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

Seizures: Classification01:13

Seizures: Classification

1.9K
Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:
1.9K

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

Historical Perspectives in Medicine using a Large Language Model: Emulating an 18th Century Physician.

medRxiv : the preprint server for health sciences·2026
Same author

Impaired autobiographical remembering and future thinking in temporal lobe epilepsy.

Epilepsy & behavior : E&B·2026
Same author

Global Socioeconomic Context and Brain Ageing in Epilepsy: an ENIGMA-Epilepsy study.

medRxiv : the preprint server for health sciences·2026
Same author

A comprehensive survey of AI agents in healthcare.

Journal of biomedical informatics·2026
Same author

Intracranial electroencephalographic connectivity analysis to localize epileptogenic networks: Systematic review and meta-analysis from ILAE Epilepsy Surgery Networks Task Force.

Epilepsia·2026
Same author

Higher-order Interaction Matters: Modeling Epidemics via Dynamic Hypergraph Neural Networks.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing·2026

相关实验视频

Updated: Feb 28, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

6.1K

抓获Former:一个多尺度的变压器从RNS衍生的生物标志物抓获风险预测.

Tianning Feng1, Juntong Ni2, Wei Jin3

  • 1School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA, tfeng24@seas.upenn.edu.

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing
|February 27, 2026
PubMed
概括

新的人工智能模型SeizureFormer使用响应神经刺激数据提前1-14天预测发作. 这一突破通过高准确度预测发作风险,提供了个性化,主动的治疗.

更多相关视频

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
08:20

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Published on: June 6, 2015

16.0K
Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

13.0K

相关实验视频

Last Updated: Feb 28, 2026

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

6.1K
Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings
08:20

Brain Source Imaging in Preclinical Rat Models of Focal Epilepsy using High-Resolution EEG Recordings

Published on: June 6, 2015

16.0K
Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

13.0K

科学领域:

  • 生物医学工程 生物医学工程
  • 人工智能在医学中的应用
  • 神经学 神经学

背景情况:

  • 预测发作仍然具有挑战性,特别是在长期预测方面.
  • 现有的模型通常依赖于原始脑电图 (EEG) 数据,这限制了它们在长期预测方面的有效性.
  • 响应神经刺激 (RNS) 系统产生有价值的生物标志物,这些生物标志物有可能改善预测.

研究的目的:

  • 开发和评估SeizureFormer,这是一个基于变压器的新型模型,用于长期预测发作风险 (1-14天).
  • 利用来自RNS系统的结构化生物标志物,特别是间接性活动 (IEA) 和长期发作 (LE),以提高预测准确性.
  • 将SeizureFormer的性能与现有的统计,经典机器学习和深度学习模型进行比较.

主要方法:

  • 开发了基于变压器的深度学习模型SeizureFormer,集成了多规模的CNN补丁嵌入,交叉变量时间卷积和挤压和激发注意力.
  • 使用从RNS系统中提取的结构化生物标志物 (IEA和LE) 进行模型培训和测试.
  • 在5名患者中评估了该模型,预测窗口范围为1至14天.

主要成果:

  • 在患者和预测窗口中,SeizureFormer实现了最先进的性能,平均ROC AUC为79.44%,平均PR AUC为76.29%.
  • 与基线模型相比,该模型显示出更高的概括性,特别是在阶级不平衡的情况下.
  • 在1至14天前成功预测了发作相关事件.

结论:

  • 在使用RNS生物标志物的长期发作风险预测中,SeizureFormer提供了显著的进步.
  • 该模型能够捕捉短期波动和长期发作周期的能力提高了预测准确度.
  • 这项技术使可操作的多天预测成为可能,为管理的个性化和主动干预铺平了道路.