MedElevator Войти в исследования
Открытая медицинская библиотека

Результаты поиска

Медицинские публикации, первоисточники и полные тексты.
Для клинического вопроса, нового знания и следующего исследования.

Ищем по исходному запросу. Уточняем медицинские термины для поиска на других языках…

Результаты поиска

8 125 публикаций

Поиск: 46 мс
Публикации на разных языках · PubMed, Europe PMC и данные издателей через Crossref · 1 947 с найденным полным текстом
Выберите статьи для научной работыПосле входа — выбор статей и сборка документа

DeepSeek-R1 vs OpenAI o1 for Ophthalmic Diagnoses and Management Plans.

IMPORTANCE: Large language models (LLMs) are increasingly being explored in clinical decision-making, but few studies have evaluated their performance on complex ophthalmology cases from clinical practice settings. Understanding whether open-weight, reasoning-enhanced LLMs can outperform proprietary models has implications for clinical utility and accessibility. OBJECTIVE: To evaluate the diagnostic accuracy, management decision-making, and cost of DeepSeek-R1 vs OpenAI o1 across diverse ophthalmic subspecialties. DESIGN, SETTING, AND PARTICIPANTS: This was a cross-sectional evaluation condu…

СтатьяСравнительное исследованиеПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 40906471Открыть статью

Semantic distance metrics in anatomy education: Toward AI-assisted mapping of anatomy-to-clinical reasoning.

Anatomy education traditionally emphasizes structural knowledge acquisition, with the implicit assumption that clinical reasoning capabilities will naturally follow. However, the cognitive pathway from anatomical understanding to clinical application is rarely linear or uniform. This article proposes a conceptual framework in which semantic distance-the conceptual separation between anatomical knowledge and clinical endpoints-operates at three analytically distinct levels: (1) the learner's internal cognitive network, shaped by prior experience and schema formation; (2) the structural distance

СтатьяПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 42900165Открыть статью

From people to prompts: Understanding susceptibility to persuasion in conversations with artificial intelligence.

Influencing others through conversation is fundamental to social interactions. With the rise of generative artificial intelligence (GenAI), people are increasingly relying on conversational AI for guidance on consumption and lifestyle choices, from picking a cuisine to choosing a travel destination. However, can conversational AI exert enough persuasive influence to serve as a viable substitute for human opinions? Across five experiments involving real conversations, participants discussed an opinion-based topic (e.g., whether it is worth subscribing to more than one streaming service) with a

СтатьяПолный текст не найденПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 42734969Открыть статью

STING-ExositeDB: An AI-assisted curated database of protein exosites for drug discovery.

MOTIVATION: Protein exosites are secondary binding sites that recruit macromolecular partners and control molecular recognition across protein families. Despite their therapeutic potential demonstrated by approved drugs such as bivalirudin, systematic characterization remains limited by fragmented literature and inconsistent reporting. Existing databases lack exosite-specific curation, residue-level contact mapping, and structure-function integration. RESULTS: We present ExositeDB, a curated database of protein exosites built through AI-assisted curation combining large language model extract

СтатьяПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 42519883Открыть статью

From feasibility to translational pathways: a bibliometric and knowledge-mapping analysis of urine-based liquid biopsy in urologic cancers (2015-2025).

BACKGROUND: Urine-based liquid biopsy enables non-invasive, repeat sampling in urologic cancers, yet evidence remains fragmented across diseases, analytes, and platforms. We mapped the research landscape and clinically framed thematic trajectories of the field. METHODS: English-language articles and reviews (2015–2025) were retrieved from WoSCC (SCIE) using urologic cancer terms combined with urine/urinary and “liquid biopsy”. CiteSpace, VOSviewer and bibliometrix were used to map collaboration, co-citation, citation bursts and keyword evolution. Robustness was assessed via sensitivity analyse

СтатьяОбзорПоддержка исследования: вне правительства СШАПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 41882723Открыть статью

Adverse Oral Mucosal Reaction to Sublingual Captopril: A Case Report With Exploratory Insights Into AI-Assisted Clinical Reasoning.

AIMS: To describe a probable oral mucosal injury associated with the off-label sublingual administration of captopril in a medically complex patient, and to illustrate the role of structured clinical reasoning in identifying route-related adverse drug reactions, with exploratory insights into AI-assisted reasoning. METHODS AND RESULTS: A 77-year-old patient presented with persistent burning pain and a progressive oral mucosal lesion on the floor of the mouth. Despite appropriate management of local infectious and mechanical factors, symptoms worsened over time. A consistent temporal relations

Клинический случайСтатьяПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 42499297Открыть статью

Utility of an LLM-powered experts-in-the-loop chatbot for pre- and post-operative care of cataract surgery patients.

PurposeTo evaluate the utility of CataractBot, an LLM (Large Language Model)-powered chatbot that provides doctor-verified answers to patient questions about cataract surgery. We examine its use by both end-users (patients and attendants) and medical experts.MethodsA 24-week study was conducted to evaluate CataractBot among patients, their attendants, doctors, and patient coordinators. The bot responded instantly to questions by querying a knowledge base curated by medical professionals. Each response was asynchronously verified by an ophthalmologist (for medical questions) or a patient coordi

СтатьяПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 41358933Открыть статью

Quantifying uncert-AI-nty: Testing the accuracy of LLMs' confidence judgments.

The rise of Large Language Model (LLM) chatbots, such as ChatGPT and Gemini, has revolutionized how we access information. These LLMs can answer a wide array of questions on nearly any topic. When humans answer questions, especially difficult or uncertain questions, they often accompany their responses with metacognitive confidence judgments indicating their belief in their accuracy. LLMs are certainly capable of providing confidence judgments, but it is currently unclear how accurate these confidence judgments are. To fill this gap in the literature, the present studies investigate the capabi

СтатьяПоддержка правительства СШАПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 40694202Открыть статью

Exploring internal representations of self-supervised networks: few-shot learning abilities and comparison with human semantics and recognition of objects.

Recent advances in self-supervised learning have attracted significant attention from both machine learning and neuroscience. This is primarily because self-supervised methods do not require annotated supervisory information, making them applicable to training artificial networks without relying on large amounts of curated data, and potentially offering insights into how the brain adapts to its environment in an unsupervised manner. Although several previous studies have elucidated the correspondence between neural representations in deep convolutional neural networks (DCNNs) and biological sy

СтатьяПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 41357072Открыть статью

Quantitative electroencephalography predicts delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage: a retrospective study.

PURPOSE: Delayed cerebral ischemia (DCI) is a common complication that occurs in aneurysmal subarachnoid hemorrhage (aSAH). This complication can lead to clinical deterioration and poor prognosis. The aim of this study is to explore the risk factors for DCI in aSAH patients in neurological ICU, develop a nomogram including quantitative electroencephalography (qEEG) parameters, and evaluate its performance. METHODS: We retrospectively analyzed and processed Severe aneurysmal subarachnoid hemorrhage (SaSAH) patients from June 2022 to May 2024 who underwent bedside qEEG monitoring and analyzed t

СтатьяПолный текст не найденПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 40288200Открыть статью

Performance of ChatGPT and Dental Students on Concepts of Periodontal Surgery.

INTRODUCTION: As a large language model, chat generative pretrained transformer (ChatGPT) has provided a valuable tool for various medical scenarios with its interactive dialogue-based interface. However, there is a lack of studies on ChatGPT's effectiveness in handling dental tasks. This study aimed to compare the knowledge and comprehension abilities of ChatGPT-3.5/4 with that of dental students about periodontal surgery. MATERIALS AND METHODS: A total of 134 dental students participated in this study. We designed a questionnaire consisting of four questions about the inclination for ChatGP

СтатьяПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 39446672Открыть статью

The Optimization of a Natural Language Processing Approach for the Automatic Detection of Alzheimer's Disease Using GPT Embeddings.

The development of noninvasive and cost-effective methods of detecting Alzheimer's disease (AD) is essential for its early prevention and mitigation. We optimize the detection of AD using natural language processing (NLP) of spontaneous speech through the use of audio enhancement techniques and novel transcription methodologies. Specifically, we utilized Boll Spectral Subtraction to improve audio fidelity and created transcriptions using state-of-the-art AI services-locally-based Wav2Vec and Whisper, alongside cloud-based IBM Cloud and Rev AI-evaluating their performance against traditional ma

СтатьяПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 38539600Открыть статью

Introduction of the Mediterranean diet in pregnancy and the incidence of gestational diabetes mellitus: A systematic review of randomised controlled trials and meta-analysis.

OBJECTIVES: To determine if introducing the Mediterranean diet in pregnancy reduces the incidence of gestational diabetes. STUDY DESIGN: Systematic review and meta-analysis of randomised controlled trials (RCTs). A literature search was conducted using the following databases: MEDLINE, Embase, Cochrane Central Register of Controlled Trials, and CINAHL with no language or date restrictions. Studies were deemed eligible if the population was pregnant women, the intervention was the Mediterranean diet, and the outcome was gestational diabetes. Quality assessment was carried out using the Cochran

СтатьяСистематический обзорМетаанализПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 38889571Открыть статью

ChatGPT and Ophthalmology: Exploring Its Potential with Discharge Summaries and Operative Notes.

PURPOSE: This study aimed to report the abilities of the large language model ChatGPTR (OpenAI, San Francisco, USA) in constructing ophthalmic discharge summaries and operative notes. METHODS: A set of prompts was constructed through statements incorporating common ophthalmic surgeries across the subspecialties of the cornea, retina, glaucoma, paediatric ophthalmology, neuro-ophthalmology, and ophthalmic plastics surgery. The responses of ChatGPT were assessed by three surgeons carefully and analyzed them for evidence-based content, specificity of the response, presence of generic text, discl

СтатьяПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 37133418Открыть статью

Using GPT-3 to Build a Lexicon of Drugs of Abuse Synonyms for Social Media Pharmacovigilance.

Drug abuse is a serious problem in the United States, with over 90,000 drug overdose deaths nationally in 2020. A key step in combating drug abuse is detecting, monitoring, and characterizing its trends over time and location, also known as pharmacovigilance. While federal reporting systems accomplish this to a degree, they often have high latency and incomplete coverage. Social-media-based pharmacovigilance has zero latency, is easily accessible and unfiltered, and benefits from drug users being willing to share their experiences online pseudo-anonymously. However, unlike highly structured of

СтатьяПоддержка исследования: вне правительства СШАПоддержка NIH: внешняя программаПоддержка правительства СШАПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 36830756Открыть статью

Prevalence and Correlates of Comorbid Posttraumatic Stress Disorder in Schizophrenia-Spectrum Disorder: A Systematic Review and Meta-Analysis.

OBJECTIVE: Schizophrenia-spectrum disorders and posttraumatic stress disorder (PTSD) share common clinical manifestations, genetic vulnerability, and environmental risk factors. We aimed to conduct a systematic review and meta-analysis of the comorbid prevalence of PTSD among schizophrenia-spectrum disorders. METHODS: We performed a meta-analysis to identify possible contributing factors to the heterogeneity among these studies. We systematically searched electronic databases with no restrictions on language of articles. RESULTS: We extracted 24 samples (18 for current prevalence and 6 for l

СтатьяПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 37248688Открыть статью

Using Xenopus to discover new candidate genes involved in BOR and other congenital hearing loss syndromes.

Hearing in infants is essential for brain development, acquisition of verbal language skills, and development of social interactions. Therefore, it is important to diagnose hearing loss soon after birth so that interventions can be provided as early as possible. Most newborns in the United States are screened for hearing deficits and commercially available next-generation sequencing hearing loss panels often can identify the causative gene, which may also identify congenital defects in other organs. One of the most prevalent autosomal dominant congenital hearing loss syndromes is branchio-oto-

СтатьяПоддержка NIH: внешняя программаПоддержка исследования: вне правительства СШАОбзорПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 37830236Открыть статью

Timing of surgery for asymptomatic patients with severe aortic valve stenosis: An updated systematic review and meta-analysis.

BACKGROUND: The research findings concerning the effect of early surgery on mortality among asymptomatic patients with severe aortic valve stenosis (AS) are controversial and contradictory. In this study, the total weight of evidence regarding early surgery versus conservative management in these population was examined. METHODS: Embase, PubMed, CENTRAL, and CINAHL databases were thoroughly searched without language restriction until 29 February, 2020. We included all studies exploring the mortality in asymptomatic patients with severe AS comparing early surgery with conservative management a

СтатьяМетаанализСистематический обзорПолный текст не найденПеревод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 33549719Открыть статью

Impact of air quality on the gastrointestinal microbiome: A review.

BACKGROUND: Poor air quality is increasingly associated with several gastrointestinal diseases suggesting a possible association between air quality and the human gut microbiome. However, details on this remain largely unexplored as current available research is scarce. The aim of this comprehensive rigorous review was to summarize the existing reports on the impact of indoor or outdoor airborne pollutants on the animal and human gut microbiome and to outline the challenges and suggestions to expand this field of research. METHODS AND RESULTS: A comprehensive search of several databases (ince

СтатьяПоддержка исследования: вне правительства СШАОбзорПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 32289569Открыть статью

Developing a patient-reported experience questionnaire with and for people who use drugs: A community engagement process in Vancouver's Downtown Eastside.

People who use drugs (PWUD) frequently have complex health care needs, yet face multiple barriers to accessing services. Involving PWUD in health service design and evaluation can enhance the quality of data collected and ensure policy and practice improvements reflect the expressed needs of the population. However, PWUD remain largely excluded from the evaluation of health services that directly affect their lives, including development of patient-reported experience measures (PREMS) that have gained prominence in health services research and clinical practice. Detailed descriptions of PWUD p

СтатьяПоддержка исследования: вне правительства СШАПоиск полного текста в очередиПеревод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

PMID 29966804Открыть статью