Результаты поиска

Speech translation for multilingual medical education leveraged by large language models.

The application of large language models (LLMs) to speech translation (ST) or, in general, to machine translation (MT) has recently provided excellent results, superseding conventional encoder-decoder MT systems in the general domain. However, this is not clearly the case when LLMs as MT systems are translating medical-related materials. In this respect, the provision of multilingual training materials for oncology professionals is a goal of the EU project Interact-Europe in which this work was framed. To this end, cross-language technology adapted to the oncology domain was developed, evaluat…

[Hippocrates and language models - Primum Non Nocere - First do no harm].

Hippocrates and language models - Primum Non Nocere - First do no harm.

Association Between Genetically Predicted Memory and Self-Reported Foreign Language Proficiency.

BACKGROUND: Foreign language proficiency is a complex trait that reflects an individual's ability to effectively understand and use a non-native language, shaped by both genetic and environmental factors. The aim of this study was to establish the relationship between genetically determined memory capacity and self-reported foreign language proficiency in 129 children (63 males, 66 females, age 14.2 ± 3.9) and 128 adults (90 males, 38 females, age 29.8 ± 8.2). METHODS: Seven single nucleotide polymorphisms (SNPs) previously linked with memory function were used in a polygenic analysis (CAMTA1…

Lithic industries, modern tools, and language: An evolutionary perspective through fMRI.

Tool use is a defining cognitive ability of the human species, relying on technical reasoning-a causal and analogical understanding of physical principles. Neuroarchaeological studies suggest that lithic tool use engaged a specialized frontoparietal network, which evolved into the left-lateralized network observed for modern tools. This network includes the left inferior parietal lobule, particularly the area PF, linked to technical reasoning, and the left inferior frontal gyrus, which is both involved in tool use and language. Since these latter two domains are based on hierarchical structuri…

Structured Transformation of Unstructured Prostate MRI Reports Using Large Language Models.

OBJECTIVES: to assess the ability of high-performing open-weight large language models (LLMs) in extracting key radiological features from prostate MRI reports. METHODS: Five LLMs (Llama3.3, DeepSeek-R1-Llama3.3, Phi4, Gemma-2, and Qwen2.5-14B) were used to analyze free-text MRI reports retrieved from clinical practice. Each LLM processed reports three times using specialized prompts to extract (1) dimensions, (2) volume and PSA density, and (3) lesion characteristics. An experienced radiologist manually annotated the dataset, defining entities (Exam) and sub-entities (Lesion, Dimension). Fea…

Association between primary language and perioperative outcomes for geriatric hip fractures.

INTRODUCTION: The purpose of this study was to assess whether language affects patient time to surgery following hip fractures. METHODS: Patients >55 years who underwent operative hip fracture repair between 2014 and 2021 were reviewed for demographics, language, hospital quality measures, and outcomes. Patients were split into English (E) or non-English (NE) cohorts based on their primary language. RESULTS: A total of 1880 patients (1477 E, 403 NE) were included. The E cohort was younger, had lower body mass index, and lower American Society of Anesthesiology Score (P < .01). The E cohort h…

Nursing personnel and speech-language therapists communication practices in dysphagia management.

BACKGROUND: Communication between speech-language therapists (SLTs) and nursing personnel is essential for safe dysphagia management, as unclear exchanges can compromise patient outcomes and care continuity. In South Africa, high patient loads, limited dysphagia training, and linguistic diversity create additional challenges, making effective interprofessional communication crucial. OBJECTIVES: This study aimed to identify communication practices related to dysphagia in exchanges between SLTs and nursing personnel, focusing on mutual understanding, openness in interactions and frustration exp…

A vision-language pretrained transformer for versatile clinical respiratory disease applications.

General artificial intelligence models have unique challenges in clinical practice when applied to diverse modalities and complex clinical tasks. Here we present MedMPT, a versatile, clinically oriented pretrained model tailored for respiratory healthcare, trained on 154,274 pairs of chest computed-tomography scans and radiograph reports. MedMPT adopts self-supervised learning to acquire medical insights and is capable of handling multimodal clinical data and supporting various clinical tasks aligned with clinical workflows. We evaluate the performance of MedMPT on a broad spectrum of chest-re

Utility of word embeddings from large language models in medical diagnosis.

OBJECTIVE: This study evaluates the utility of word embeddings, generated by large language models (LLMs), for medical diagnosis by comparing the semantic proximity of symptoms to their eponymic disease embedding ("eponymic condition") and the mean of all symptom embeddings associated with a disease ("ensemble mean"). MATERIALS AND METHODS: Symptom data for 5 diagnostically challenging pediatric diseases-CHARGE syndrome, Cowden disease, POEMS syndrome, Rheumatic fever, and Tuberous sclerosis-were collected from PubMed. Using the Ada-002 embedding model, disease names and symptoms were transla…

Predicting Postpartum Hemorrhage Using Clinical Features Extracted With Large Language Models.

OBJECTIVE: To evaluate whether large language models (LLMs) applied to prenatal clinical notes can predict postpartum hemorrhage (PPH) before the onset of labor and to compare model performance across outcome definitions, including a novel intervention-based definition. METHODS: We conducted a retrospective cohort study within a large regional health network. Two outcome definitions for PPH were used: 1) estimated or quantitative blood loss (EBL-QBL) extracted from clinical notes; and 2) a clinical intervention-based PPH definition (cPPH) designed to capture significant hemorrhage requiring i…

Toward a Recognition System for Mexican Sign Language: Arm Movement Detection.

This paper describes ongoing work surrounding the creation of a recognition system for Mexican Sign Language (LSM). We propose a general sign decomposition that is divided into three parts, i.e., hand configuration (HC), arm movement (AM), and non-hand gestures (NHGs). This paper focuses on the AM features and reports the approach created to analyze visual patterns in arm joint movements (wrists, shoulders, and elbows). For this research, a proprietary dataset-one that does not limit the recognition of arm movements-was developed, with active participation from the deaf community and LSM exper…

Can a large language model inform patients about auditory brainstem implants?

OBJECTIVE: This study evaluated the performance of ChatGPT-4o in responding to patient-centered questions concerning auditory brainstem implantation (ABI), with a focus on content quality and readability. METHODS: A total of 51 real-world patient questions related to ABI were reviewed and grouped into five thematic categories: diagnosis and candidacy, surgical procedures and complications, device function and mapping, rehabilitation and expected outcomes, and daily life and long-term concerns. Responses were independently assessed by two audiologists and one otologist across four domains-accu

Tropical kidney diseases: underrepresented in foundational English-language medical education resources.

Tropical nephrology refers to kidney diseases commonly found in tropical and subtropical regions. These conditions, such as malaria-associated acute kidney injury, leptospirosis with renal involvement, schistosomiasis-related nephropathy, HIV-associated nephropathy, and dengue-associated kidney injury, are becoming increasingly relevant to clinicians worldwide due to global travel, climate change, and migration. However, their coverage in foundational English-language medical education resources may be inadequate, potentially impairing clinicians' ability to manage these conditions effectively…

Оценка приемлемости преподавания и обычного языка во время общения с пациентами.

ЦЕЛЬ: В ходе этого исследования участники изучили вопрос о приемлемости использования врачами языка преподавания и обычного языка. МИНИМОДЫ: Обследование продолжительностью 30 мин. было проведено для 162 студентов, которые наблюдали и оценивали два врачебно-стационарных взаимодействия, объясняющих множественный склероз и диабет. &lt; &lt; Взаимодействие &gt; &gt; включало только жаргон, жаргон+тач-бэк &gt; &gt; , только простой язык и обычный язык+трибут. Результаты: Полученные результаты свидетельствуют о том, что обычному языку отдается значительное предпочтение по сравнению с жаргоном как п

Совпадение в аннотации оригинала
OBJECTIVE: This research investigated participants' acceptability of clinicians' use of teach-back and plain language. METHODS: A 30-min survey was administered to 162 undergraduates who watched and rated two doctor-patient interactions explaining multiple sclerosis and diabetes.Interactions included jargon only, jargon+teach-back, plain language only, and …

Mapping the basal temporal language network: a SEEG functional connectivity study.

The Basal Temporal Language Area (BTLA) is recognized in epilepsy surgery setting when cortical electrical stimulation (CES) of the ventral temporal cortex (VTC) trigger anomia or paraphasia during naming tasks. Despite acknowledging a ventral language stream, current cognitive language models fail to properly integrate this entity. In this SEEG study we used cortico-cortical evoked potentials in nine epileptic patients to assess and compare the effective connectivity of 73 sites in the left VTC of which 26 were deemed eloquent for naming after CES (BTLA). Eloquent sites connectivity supports …

Large language models to facilitate pregnancy prediction after in vitro fertilization.

We evaluated the efficacy of large language models (LLMs), specifically, generative pre-trained transformer-4 (GPT-4), in predicting pregnancy following in vitro fertilization (IVF) treatment and compared its accuracy with results from an original published study. Our findings revealed that GPT-4 can autonomously develop and refine advanced machine learning models for pregnancy prediction with minimal human intervention. The prediction accuracy was 0.79, and the area under the receiver operating characteristic curve (AUROC) was 0.89, exceeding or being at least equivalent to the metrics report…

Secondary language impairment in posterior cortical atrophy: insights from sentence repetition.

INTRODUCTION: Posterior cortical atrophy (PCA) is a neurodegenerative syndrome characterized by progressive impairment in visuospatial and perceptual function linked to atrophy of the occipito-parietal cortex. Besides the salient visual impairment, several studies have documented subtle changes in language may also be present. Sentence repetition is a highly constrained linguistic task involving multiple linguistic and cognitive processes and have been shown to be impaired in other AD spectrum disorders, with little consensus on its relevance in PCA. This aim of this study was to further delin…

Developing expressive language skills of deaf students through specialized writing instruction.

Writing is an essential element of literacy development, and language plays a central role in the composing process, including developing, organizing, and refining ideas. Language and writing are interconnected, making it paramount for educators to attend to the development of deaf students' language skills. In this quasi-experimental study, we examined the impact of strategic and interactive pedagogical approaches, namely Strategic and Interactive Writing Instruction, implemented with deaf students in grades 3-6 to develop genre-specific traits in their expressive language (spoken or signed) …

Neural underpinnings of sentence reading in deaf, native sign language users.

The goal of this study was to investigate sentence-level reading circuits in deaf native signers, a unique group of deaf people who are immersed in a fully accessible linguistic environment from birth, and hearing readers. Task-based fMRI, functional connectivity and lateralization analyses were conducted. Both groups exhibited overlapping brain activity in the left-hemispheric perisylvian regions in response to a semantic sentence task. We found increased activity in left occipitotemporal and right frontal and temporal regions in deaf readers. Lateralization analyses did not confirm more righ

South African speech-language therapists' and audiologists' professional quality of life.

BACKGROUND: Limited research is available regarding the professional quality of life experiences of South African speech-language therapists and audiologists, despite the implications this has for wellbeing, quality of patient care, productivity and attrition from the professions. OBJECTIVES: This study explored levels of compassion satisfaction, burnout, and secondary traumatic stress, the relationships between these, differences on the basis of registration and years of experience and participants' perceptions of their professional quality of life. METHOD: A sample of 92 South African spee…