History

History
  • 文章类型: Journal Article
    背景:虽然病史是诊断疾病的基础,由于资源限制,教学和提供技能反馈可能具有挑战性。因此,虚拟模拟患者和基于网络的聊天机器人已经成为教育工具,随着人工智能(AI)的最新进展,如大型语言模型(LLM),增强了它们的真实性和提供反馈的潜力。
    目的:在我们的研究中,我们旨在评估生成预训练变压器(GPT)4模型的有效性,以对医学生在模拟患者的历史表现提供结构化反馈.
    方法:我们进行了一项前瞻性研究,涉及医学生使用GPT驱动的聊天机器人进行历史学习。为此,我们设计了一个聊天机器人来模拟病人的反应,并提供对学生的全面性的即时反馈。分析了学生与聊天机器人的互动,并将聊天机器人的反馈与人类评估者的反馈进行了比较。我们测量了评估者间的可靠性,并进行了描述性分析以评估反馈的质量。
    结果:研究的大多数参与者都在医学院三年级。我们的分析中总共包括了来自106个对话的1894个问答对。在超过99%的病例中,GPT-4的角色扮演和反应在医学上是合理的。GPT-4与人类评估者之间的评估者间可靠性显示出“几乎完美”的一致性(Cohenκ=0.832)。在45个反馈类别中的8个中,检测到的一致性较低(κ<0.6)突出了模型评估过于具体或与人类判断不同的主题。
    结论:GPT模型在医学生提供的关于历史记录对话的结构化反馈方面是有效的。尽管我们揭示了某些反馈类别的反馈特异性的一些限制,与人类评估者的总体高度一致表明,LLM可以成为医学教育的宝贵工具。我们的发现,因此,倡导在医疗培训中仔细整合人工智能驱动的反馈机制,并在这种情况下使用LLM时突出重要方面。
    BACKGROUND: Although history taking is fundamental for diagnosing medical conditions, teaching and providing feedback on the skill can be challenging due to resource constraints. Virtual simulated patients and web-based chatbots have thus emerged as educational tools, with recent advancements in artificial intelligence (AI) such as large language models (LLMs) enhancing their realism and potential to provide feedback.
    OBJECTIVE: In our study, we aimed to evaluate the effectiveness of a Generative Pretrained Transformer (GPT) 4 model to provide structured feedback on medical students\' performance in history taking with a simulated patient.
    METHODS: We conducted a prospective study involving medical students performing history taking with a GPT-powered chatbot. To that end, we designed a chatbot to simulate patients\' responses and provide immediate feedback on the comprehensiveness of the students\' history taking. Students\' interactions with the chatbot were analyzed, and feedback from the chatbot was compared with feedback from a human rater. We measured interrater reliability and performed a descriptive analysis to assess the quality of feedback.
    RESULTS: Most of the study\'s participants were in their third year of medical school. A total of 1894 question-answer pairs from 106 conversations were included in our analysis. GPT-4\'s role-play and responses were medically plausible in more than 99% of cases. Interrater reliability between GPT-4 and the human rater showed \"almost perfect\" agreement (Cohen κ=0.832). Less agreement (κ<0.6) detected for 8 out of 45 feedback categories highlighted topics about which the model\'s assessments were overly specific or diverged from human judgement.
    CONCLUSIONS: The GPT model was effective in providing structured feedback on history-taking dialogs provided by medical students. Although we unraveled some limitations regarding the specificity of feedback for certain feedback categories, the overall high agreement with human raters suggests that LLMs can be a valuable tool for medical education. Our findings, thus, advocate the careful integration of AI-driven feedback mechanisms in medical training and highlight important aspects when LLMs are used in that context.
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

  • 文章类型: Journal Article
    宫腔镜检查真正彻底改变了妇科诊断和手术领域。目前,它被认为是诊断和治疗子宫内疾病的金标准方法,并且从根本上改变了妇科医生治疗患有此类疾病的患者的方式。这些疾病现在可以在门诊进行诊断和治疗,由于技术的进步和仪器的缩小。两百年的发展和显着的创新现在反映在目前的宫腔镜实践。这篇综述试图通过强调技术的进步以及这种开创性方法提供的治疗和诊断益处来追踪宫腔镜检查的界限推动历史。
    Hysteroscopy has truly revolutionized the field of diagnostic and operative gynecology. It is presently regarded as the gold standard method for both the diagnosis and treatment of intrauterine diseases and it has fundamentally altered the way gynecologists treat patients with such conditions. These pathologies can now be diagnosed and treated in an outpatient setting, thanks to technological advancements and instrument downsizing. Two hundred years of development and notable innovation are now reflected in the present hysteroscopic practice. This review attempts to trace the boundaries-pushing history of hysteroscopy by highlighting the advancements in technology and the therapeutic and diagnostic benefits offered by this groundbreaking approach.
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

  • 文章类型: News
    暂无摘要。
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

  • 文章类型: Journal Article
    这篇评论讨论了多动症的历史,以及它如何为当代关于这种疾病的辩论提供信息。它批评多动症的回顾性历史,它提出了这种疾病的早期起源,而不是与历史证据相匹配。结论是指出ADHD何时确实出现为一种独特的疾病,以及为什么这样做。
    This commentary discusses the history of ADHD and how it can inform contemporary debates about the disorder. It critiques retrospective histories of ADHD, which propose earlier origins for the disorder than match the historical evidence. It concludes by indicating when ADHD did emerge as a distinctive disorder and why it did so.
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

  • 文章类型: News
    暂无摘要。
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

  • 文章类型: Journal Article
    不要惊慌.发现莱姆病近50年来,伯氏疏螺旋体已经成为微生物学的主力。对研究宿主-病原体相互作用的兴趣推动了在实验室环境中使挑剔的微生物接近的重大进展,包括培养方法的发展,动物模型,和遗传工具。通过开发这些系统,已经深入了解了微生物如何能够在其植物性周期中存活并引起人类疾病。这里,我们讨论了B.burgdorferi的发现及其作为模型生物的发展,然后深入研究了我们在其生命周期的关键阶段学到的关于B.burgdorferi生物学的重要教训:在蜱血粉期间的基因表达变化,一个新的脊椎动物宿主的定殖,并在脊椎动物中持续感染,直到新的蜱虫进食。我们的目标是强调促进B.burgdorferi研究的进展,并确定我们目前对微生物的理解中的差距。
    Don\'t Panic. In the nearly 50 years since the discovery of Lyme disease, Borrelia burgdorferi has emerged as an unlikely workhorse of microbiology. Interest in studying host-pathogen interactions fueled significant progress in making the fastidious microbe approachable in laboratory settings, including the development of culture methods, animal models, and genetic tools. By developing these systems, insight has been gained into how the microbe is able to survive its enzootic cycle and cause human disease. Here, we discuss the discovery of B. burgdorferi and its development as a model organism before diving into the critical lessons we have learned about B. burgdorferi biology at pivotal stages of its lifecycle: gene expression changes during the tick blood meal, colonization of a new vertebrate host, and developing a long-lasting infection in that vertebrate until a new tick feeds. Our goal is to highlight the advancements that have facilitated B. burgdorferi research and identify gaps in our current understanding of the microbe.
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

  • 文章类型: News
    暂无摘要。
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

  • 文章类型: Journal Article
    识别多动症,冲动,分心,作为临床综合征的情绪不稳定是确定是否有注意力缺陷多动障碍(ADHD)的发现者的核心。正如被诊断患有多动症的儿童的诊所没有捕获同质的男孩和女孩一样,然而,历史也不是。不同的观察者/临床医生选择强调什么反映了什么对他们和他们生活的时代很重要。海因里希·霍夫曼(FidgetyPhilfame)和乔治·斯蒂尔(强调冲动侵略是道德缺陷)所描述的孩子/孩子,例如,没有列出标准(即使现在我们也不能总是同意)来明确证明他们患有多动症。谁在乎!他们认识到某些共同发生行为的重要性,并与我们分享他们的观察结果,这样我们就可以得出结论,我们的诊所的孩子被过去的好观察者所认可。多动症般的孩子,像穷人一样,可能一直和我们在一起.
    Recognition of hyperactivity, impulsivity, distractibility, and emotional lability as a clinical syndrome is at the heart of identifying whether there is a discoverer of the condition of attention deficit hyperactivity disorder (ADHD). Just as clinics of children diagnosed with ADHD do not capture a homogeneous group of boys and girls, however, history does not either. What different observers/clinicians have chosen to highlight reflects what is important to them and to the times in which they lived. The child/children described by Heinrich Hoffman (of Fidgety Phil fame) and George Still (who highlighted impulsive aggression as a moral defect), for instance, did not come with a list of criteria (with which even now we cannot always agree) to prove unequivocally that they had ADHD. Who cares! It is sufficient that they recognized the importance of certain co-occurring behaviors and shared their observations with us such that we can conclude our clinic\'s children were recognized by good past observers. ADHD-like children, like the poor, have probably always been with us.
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

  • 文章类型: Editorial
    暂无摘要。
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

       PDF(Pubmed)

  • 文章类型: Journal Article
    慢性病是世界上死亡的主要原因之一,解决共同风险因素的重大区域和国际努力的主题,实施预防和控制措施,并制定国家目标,作为实现全民健康覆盖的一部分。然而,越来越多的人相信慢性病会出现形象问题。有人建议,术语“使问题变得迟钝”,在这个时代,大众媒体提供了前所未有的机会来告知和说服人们关心自己和他人的健康,慢性病代表仍然是一个有争议和争议的问题。本文调查了20世纪下半叶WHO如何创建和传播视觉叙事以提高大众意识并围绕慢性病建立视觉词汇。它检查了概念化所采取的措施,拍摄和宣传慢性病,并考虑谁控制了他们的代表。主要集中在癌症上,糖尿病和心血管疾病,它揭示了不同的叙述;科技进步的力量;个人和社区为健康而采取的行动;有希望的乌托邦式和平行的反乌托邦式愿景。它将这些嵌入到生产环境中,揭示了一个复杂的描绘过程,涉及克服代表性的挑战。它利用这种历史背景来讨论与如何从视觉上叙述慢性疾病和慢性疼痛有关的问题,比如情绪反应的想法,道德失败,人们如何驾驭“风险社会”,并最终关注媒体对社会疾病形象的有意和无意影响。
    Chronic diseases are among the leading causes of mortality in the world, the subject of major regional and international efforts to tackle shared risk factors, implement prevention and control measures and set national targets as part of the drive towards universal health coverage. Yet there is a growing conviction that chronic diseases suffer an image problem. It has been suggested that the terminology \'dulls the senses\' to the problems, and in an age where the mass media affords unprecedented opportunities to inform and persuade people to care about their health and that of others, chronic disease representation remains a contested and much debated issue.This article investigates how WHO created and disseminated visual narratives to raise popular consciousness and build a visual vocabulary around chronic disease in the second half of the 20th century. It examines the measures taken to conceptualise, photograph and publicise chronic diseases, and considers who had control over their representation. In focussing predominantly on cancer, diabetes and cardiovascular disease, it reveals different narratives; the power of scientific and technological progress; individual and community action for health; promising utopian and parallel dystopian visions. It embeds these in a production context which reveals an intricate picturing process involving overcoming challenges of representation. It uses this historical background to discuss issues relating to how chronic disease and chronic pain have been narrated visually, such as the ideas of emotional response, moral failure, how people navigate the \'risk society\' and ultimately the concerns regarding the intentional and unintentional influence that the media can have on the image of disease given to society.
    导出

    更多引用

    收藏

    翻译标题摘要

    我要上传

    求助全文

公众号