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

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

128
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
128

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

Access toward Fluorenone Derivatives through Solvent-Free Ruthenium Trichloride Mediated [2 + 2 + 2] Cycloadditions.

Organic letters·2016
Same author

Identification of SNPs in a nonmodel macrofungus (<i>Lepista nuda</i>, Basidiomycota) through RAD sequencing.

SpringerPlus·2016
Same author

Mesenchymal stem cells with Sirt1 overexpression suppress breast tumor growth via chemokine-dependent natural killer cells recruitment.

Scientific reports·2016
Same author

RNA Sequencing of Formalin-Fixed, Paraffin-Embedded Specimens for Gene Expression Quantification and Data Mining.

International journal of genomics·2016
Same author

Babao Dan attenuates hepatic fibrosis by inhibiting hepatic stellate cells activation and proliferation via TLR4 signaling pathway.

Oncotarget·2016
Same author

Hepatitis C virus double-stranded RNA is the predominant form in human liver and in interferon-treated cells.

Hepatology (Baltimore, Md.)·2016

相关实验视频

Updated: Jul 3, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

170

一个定制的下方采样机器学习方法用于败血症预测.

Qinhao Wu1, Fei Ye2, Qianqian Gu3

  • 1Apriko Research, Eindhoven, the Netherlands; Department of Mathematics and Computer Science, Eindhoven University of Technology, De Zaale, Eindhoven, 5612 AZ, Noord Brabant, the Netherlands.

International journal of medical informatics
|February 13, 2024
PubMed
概括
此摘要是机器生成的。

这项研究提出了一种使用生命体征和实验室测试的新的败血症预测方法. 该方法结合了下降采样,动态滑动窗口和XGBoost,用于在重症监护室 (ICU) 准确和强大的败血症检测.

关键词:
降低报警的报警方式早期检测 早期检测在重症监护病房的重症监护病房.机器学习是机器学习.败血症预测的预测

更多相关视频

Murine Oropharyngeal Aspiration Model of Ventilator-associated and Hospital-acquired Bacterial Pneumonia
04:32

Murine Oropharyngeal Aspiration Model of Ventilator-associated and Hospital-acquired Bacterial Pneumonia

Published on: June 28, 2018

11.8K
A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats
05:56

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

Published on: February 20, 2021

2.1K

相关实验视频

Last Updated: Jul 3, 2025

A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

170
Murine Oropharyngeal Aspiration Model of Ventilator-associated and Hospital-acquired Bacterial Pneumonia
04:32

Murine Oropharyngeal Aspiration Model of Ventilator-associated and Hospital-acquired Bacterial Pneumonia

Published on: June 28, 2018

11.8K
A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats
05:56

A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

Published on: February 20, 2021

2.1K

科学领域:

  • 关键护理医学 关键护理医学
  • 医疗信息学 医疗信息学
  • 医疗保健中的机器学习

背景情况:

  • 败血症是一种需要及时干预的临界ICU病症.
  • 现有的败血症预测模型面临着警报疲劳和患者安全方面的挑战.
  • 需要使用生命体征和实验室测试的准确,强大和可部署的预测方法.

研究的目的:

  • 为ICU开发一个准确和强大的败血症预测方法.
  • 仅使用生命体征和实验室测试来预测败血症.
  • 通过提高预测特异性来减轻警报疲劳.

主要方法:

  • 针对 XGBoost 模型训练的回顾性数据应用了一个定制的下方采样过程.
  • 一个动态的滑动窗口方法与训练的XGBoost模型集成.
  • 该方法在PhysioNet (PhysioNet-A,PhysioNet-B) 和FHC回顾性数据集上进行了评估.

主要成果:

  • 该方法在PhysioNet-A上获得了80.74%的精度 (77.90%的灵敏度,84.42%的特异性),在PhysioNet-B.上获得了83.95%的精度 (84.82%的灵敏度,82.00%的特异性).
  • 两个PhysioNet数据集的AUC得分为0.89.
  • 在FHC数据集上,获得了92.38%的准确性 (88.37%的灵敏度,95.16%的特异性) 和0.98的AUC得分.

结论:

  • 开发的方法证明了在不同ICU设置中强大而准确的败血症预测能力.
  • 下方采样,动态滑动窗口和XGBoost的组合有效地预测了败血症.
  • 这种局部化和强大的方法可以帮助在不同的ICU环境中诊断败血症.