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

115
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:
115

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

Summary of best evidence for drainage tube management to prevent surgical site infections.

BMC surgery·2026
Same author

Di-2-ethylhexylphthalate-induced miR155-5P promotes placental ferroptosis.

International journal of biological macromolecules·2026
Same author

Mid-infrared to ultraviolet efficient multiphoton frequency upconversion in NbOI<sub>2</sub> crystals.

Nature communications·2026
Same author

AMBP gene activation promotes cholangiocarcinoma progression through the WNT/β-catenin signaling pathway: Regulatory effect of polysaccharides from Auricularia auricula-judae.

Medicine·2026
Same author

PRMT3-mediated FOXO1 arginine methylation exacerbates oxidative stress-induced decidualization defects in the eutopic endometrium of endometriosis.

Cellular and molecular life sciences : CMLS·2025
Same author

A simple and standardized method supports efficient derivation of clinical-grade human embryonic stem cells under feeder- and xeno-free conditions.

Stem cell research & therapy·2025

相关实验视频

Updated: Jun 17, 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

157

基于可解释机器学习方法的早期败血症死亡率预测模型:开发和验证研究.

Yiping Wang1, Zhihong Gao2, Yang Zhang2

  • 1Department of Emergency, The First Affiliated Hospital of WenZhou Medical University, Wenzhou, 325000, China.

Internal and emergency medicine
|August 14, 2024
PubMed
概括
此摘要是机器生成的。

机器学习模型,特别是XGBoost,使用临床数据有效预测败血症死亡率. 这种方法超越了传统的评分系统,为各种医疗保健环境中早期风险评估提供了经过验证的工具.

关键词:
人工智能的人工智能是人工智能.机器学习 机器学习死亡率预测模型的模型.败血症 这是一种败血症.败血症的冲击是一个令人震惊的结果.在XGBoost中使用.

更多相关视频

Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis
05:28

Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis

Published on: December 9, 2022

3.4K
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

2.0K

相关实验视频

Last Updated: Jun 17, 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

157
Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis
05:28

Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis

Published on: December 9, 2022

3.4K
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

2.0K

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:

  • 败血症是一种危及生命的疾病,其特点是免疫反应对感染的失调,导致高死亡率.
  • 早期预测败血症的结果对于及时干预和改善患者管理至关重要.
  • 虽然机器学习 (ML) 在医学研究中表现有前途,但使用真实世界数据集 (如MIMIC-IV) 来预测败血症的本地验证是有限的.

研究的目的:

  • 开发和验证基于机器学习的预后模型,用于预测与败血症相关的死亡率.
  • 利用密集护理IV (MIMIC-IV) 数据库的医疗信息中心进行模型开发和内部验证.
  • 在中国的教学医院环境中对模型的性能进行外部验证.

主要方法:

  • 利用了来自MIMIC-IV数据库的患者数据,分为培训和内部验证集.
  • 开发并比较了四种机器学习模型:逻辑回归 (LR),支持向量机 (SVM),深度神经网络 (DNN) 和极端梯度增强 (XGBoost).
  • 采用沙普利增量解释来解释模型的可解释性,并使用接收器运行特征曲线 (AUROC) 下的面积来评估预测性能.

主要成果:

  • 该研究包括来自MIMIC-IV的27,134名败血症患者和来自中国医院的487名患者,具有52个选定的临床指标.
  • 所有开发的ML模型都在预测败血症死亡率方面表现出强大的区分能力.
  • XGBoost实现了最高的预测性能,内部AUROC为0.873和外部AUROC为0.844,超过了LR,SVM,DNN,并建立了临床评分系统.

结论:

  • 成功开发了一种可解释的机器学习模型,用于预测败血症死亡风险.
  • 机器学习算法,特别是XGBoost,在预测与败血症相关的死亡方面显著超过了传统的临床评分.
  • 这些发现在中国一家教学医院得到了验证,证实了ML方法对败血症结果预测的概括性和有效性.