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

Joint Impact of Triglyceride-glucose Index and Free Fatty Acid Levels on Cardiovascular Outcomes in Overweight or Obese Patients with Coronary Artery Disease - A Large Multicenter Prospective Study.

Biomedical and environmental sciences : BES·2026
Same author

Parallel anterior cingulate cortex pathways underlie dissociable social and attentional outputs.

Science advances·2026
Same author

Artificial Intelligence in Cardiac Remodeling Assessment: From Models to Clinical Integration.

Journal of visualized experiments : JoVE·2026
Same author

iRGD-modified peptide-drug conjugate improves brain delivery and antitumor efficacy in glioblastoma.

European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences·2026
Same author

Ethanol Infusion Into the Vein of Marshall for Atrial Fibrillation: Clinical Efficacy and Technical Limitations.

Clinical cardiology·2026
Same author

PD-1/PD-L1 immune checkpoint inhibitors in Hodgkin lymphoma: A meta- and network meta-analysis.

Translational oncology·2026

相关实验视频

Updated: Jun 10, 2025

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis
08:46

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis

Published on: August 12, 2020

6.3K

一个时间序列算法来预测新生儿死性肠球炎手术.

Cheng Cui1, Ling Qiu2, Ling Li3

  • 1Neonatal Diagnosis and Treatment Center of Children's Hospital of Chongqing Medical University, National Clinical Research Center for Child Health and Disorders, Ministry of Education Key Laboratory of Child Development and Disorders, Chongqing Key Laboratory of Child Rare Diseases in Infection and Immunity, Chongqing, 400014, China.

BMC medical informatics and decision making
|October 18, 2024
PubMed
概括

这项研究开发了使用长期短期记忆网络 (LSTM) 和焦点丧失 (FL) 的新生儿死性肠球炎 (NEC) 的预测模型. 该模型准确地预测了NEC婴儿手术干预的需要,使得早期治疗成为可能.

关键词:
辅助诊断是一种辅助诊断.深度学习是一种深度学习.长期短期内存网络中的长期内存.新生儿死性肠球炎新生儿预测性手术是一种预测性手术.

更多相关视频

Author Spotlight: Enhancing Understanding and Treatment Strategies with the NEC-on-a-Chip Model
06:51

Author Spotlight: Enhancing Understanding and Treatment Strategies with the NEC-on-a-Chip Model

Published on: July 28, 2023

1.2K
Author Spotlight: Simulating Pediatric Cardiac Surgery Using a Neonatal Piglet Model
04:55

Author Spotlight: Simulating Pediatric Cardiac Surgery Using a Neonatal Piglet Model

Published on: May 26, 2023

724

相关实验视频

Last Updated: Jun 10, 2025

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis
08:46

A Neonatal Imaging Model of Gram-Negative Bacterial Sepsis

Published on: August 12, 2020

6.3K
Author Spotlight: Enhancing Understanding and Treatment Strategies with the NEC-on-a-Chip Model
06:51

Author Spotlight: Enhancing Understanding and Treatment Strategies with the NEC-on-a-Chip Model

Published on: July 28, 2023

1.2K
Author Spotlight: Simulating Pediatric Cardiac Surgery Using a Neonatal Piglet Model
04:55

Author Spotlight: Simulating Pediatric Cardiac Surgery Using a Neonatal Piglet Model

Published on: May 26, 2023

724

科学领域:

  • 新生儿科学 新生儿科学
  • 人工智能在医学中的应用
  • 手术预测手术预测

背景情况:

  • 新生儿死性肠球炎 (NEC) 在确定最佳手术时间方面存在挑战.
  • 早期识别患有严重NEC (贝尔IIB+) 风险的婴儿对于及时干预至关重要.

研究的目的:

  • 开发一个利用长期短期记忆 (LSTM) 网络与焦点损失 (FL) 的预测模型.
  • 为了识别患有贝尔IIB+NEC高风险的婴儿,并提供早期手术警告.

主要方法:

  • 利用了791名被诊断为NEC的新生儿的数据,包括35个特征.
  • 采用五重交叉验证方法培训和测试LSTM模型.
  • 应用焦点损失 (FL) 来解决类不平衡并捕捉时间关系.

主要成果:

  • 该模型在提前一天预测手术风险方面取得了很高的表现 (精度:0.913,回忆:0.841,F1:0.874).
  • 提前两天的预测也显示出强的表现 (精度:0.905,回忆:0.815,F1:0.857).
  • 该模型在1天 (0.917) 和2天 (0.905) 预测中都显示出高平均精度 (AP).

结论:

  • 患有FL的LSTM模型准确地预测了NEC患者在1 - 2天前需要进行外科手术的需要.
  • 这种预测能力可以显著改善临床决策和增强婴儿的结果.
  • 模型所促进的及时外科预警,有望更好地管理严重的NEC病例.