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

5E management protocol for enhanced recovery after total knee arthroplasty: stratified RCT.

Journal of orthopaedic surgery and research·2026
Same author

Large language models instantiate evolutionarily robust strategies of cooperation.

PNAS nexus·2026
Same author

Ocean acidification exacerbates UVR-induced inhibition of photosystem II and I in Corallina officinalis.

Journal of photochemistry and photobiology. B, Biology·2026
Same author

Bivalent impact of social networks on overarming: Insights on the alignment between social and individual interests.

Science advances·2026
Same author

Direct Photocatalytic Conversion of Methane to Acetone Through a Synergistic Ta Single-Atom/Ga Lewis Acid Catalyst.

Angewandte Chemie (International ed. in English)·2026
Same author

Opioid Receptor Independent Effects of Opioid Peptides.

Current reviews in clinical and experimental pharmacology·2026

相关实验视频

Updated: May 20, 2025

Monitoring Lung Function with Electrical Impedance Tomography in the Intensive Care Unit
05:56

Monitoring Lung Function with Electrical Impedance Tomography in the Intensive Care Unit

Published on: September 6, 2024

1.4K

一个可解释的人工智能框架,用于预测断奶结果,使用电阻断层扫描仪的特征.

Pu Wang1, Teng-Hui Chen2, Mei-Yun Chang2

  • 1Department of Biomedical Engineering, Fourth Military Medical University, Xi'an 710032, China; Tianjin International Joint Research Centre for Neural Engineering, and Tianjin Key Laboratory of Brain Science and Neural Engineering, Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China.

Computer methods and programs in biomedicine
|May 8, 2025
PubMed
概括

本研究引入了一种机器学习模型,使用电阻断层扫描 (EIT) 来预测长期机械通风 (PMV) 断奶的结果. 基于EIT的模型提供了一种独立于呼吸机的方法,以改善临床决策.

关键词:
电阻断层扫描仪电阻断层扫描仪机器学习是机器学习.模型解释模型解释结果预测结果预测.长时间的机械通风.

更多相关视频

Noninvasive EEG Recordings from Freely Moving Piglets
04:05

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

7.2K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

10.8K

相关实验视频

Last Updated: May 20, 2025

Monitoring Lung Function with Electrical Impedance Tomography in the Intensive Care Unit
05:56

Monitoring Lung Function with Electrical Impedance Tomography in the Intensive Care Unit

Published on: September 6, 2024

1.4K
Noninvasive EEG Recordings from Freely Moving Piglets
04:05

Noninvasive EEG Recordings from Freely Moving Piglets

Published on: July 13, 2018

7.2K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

10.8K

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
  • 生物医学工程 生物医学工程

背景情况:

  • 长时间的机械通风 (PMV) 带来了风险,包括与呼吸机相关的肺炎和腹膜损伤,可能会使断奶复杂化.
  • 目前的断奶结果预测方法可能由于依赖于通风机数据而受到限制.

研究的目的:

  • 开发和验证一种机器学习 (ML) 框架,用于预测PMV患者的断奶结果.
  • 使用电阻断层扫描 (EIT) 数据,独立于通风器参数,以提高预测准确度.
  • 提高ML模型在临床环境中的可解释性.

主要方法:

  • 分析了58名PMV患者的EIT数据.
  • 用于ML模型开发的特征提取,标准化 (min-max) 和选择 (Boruta).
  • 数据平衡 (SMOTE) 和10个ML算法的比较,通过Leave-One-Out交叉验证进行超参数调整.
  • 使用SHAP和LIME方法进行模型解释性.

主要成果:

  • 结合SMOTE平衡的ML模型显示,与不平衡数据相比,AUC,特异性和精度 (p < 0.05) 显著改善.
  • 最优的模型XGBoost实现了高性能指标:AUC=0.862,灵敏度=0.923,特异性=0.800,精度=0.889,精度=0.923,f-score=0.923.
  • 决策曲线分析和校准曲线证实了该模型的临床通用性和可靠性.
  • SHAP和LIME提供了全球和个人样本级模型解释.

结论:

  • 基于EIT的断奶结果预测模型提供了无呼吸器解决方案,在各种临床场景中扩大了适用性.
  • 拟议的全面的ML框架,增强了SHAP和LIME,显著提高了断奶结果预测的解释性和临床实用性.