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

Classification of Illness01:17

Classification of Illness

8.0K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
8.0K

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

Extracorporeal Membrane Oxygenation Support Before Pediatric Heart Transplantation: A Comparison of Two Eras.

ASAIO journal (American Society for Artificial Internal Organs : 1992)·2026
Same author

Optimizing AI implementation for surgery: recommendations for infrastructure and deployment in the operating room.

NPJ digital medicine·2026
Same author

Reinforcement Learning for Intraoperative Hypotension Management with Consideration to Postoperative Acute Kidney Injury.

Kidney360·2026
Same author

An Exploration of Competency Assessment in Graduate Medical Education.

Journal of graduate medical education·2026
Same author

Divergent chromatin remodeling trajectories in CD66b <sup>+</sup> MDSCs distinguishes recovery from chronic critical illness after sepsis.

bioRxiv : the preprint server for biology·2026
Same author

Building AI competence in the healthcare workforce with the AI for clinical care workshop: A Bridge2AI for clinical CHoRUS project.

Journal of clinical and translational science·2025

相关实验视频

Updated: Sep 16, 2025

Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma
10:31

Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma

Published on: August 9, 2016

12.9K

多标签文档语言模型 探索性腹腔切除术手术概念的分类 操作笔记:算法开发研究

Jeremy A Balch1,2, Sasank S Desaraju3, Victoria J Nolan1

  • 1Department of Surgery, University of Florida College of Medicine, Gainesville, FL, United States.

JMIR medical informatics
|July 9, 2025
PubMed
概括
此摘要是机器生成的。

大型语言模型 (LLM) 显著提高了从外科手术笔记中提取数据的性能,优于传统方法. 为了在外科研究和质量改进中可靠使用,需要进一步改进.

关键词:
查看图表查看图表 查看图表探索性腹腔切除术 (LAPAROTOMY) 是一种探索性腹腔切除术.整体外科的一般手术.生成型的大型语言模型自然语言处理自然语言处理.

更多相关视频

Learning Modern Laryngeal Surgery in a Dissection Laboratory
07:30

Learning Modern Laryngeal Surgery in a Dissection Laboratory

Published on: March 18, 2020

8.2K
Clinical Application of Single-Surgeon, Three-Port, Laparoscopic Resection for Colorectal Cancer with Natural Orifice Specimen Extraction
08:26

Clinical Application of Single-Surgeon, Three-Port, Laparoscopic Resection for Colorectal Cancer with Natural Orifice Specimen Extraction

Published on: March 24, 2023

642

相关实验视频

Last Updated: Sep 16, 2025

Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma
10:31

Intraoperative Gastroscopy for Tumor Localization in Laparoscopic Surgery for Gastric Adenocarcinoma

Published on: August 9, 2016

12.9K
Learning Modern Laryngeal Surgery in a Dissection Laboratory
07:30

Learning Modern Laryngeal Surgery in a Dissection Laboratory

Published on: March 18, 2020

8.2K
Clinical Application of Single-Surgeon, Three-Port, Laparoscopic Resection for Colorectal Cancer with Natural Orifice Specimen Extraction
08:26

Clinical Application of Single-Surgeon, Three-Port, Laparoscopic Resection for Colorectal Cancer with Natural Orifice Specimen Extraction

Published on: March 24, 2023

642

科学领域:

  • 自然语言处理 (NLP) 是一种自然语言处理.
  • 医疗保健中的机器学习
  • 手术数据科学手术数据科学

背景情况:

  • 操作笔记对于临床护理,研究和计费至关重要,但手动提取数据是耗时的.
  • 传统的NLP方法,如词袋 (BoW) 和tf-idf,对复杂的手术笔记分析有局限性.
  • 大型语言模型 (LLM) 在增强或取代手术文本挖掘的传统NLP方面表现有前途.

研究的目的:

  • 开发和评估LLMs以加快从外科手术手术笔记中提取数据.
  • 将LLM与传统NLP技术的性能进行比较,以对外科概念进行多标签分类.
  • 评估不同LLM架构的实用性以及背景对分类准确性的影响.

主要方法:

  • 一个数据集由388个探索性腹腔切除术笔记组成,对21个外科概念进行了注释.
  • 将传统的BoW和tf-idf模型与仅用编码器 (临床长变压器) 和仅用解码器 (Llama 3) 的变压器模型进行比较.
  • 使用5倍交叉验证,F1得分和哈明损失 (HL) 进行评估的多标签分类,有或没有上下文信息.

主要成果:

  • 只有解码器的Llama 3模型实现了最高的性能 (微F1得分0.88,HL 0.11),显著超过BoW,tf-idf和临床-longformer.
  • 整合上下文使拉玛3的F1分数平均提高了0.16.
  • 性能在各个概念中各不相同,在分类污染和处理先前或同时操作等复杂案例方面存在挑战.

结论:

  • 现成的自动回归LLM在分类外科手术手术笔记方面表现优于传统的NLP和仅编码器模型.
  • 在外科手术中,LLM提供了一种潜在的解决方案,可以简化回顾性审查.
  • 需要进一步开发,以解决语义细微差别和边缘情况,以便在研究和质量改进中可靠地应用.