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

Multidimensional Sleep Health and Its Association with Traditional Chinese Medicine Constitution Types Among Community-Dwelling Older Adults: A Cross-Sectional Study.

Clinical gerontologist·2026
Same author

Phenylephrine- and Pseudoephedrine-Associated Psychotic Relapse in Stable Schizophrenia on Long-Acting Injectables: A Case Series and Clinical Caution.

Asia-Pacific psychiatry : official journal of the Pacific Rim College of Psychiatrists·2026
Same author

A community-based Daoyin program for health promotion: effects of the Qi and mind harmonizing method on body constitution for the health of older adults.

Frontiers in public health·2026
Same author

Monitoring for early prediction of gram-negative bacteremia using machine learning and hematological data in the emergency department.

Communications medicine·2025
Same author

Establishment of a novel human amniotic epithelial-derived cell line, HAT, for high-yield AAV vector production.

Molecular therapy. Methods & clinical development·2025
Same author

In vitro evaluation of novel composite bioceramic filaments for alveolar bone regeneration.

Journal of dental sciences·2025

相关实验视频

Updated: Sep 13, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K

通过可解释的多分支深度学习来增强基于EEG的精神分裂症诊断.

Yu-Hsin Chang, Yih-Ning Huang, Jing-Lun Chou

    IEEE journal of biomedical and health informatics
    |July 29, 2025
    PubMed
    概括

    在没有客观测试的情况下,诊断精神分裂症是困难的. 一个新的深度学习模型,MBSzEEGNet,使用脑电图 (EEG) 来分类精神分裂症,显示有希望的结果并识别潜在的神经标记.

    科学领域:

    • 神经科学是一个神经科学.
    • 人工智能的人工智能
    • 生物医学工程 生物医学工程

    背景情况:

    • 精神分裂症的诊断依赖于主观的临床评估,缺乏客观的生物标志物.
    • 现有的诊断方法在准确性和早期检测方面面临挑战.

    研究的目的:

    • 开发一种可靠和可解释的深度学习模型,使用脑电图 (EEG) 数据对精神分裂症进行分类.
    • 通过可解释的人工智能技术,识别与精神分裂症相关的潜在神经标记.

    主要方法:

    • 提出了MBSzEEGNet,这是一个多分支深度学习架构,旨在捕捉静态EEG的复杂振荡和空间光谱特征.
    • 在两个独立的精神分裂症EEG数据集上训练并验证了模型.
    • 采用基于突出性的模型解释性方法来确定相关的EEG特征.

    主要成果:

    • 与现有的深度学习模型相比,MBSzEEGNet表现出更高的性能.
    • 实现了高主题分类准确度:在一个数据集上高达85.71%,在另一个数据集上高达75.64%.
    • 确定了特定的EEG频段 (delta,alpha) 和大脑区域 (时间,右头部) 作为潜在的诊断生物标志物.

    结论:

    更多相关视频

    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

    5.7K
    A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy
    08:23

    A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

    Published on: November 13, 2016

    11.3K

    相关实验视频

    Last Updated: Sep 13, 2025

    Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
    09:47

    Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

    Published on: December 15, 2023

    1.3K
    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

    5.7K
    A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy
    08:23

    A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

    Published on: November 13, 2016

    11.3K
    • 集成EEG的可解释的多分支深度学习模型为客观的精神分裂症诊断提供了一个有希望的途径.
    • 这些发现为与精神分裂症相关的神经机制提供了洞察力,并支持开发新型生物标志物.