possible. This survey was developed using procedures outlin…

Automated sepsis prediction from unstructured electronic health records using natural language processing: a retrospective cohort study.

OBJECTIVE: Artificial intelligence (AI) holds promise for predicting sepsis. However, challenges remain in integrating AI, natural language processing (NLP) and free text data to enhance sepsis diagnosis at emergency department (ED) triage. This study aimed to evaluate the effectiveness of AI in improving sepsis diagnosis. METHODS: This retrospective cohort study analysed data from 134 266 patients admitted to the ED and subsequently hospitalised between 1 January 2016 and 31 December 2021. The data set comprised 10 variables and free-text triage comments, which underwent tokenisation and pro…

Cognitive-Linguistic Profiles Underlying Reading Difficulties Within the Unique Characteristics of Hebrew Language and Writing System.

While the multiple cognitive deficits model of reading difficulties (RD) is widely supported, different cognitive-linguistic deficits may manifest differently depending on language and writing system characteristics. This study examined cognitive-linguistic profiles underlying RD in Hebrew, characterised by rich Semitic morphology and two writing versions differing in orthographic consistency-a transparent-pointed version and a deep-unpointed version. A two-step cluster analysis grouped 96 s graders and 81 fourth graders based on their phonological awareness (PA), rapid naming (RAN), orthograp…

RETRACTED ARTICLE: Multimodal deep learning methods for speech and language rehabilitation: a cross-sectional observational study.

We, the Editor-in-Chief and Publisher of Disability and Rehabilitation: Assistive Technology, have retracted the following articles, which w … oi.org/10.1080/17483107.2025.2555541Cen, X. (2025). Multimodal deep learning methods for speech and language rehabilitation: a cross-sectional observational study. Disability and Rehabilitation: Assistive Technology, 1-13. https://doi.org/10.1080/17483107.2025.2551708Wang, Y., Li, H., Du, Y., Zhang, P., Shi, S., Ma, Y., & Wang, S. (2025). The relationship …

Enhancing Diagnostic Precision: Utilising a Large Language Model to Extract U Scores from Thyroid Sonography Reports.

This study evaluates the performance of ChatGPT-4, a Large Language Model (LLM), in automatically extracting U scores from free-text thyroid ultrasound reports collected from University Hospitals Birmingham (UHB), UK, between 2014 and 2024. The LLM was provided with guidelines on the U classification system and extracted U scores independently from 14,248 de-identified reports, without access to human-assigned scores. The LLM-extracted scores were compared to initial clinician-assigned and refined U scores provided by expert reviewers. The LLM achieved 97.7% agreement with refined human U scor…

Grounding DINO-US-SAM: Text-Prompted Multiorgan Segmentation in Ultrasound With LoRA-Tuned Vision-Language Models.

Accurate and generalizable object segmentation in ultrasound imaging remains a significant challenge due to anatomical variability, diverse imaging protocols, and limited annotated data. In this study, we propose a prompt-driven vision-language model (VLM) that integrates grounding DINO with SAM2 to enable object segmentation across multiple ultrasound organs. A total of 18 public ultrasound datasets, encompassing the breast, thyroid, liver, prostate, kidney, and paraspinal muscle, were utilized. These datasets were divided into 15 for fine-tuning and validation of grounding DINO using low-ran…

French language validation of the USS-PROM questionnaire assessing clinical outcomes and patient satisfaction after urethroplasty.

INTRODUCTION: Urethral stricture is a common condition in men that can significantly impair quality of life. The Urethral Stricture Surgery - Patient Reported Outcome Measure (USS-PROM) is a validated questionnaire that assesses urinary symptoms, quality of life, and patient's satisfaction following urethroplasty. However, no validated French version is currently available. METHODS: First, the questionnaire was translated into French by two bilingual native French speakers. It was then back-translated into English by two bilingual native English speakers to ensure that no distortion from the

Constructing Mediated Betting Discourse: A Typology of Responsible Gambling Language Identified Through ESPN's Sports Wagering Shows.

Media play an integral part in the presentation of information surrounding gambling, and thus, it is important to consider the sharing of such details to inform and educate about suggested participation in sports wagering. This study analyzes discourse during ESPN's dedicated sports betting program, ESPN Bet Live (formerly Daily Wager), to produce a typology of responsible mediated gambling language offered by on-air talent and through visual graphics to an active gambling audience. Analysis of 45 episodes aired during the men's and women's NCAA basketball tournaments between 2021 and 2024 rev…

Large Language Model-Supported Identification of Intellectual Disabilities in Clinical Free-Text Summaries: Mixed Methods Study.

BACKGROUND: Free-text clinical data are unstructured and narrative in nature, providing a rich source of patient information, but extracting research-quality clinical phenotypes from these data remains a challenge. Manually reviewing and extracting clinical phenotypes from free-text patient notes is a time-consuming process and not suitable for large-scale datasets. On the other hand, automatically extracting clinical phenotypes can be challenging because medical researchers lack gold-standard annotated references and other purpose-built resources, including software. Recent large language mod…

Automating the extraction of otology symptoms from clinic letters: a methodological study using natural language processing.

BACKGROUND: Most healthcare data is in an unstructured format that requires processing to make it usable for research. Generally, this is done manually, which is both time-consuming and poorly scalable. Natural language processing (NLP) using machine learning offers a method to automate data extraction. In this paper we describe the development of a set of NLP models to extract and contextualise otology symptoms from free text documents. METHODS: A dataset of 1,148 otology clinic letters written between 2009 - 2011, from a London NHS hospital, were manually annotated and used to train a hybri…

Оценка и анализ < < Биаса > > крупных языковых моделей для подготовки синтетических электронных медицинских записей: сравнительное исследование.

СПРАВОЧНАЯ ИНФОРМАЦИЯ: Синтетические электронные медицинские записи (ЭПЧ), генерируемые крупными языковыми моделями (ЛММ), открывают возможности для клинического обучения и типовой подготовки при одновременном решении проблем, связанных с неприкосновенностью частной жизни. Однако различия в показателях деятельности и демографические отклонения в этих моделях по-прежнему недостаточно изучены, что создает угрозу для справедливого медицинского обслуживания. ЦЕЛЬ: Данное исследование было направлено на систематическую оценку эффективности различных МУП в создании синтетических ЭПЧ и критическую оц

Совпадение в аннотации оригинала
BACKGROUND: Synthetic electronic health records (EHRs) generated by large language models (LLMs) offer potential for clinical education and model training while addressing privacy concerns. However, performance variations and demographic biases in these models remain underexplored, posing risks to equitable health care. OBJECTIVE: This study aimed to system…

Prediction of Alzheimer's disease progression within 6 years using speech: A novel approach leveraging language models.

INTRODUCTION: Identification of individuals with mild cognitive impairment (MCI) who are at risk of developing Alzheimer's disease (AD) is crucial for early intervention and selection of clinical trials. METHODS: We applied natural language processing techniques along with machine learning methods to develop a method for automated prediction of progression to AD within 6 years using speech. The study design was evaluated on the neuropsychological test interviews of n = 166 participants from the Framingham Heart Study, comprising 90 progressive MCI and 76 stable MCI cases. RESULTS: Our best m…

Ab-Amy 2.0: Predicting light chain amyloidogenic risk of therapeutic antibodies based on antibody language model.

Therapeutic antibodies have emerged as a promising treatment option for a wide range of diseases. However, the light chain of antibodies can … ssing the light chain amyloidogenic risk of therapeutic antibodies. By employing pretrained protein language models (PLMs) embeddings, AB-Amy 2.0 achieves higher accuracy in amyloidogenic risk prediction compared with traditional features offering a crucial tool for early-stage identification of antibodies with low aggregation propensity. The AB-Amy 2.0 wa …

Exploring the relationship between auditory late latency response and language age in children using cochlear implant.

AIM & OBJECTIVES: The study aimed to compare P1 latency and P1-N1 amplitude with receptive and expressive language ages in children using cochlear implant (CI) in one ear and a hearing aid (HA) in non-implanted ear. METHODS: The study included 30 children, consisting of 18 males and 12 females, aged between 48 and 96 months. The age at which the children received CI ranged from 42 to 69 months. A within-subject research design was utilized and participants were selected through purposive sampling. Auditory late latency responses (ALLR) were assessed using the Intelligent hearing system to mea…

Retrieval-Augmented Generation for Large Language Models in Radiology: Another Leap Forward in Board Examination Performance.

Supplemental material is available for this article. See also the editorial by Forghani in this issue.

Lingdan: enhancing encoding of traditional Chinese medicine knowledge for clinical reasoning tasks with large language models.

OBJECTIVE: The recent surge in large language models (LLMs) across various fields has yet to be fully realized in traditional Chinese medicine (TCM). This study aims to bridge this gap by developing a large language model tailored to TCM knowledge, enhancing its performance and accuracy in clinical reasoning tasks such as diagnosis, treatment, and prescription recommendations. MATERIALS AND METHODS: This study harnessed a wide array of TCM data resources, including TCM ancient books, textbooks, and clinical data, to create 3 key datasets: the TCM Pre-trained Dataset, the Traditional Chinese P…