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

Retrospective external validation of the Mayo Delirium Prediction tool in a Swiss cohort of medical and surgical inpatients.

BMC medical informatics and decision making·2026
Same author

Current Evidence of Acetyl-L-Carnitine Use in Mood Disorders-: A Systematic Review and Meta-Analysis.

Neuropsychiatric disease and treatment·2026
Same author

A Structured Consent Framework for Research of Electroconvulsive Therapy in Advanced Dementia: Consent Process for the ECT-AD Trial.

The journal of ECT·2026
Same author

The Rise of Small Language Models in Healthcare: A Comprehensive Survey.

Computer science review·2026
Same author

Socioeconomic deprivation, rurality, and travel distance negatively impact survival in early-stage pancreatic ductal adenocarcinoma but are not associated with stage at diagnosis.

Cancer epidemiology·2026
Same author

A lifecycle governance and learning health system framework for trustworthy, generalizable, and sustainable human-ai partnership in clinical practice: Lessons from the asthma-guidance and prediction system (A-GPS).

Journal of the National Medical Association·2026

相关实验视频

Updated: Sep 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

682

在使用大型语言模型的电子健康记录中确定移动功能状态.

Xingyi Liu1, Muskan Garg1, Heling Jia1

  • 1Mayo Clinic.

Research square
|August 6, 2025
PubMed
概括

大型语言模型 (LLM) 可以从电子健康记录 (EHR) 中的临床笔记中准确地提取患者的移动性状态. 这种方法通过标准化用于研究和临床使用的功能状态数据来增强精准医学.

科学领域:

  • 医疗信息学 医疗信息学
  • 医疗保健中的人工智能
  • 老年医学 老年医学

背景情况:

  • 全球人口老龄化需要对个性化医学进行精确的功能状态评估.
  • 电子健康记录 (EHR) 包含丰富,但在很大程度上是无结构的患者移动数据.
  • 从临床笔记中标准化移动性信息对于临床应用和研究至关重要.

研究的目的:

  • 调查大型语言模型 (LLM) 在从非结构化的EHR临床笔记中提取和标准化患者移动状态的有效性.
  • 评估不同的LLM提示策略,用于移动数据提取和损伤分类.
  • 评估基于LLM的方法在多个医疗机构的可信度和通用性.

主要方法:

  • 来自三个医疗机构的600份临床笔记的注释,重点关注移动性和损伤表达.
  • 利用开源的Llama 3模型,使用零射击,少数射击和任务分解提示技术.
  • 通过错误分析和患者级准确度和F1分数的计算来评估性能,以获得移动性提取和损伤分类.

主要成果:

  • 移动提取实现了0.952的微平均精度和0.962.96的F1得分.
  • 损伤分类实现了0.912的微平均精度和0.948.94的F1得分.
  • 错误分析表明了临床上合理的推断,即使在模两可的情况下,局部的确定性设置提高了可信度和可概括性.

更多相关视频

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.0K
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

1.6K

相关实验视频

Last Updated: Sep 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

682
Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.0K
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

1.6K

结论:

  • 基于LLM的解决方案可用于从非结构化的EHR数据中提取功能移动状态.
  • 该方法支持将移动数据整合到精准医学计划和临床研究中.
  • 开发的方法表明了跨机构的概括性,并增强了数据隐私和一致性.