Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Time-Series Graph

Time-Series Graph

A time-series graph is a line graph with repeated measurements taken at successive intervals of time. It is also called a time series chart. To construct a time-series graph, one must look at both pieces of a paired data set. The horizontal axis is used to plot the time increments, and the vertical axis is used to plot the values of the variable that one is measuring. By using the axes in this way, each point on the graph will correspond to time and a measured quantity. The points on the graph...

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

Noninvasive Respiratory Support for Adult Patients with Acute Respiratory Failure. An Official American Thoracic Society Clinical Practice Guideline.

American journal of respiratory and critical care medicine·2026

Same author

Development and evaluation of an ontology for non-invasive respiratory support in acute care.

PloS one·2026

Same author

Failure Modes of Time Series Interpretability Algorithms for Critical Care Applications and Potential Solutions.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026

Same author

PHEONA: An Evaluation Framework for Large Language Model-based Approaches to Computational Phenotyping.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026

Same author

SHREC: A framework for advancing next-generation computational phenotyping with large language models.

PLOS digital health·2026

Same author

Standardizing Data Elements for Implementation of ICU Liberation Bundle.

Applied clinical informatics·2026

Search research articles

相关实验视频

Updated: Jan 8, 2026

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

基于时空图神经网络的框架,用于ARDS预测和可解释性.

Shashank Yadav¹, Molly Douglas², Jarrod Mosier²

¹College of Engineering, The University of Arizona, Tucson, 85721, AZ, USA.

Journal of biomedical informatics

|December 12, 2025

概括

此摘要是机器生成的。

图形-spa是一种新的动态空间时间图形神经网络 (STGNN),通过建模不断演变的临床变量相互作用,增强了急性呼吸困扰综合征 (ARDS) 的早期预测. 它的性能优于现有模型,并识别了关键的早期指标,如水平和格拉斯哥昏迷表得分.

关键词:

临床时间序列.图形神经网络图形神经网络模型的解释性模型的解释性签名发现发现签名发现

更多相关视频

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

相关实验视频

Last Updated: Jan 8, 2026

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Modeling the Functional Network for Spatial Navigation in the Human Brain

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

科学领域:

计算生物学和医学计算生物学和医学
医疗保健中的人工智能
时间序列分析和深度学习

背景情况:

传统的深度学习模型在多变量时间序列数据中与长距离的时间依赖性作斗争,阻碍了急性呼吸系统应急综合征 (ARDS) 等关键条件的早期预测.
现有的方法缺乏动态建模临床变量之间不断变化的相互作用的能力,这些变量对于及时和准确的事件预测至关重要.

研究的目的:

引入Graph-spa,一个动态的时空图神经网络 (STGNN) 框架,旨在改善ARDS发病的早期预测.
通过识别ARDS之前的关键临床特征及其时间相互作用来增强模型的解释性.
为在重症监护病房 (ICU) 进行动态临床事件预测提供灵活和可扩展的框架.

主要方法:

开发了Graph-spa,将时间卷积与动态STGNN集成,更新相邻结构以捕捉复杂的时间依赖.
与传统的深度学习模型 (GRU,LSTM,TCN,Transformer) 和三个大型临床数据集 (HiRID,MIMIC-IV,eICU) 的基线STGNN相比,基准图形spa.
采用基于面具的可解释性方法来进行特征时间归因和并发分析,以确定在ARDS之前持续的特征激活.

主要成果:

在内部和外部验证中,Graph-spa在ARDS预测中始终优于所有基线模型,达到更高的AUC F1-MCC分数.
在Graph-spa中的动态相邻机制有效地捕捉了不断变化的特征交互,导致了比基线更多样化的连接模式.
解释性分析强调持续的异常和格拉斯哥昏迷表得分的下降是ARDS的关键早期指标.

结论:

Graph-spa代表了动态临床事件预测的重大进步,为器官衰竭的早期检测提供了一个端到端的方法.
该框架的无模型核心模块 (动态图构造,归因,并发挖掘) 允许广泛适用于各种ICU动态分类和回归任务.
该研究为早期ARDS检测提供了有价值的工具,并证明了发现预测关键事件的亚临床特征的潜力.