Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Genome sequencing identifies monogenic causes in adults with metabolic diseases.

Journal of the Endocrine Society·2026
Same author

Diabetic Status, Advanced Age, and Hispanic Ethnicity Predict Poorer Weight Loss in Patients With Obesity Receiving Semaglutide.

Endocrine practice : official journal of the American College of Endocrinology and the American Association of Clinical Endocrinologists·2026
Same author

The Chatbot in My Head: Learning from My Inner Reflective Voice.

Academic psychiatry : the journal of the American Association of Directors of Psychiatric Residency Training and the Association for Academic Psychiatry·2026
Same author

Seeing medicine: learning to read between the shadows.

Academic medicine : journal of the Association of American Medical Colleges·2026
Same author

Finding Poetry in Vital Signs.

Anesthesiology·2026
Same author

Treatment of Modifiable Risks in Metabolic Dysfunction-Associated Steatotic Liver Disease: Drugs Targeting Obesity and Type 2 Diabetes.

Clinics in liver disease·2026
Same journal

A Retrospective Analysis of Cardiac Anatomy in Patients Undergoing the Fontan Operation.

Cureus·2026
Same journal

A Narrative Review of the Potential Impact of Next-Generation Tobacco and Nicotine Products on Cardiovascular Health.

Cureus·2026
Same journal

A Prospective Comparative Study for the Evaluation of Digital Learning as an Academic Tool for MBBS Phase III Students.

Cureus·2026
Same journal

Crossing the Septum: May-Thurner Syndrome and Patent Foramen Ovale as a Dual Mechanism for Recurrent Ischemic Stroke.

Cureus·2026
Same journal

Physical Restraint Practices, Attitudes, and Ethical Perceptions Among Intensive Care Unit (ICU) Doctors and Nurses in Morocco: A Cross-Sectional Survey Highlighting the Training-Use Paradox.

Cureus·2026
Same journal

Reversible Rapidly Progressive Dementia Due to Cerebral Amyloid Angiopathy.

Cureus·2026
查看所有相关文章

相关实验视频

Updated: Jun 12, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

510

为血管外科委员会认证做准备:使用大型语言模型进行比较研究.

Sonal Kumar1, George Y Tadros2, Taylor E Collignon3

  • 1Vascular Surgery, Ross University School of Medicine, Miramar, USA.

Cureus
|June 10, 2025
PubMed
概括
此摘要是机器生成的。

与其他大型语言模型 (LLM) 相比,Claude 3.5 在回答血管外科委员会考试问题方面表现出卓越的表现. 虽然有希望,但目前的LLM需要进一步发展,以充分支持血管外科教育.

关键词:
人工智能绩效评价AI的表现评估美国外科手术委员会.人工智能的人工智能是人工智能.在手术中使用人工智能.董事会考试的委员会考试.这是一项比较性研究.大型语言模型.血管教育和自我评估计划.血管外科手术 血管外科血管外科教育 血管外科教育

更多相关视频

Surgical Training for the Implantation of Neocortical Microelectrode Arrays Using a Formaldehyde-fixed Human Cadaver Model
08:11

Surgical Training for the Implantation of Neocortical Microelectrode Arrays Using a Formaldehyde-fixed Human Cadaver Model

Published on: November 19, 2017

11.3K
Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.6K

相关实验视频

Last Updated: Jun 12, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

510
Surgical Training for the Implantation of Neocortical Microelectrode Arrays Using a Formaldehyde-fixed Human Cadaver Model
08:11

Surgical Training for the Implantation of Neocortical Microelectrode Arrays Using a Formaldehyde-fixed Human Cadaver Model

Published on: November 19, 2017

11.3K
Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.6K

科学领域:

  • 医疗教育 技术 技术 医学教育
  • 在外科手术中使用人工智能
  • 血管外科培训 血管外科培训

背景情况:

  • 大型语言模型 (LLM) 正在成为医学教育中的变革性工具.
  • 有限的研究存在于LLM应用,特别是在血管外科培训.
  • 评估LLM在血管外科委员会认证准备中的有效性至关重要.

研究的目的:

  • 评估和比较各种LLM在准备血管外科委员会认证考试时的有效性.
  • 探索LLM作为血管外科的补充教育资源的潜力.

主要方法:

  • 使用了来自血管教育和自我评估计划 (VESAP) 版本6的269个基于文本的多选题.
  • 四个人工智能工具 (ChatGPT 3.5,Google Gemini,Microsoft Bing,Claude 3.5) 被一个独立的审查员评估.
  • 问题被输入无上下文的隐形AI窗口;千平方测试分析了性能变化.

主要成果:

  • 克劳德3.5实现了最高的准确性 (65.7%),超过了谷歌双子座 (55.3%),聊天GPT (55.0%) 和微软Bing (53.9%).
  • 克劳德3.5在各个学科中显示出显著的绩效差异 (p=0.001),在下肢 (86%) 和透析接入 (80%) 中表现出色.
  • 聊天GPT,谷歌Gemini和微软Bing没有表现出学科的显著准确度变化.

结论:

  • 克劳德3.5在回答血管外科委员会考试问题 (VSQE6) 中表现优异.
  • LLM显示出作为补充工具的潜力,特别是在诸如下肢血管问题和透析接入等主题上.
  • 目前的LLM能力并不完全满足血管外科教育不断发展的需求;预计将进一步发展.