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

Flow Sheet01:17

Flow Sheet

1.6K
Flowsheets are valuable tools in nursing documentation. They enable healthcare professionals to efficiently record and monitor various patient assessments and measurements in a consolidated format.
Here's a closer look at the examples of flowsheets commonly used by nurses:
Graphic Sheet Documentation:
1.6K

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

Size-dependent activation of ammonia borane on copper clusters (Cu <sub><i>x</i></sub> , <i>x</i> = 2-10): a DFT study of bonding, electronic structure, and hydrogen evolution.

RSC advances·2026
Same author

Tissue expression profiles of miR-6809 and miR-4753 in triple-negative breast cancer: Novel biomarkers of early detection and staging.

Biomarkers : biochemical indicators of exposure, response, and susceptibility to chemicals·2026
Same author

Towards Conversational AI for Disease Management.

Nature·2026
Same author

Development and evaluation of a propolis, tea tree oil, and jojoba oil nanoemulgel with enhanced antioxidant, anti-inflammatory, and wound-healing activities.

Scientific reports·2026
Same author

Accelerating scientific discovery with Co-Scientist.

Nature·2026
Same author

Advancing conversational diagnostic AI with multimodal reasoning.

Nature medicine·2026

相关实验视频

Updated: Jul 2, 2025

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

12.4K

通过使用工作流笔记进行可靠的发作发作检测.

Khaled Saab1, Siyi Tang2, Mohamed Taha3

  • 1Department of Electrical Engineering, Stanford University, Stanford, CA, USA. ksaab@stanford.edu.

NPJ digital medicine
|February 22, 2024
PubMed
概括
此摘要是机器生成的。

在医疗保健中利用人工智能 (AI) 的常规临床工作流程笔记显著提高了从电脑电图 (EEG) 数据中发作发作的检测. 一个新的多标签人工智能模型提高了稳定性和临床实用性,解决了子组性能差异并减少了假阳性.

更多相关视频

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits
10:25

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits

Published on: March 27, 2021

6.0K
Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury
09:16

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Published on: June 21, 2019

25.6K

相关实验视频

Last Updated: Jul 2, 2025

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

12.4K
Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits
10:25

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits

Published on: March 27, 2021

6.0K
Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury
09:16

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Published on: June 21, 2019

25.6K

科学领域:

  • 医疗保健中的人工智能
  • 医疗信号处理 医疗信号处理
  • 机器学习用于临床应用.

背景情况:

  • 可信度是部署医疗保健人工智能的关键障碍,跨子组的模型稳定性是关键问题.
  • 目前用于发作检测的AI模型通常依赖于非因果特征,导致隐藏子组的性能下降.
  • 包含各种事件描述的常规临床工作流记录,为人工智能模型培训提供了有价值的,未充分利用的数据源.

研究的目的:

  • 提高AI模型的可靠性和稳定性,以使用临床工作流程笔记检测发作.
  • 通过扩展培训数据和采用多标签分类方法来评估性能增长.
  • 解决子组绩效差异,减少脑电图 (EEG) 分析中的错误阳性率.

主要方法:

  • 使用了68,920小时的EEG数据,并附有常规临床工作流程注释,包括和非事件描述.
  • 开发并将二进制发作发作检测模型与分类26个额外属性 (例如,文物) 的多标签模型进行比较.
  • 在各种子组和条件中使用接收器操作特征 (AUROC) 曲线下的面积和假阳性率 (FPR) 评估模型性能.

主要成果:

  • 将训练数据与工作流程笔记进行缩放,与较小的黄金标准数据集相比,提高了12.3个AUROC点的发作发作检测.
  • 最初的二进制模型显示了各子组的表现差距 (高达6.5个AUROC点) 和非形异常的更高的FPR (+19个FPR点).
  • 多标签模型提高了整体表现 (+5.9 AUROC点),改善了子组表现 (高达 +8.3 AUROC点),并减少了非形异常的错误阳性 (8 FPR点).

结论:

  • 临床工作流程笔记是培养强大和可信赖的医疗保健人工智能的强大资源,显著改善了发作发作的检测.
  • 多标签方法有效地解决了模型偏差,并提高了跨不同患者子组和EEG信号特征的性能.
  • 开发的多标签模型证明了临床效益的两倍改善,减少了每24小时EEG错误阳性.