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

Language Development01:22

Language Development

810
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
810

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

Multi-site health research integrating complementary data sources: A scoping review of statistical inference methods for vertically partitioned data.

International journal of medical informatics·2026
Same author

Adoption and Use of Social Media in Health Care Among Medical Residents: Cross-Sectional Study.

JMIR medical education·2026
Same author

Challenges of Ontology-Based Concept Normalization for Deep Phenotyping in Rare Skin Diseases.

Studies in health technology and informatics·2026
Same author

From annotation to adaptation: extracting temporal relations in French clinical narratives.

BMC medical research methodology·2026
Same author

Empowering Patients and Clinicians: LLMs in Hypertension Care, A Scoping Review.

Hypertension (Dallas, Tex. : 1979)·2026
Same author

Real-world Effectiveness of Burosumab Across Age Groups: X-linked Hypophosphatemia (XLH) Disease Monitoring Program.

The Journal of clinical endocrinology and metabolism·2026

相关实验视频

Updated: Jan 10, 2026

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

1000

使用大型语言模型从儿科临床报告中提取时间关系.

Judith Jeyafreeda Andrew1,2, Juliette Potier1, Nicolas Garcelon1

  • 1Clinical Bioinformatics Laboratory, INSERM UMR1163, Imagine Institute, Université Paris Cité, Paris, F-75006, France.

JAMIA open
|November 24, 2025
PubMed
概括
此摘要是机器生成的。

大型语言模型 (LLM) 显示出从儿科罕见病报告中提取时间关系的希望. 将任务简化为二进制分类显著提高了性能,使得可以自动创建患者时间表.

关键词:
大型语言模型患者时间表患者时间表罕见的疾病 罕见的疾病时间关系提取时间关系提取.

更多相关视频

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

16.4K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K

相关实验视频

Last Updated: Jan 10, 2026

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

1000
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

16.4K
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

1.3K

科学领域:

  • 临床自然语言处理 临床自然语言处理
  • 医疗保健中的人工智能

背景情况:

  • 自动创建患者时间表对于管理儿科罕见病至关重要.
  • 从临床报告中提取时间关系是一个关键的挑战.

研究的目的:

  • 评估大型语言模型 (LLM) 来从儿科罕见病临床报告中提取时间关系.
  • 通过LLMs实现自动化患者时间线创建.

主要方法:

  • 使用25份临床报告开发了一个时间关系提取框架.
  • 在安全的本地环境中,使用3个LLM实现了几次射击提示.
  • 比较二进制与多类分类方法.

主要成果:

  • 二元分类显著优于多类方法的时间关系提取 (最佳F1:0.70).
  • 米斯特拉22B显示了最强的整体性能,尽管模型优越性有所不同.
  • 复杂的时间关系仍然具有挑战性 (F1:0.03-0.40).

结论:

  • 任务的制定,特别是二进制分类,对临床领域的LLM有效性产生了重大影响.
  • 少数镜头的方法可以安全地从法语儿科文本中提取时间关系.
  • 这种方法为医疗机构提供了可行的解决方案,这些机构有严格的数据治理.