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

Methods of Documentation VII: EMR01:30

Methods of Documentation VII: EMR

784
Electronic Medical Records (EMRs) primarily center around electronically documenting patients' health information within a single healthcare organization or practice. They contain essential clinical data related to a patient's medical history, diagnoses, medications, treatment plans, lab results, and other pertinent information relevant to the specific encounter or episode of care. EMRs are designed to streamline documentation and workflow processes within individual healthcare...
784

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

Transfer times for patients with extradural and subdural haematomas to neurosurgery in Greater Manchester.

British journal of neurosurgery·2007
Same author

Assessment of middle ear disease in the dog: a comparison of diagnostic imaging modalities.

The Journal of small animal practice·2007
Same author

Desensitized renal transplant recipients show reduced cellular responses to in vitro challenge.

Transplantation proceedings·2006
Same author

Succinate dehydrogenase and fumarate hydratase: linking mitochondrial dysfunction and cancer.

Oncogene·2006
Same author

The DNA sequence and biological annotation of human chromosome 1.

Nature·2006
Same author

Entamoeba histolytica: comparison of the role of receptors and filamentous actin among various endocytic processes.

Experimental parasitology·2006

相关实验视频

Updated: May 16, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

自然语言处理从非结构化的电子健康记录中提取头癌数据

T Young1, J Au Yeung1, K Sambasivan1

  • 1Guy's and St Thomas' NHS Foundation Trust (GSTT), UK; King's College London, UK.

Clinical oncology (Royal College of Radiologists (Great Britain))
|April 6, 2025
PubMed
概括
此摘要是机器生成的。

使用自然语言处理 (NLP) 的人工智能可以有效地从非结构化的电子健康记录中提取有价值的头癌 (HNC) 数据. 有限的培训提高了数据提取的准确性,证明了AI在策划真实世界的临床数据集方面的潜力.

关键词:
人工智能的人工智能是人工智能.数据挖掘是数据挖掘的一个方法.自然语言处理自然语言处理.现实世界的数据.

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

15.7K
TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
09:00

TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients

Published on: April 13, 2021

4.4K

相关实验视频

Last Updated: May 16, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
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

15.7K
TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients
09:00

TBase - an Integrated Electronic Health Record and Research Database for Kidney Transplant Recipients

Published on: April 13, 2021

4.4K

科学领域:

  • 医疗信息学 医疗信息学
  • 医疗保健中的人工智能
  • 瘤学数据管理管理

背景情况:

  • 电子健康记录 (EHR) 通常包含非结构化的患者数据,需要手动修复.
  • 自然语言处理 (NLP) 为快速提取和结构化这些数据提供了一个潜在的解决方案.
  • 头癌 (HNC) 研究可以从来自EHR的丰富数据集中受益.

研究的目的:

  • 评估开源医疗保健NLP工具 (CogStack) 的有效性,用于从非结构化的电子健康记录中提取头癌 (HNC) 患者数据.
  • 在有限的监督培训周期后评估NLP工具的性能.
  • 为了确定一个值策略是否可以提高数据提取精度.

主要方法:

  • 使用CogStack从HNC的患者文件中提取SNOMED-CT概念.
  • 评估初始性能与手动策划的地面真相数据进行了对比.
  • 该模型经历了两轮监督训练,使用注释的临床文件.
  • 实施了值方法以提高精度,并对最终的模型进行了评估,对一个看不见的测试队列进行了评估.
  • 使用F1得分作为主要评估指标.

主要成果:

  • 在训练前,F1分数在19.5%的概念中是无法计算的,这是由于回忆能力低.
  • 经过一个训练周期后,F1分数对所有概念都可计算 (中位数为0.692).
  • 最终的模型在进一步训练后获得了0.708的F1中位数.
  • 测试队列的F1平均得分为0.750,提高到0.778的概念特定值.
  • 在109个SNOMED-CT概念中,有50个符合足够微调的预定义标准.

结论:

  • 像CogStack这样的NLP工具可以在有限的训练下有效地挖掘非结构化癌症数据.
  • 模型性能很好地对未见的测试队列进行了概括,表明了稳定性.
  • 一个特定概念的值策略显著改善了开采性能.
  • 虽然一般有效,但某些概念,如组织病理学术语仍然具有挑战性,难以准确地检索.
  • 经过验证的NLP方法被成功应用,在整个追溯HNC队列中提取50个概念的数据.