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

Obsessive-Compulsive Disorder01:28

Obsessive-Compulsive Disorder

28
Obsessive-compulsive disorder (OCD) is a mental health condition characterized by recurrent obsessions, compulsions, or both, which consume significant time and interfere with daily functioning. Obsessions involve persistent, intrusive, and unwanted thoughts, images, or urges that evoke anxiety. Common examples include irrational fears of contamination or harm. Compulsions are repetitive behaviors or mental acts performed to reduce the anxiety caused by obsessions. For instance, individuals...
28

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

α<sub>2</sub>-Adrenergic receptor modulates 5-HT<sub>2A</sub>-mediated behavioral effects of MDMA and psilocybin in mice.

Molecular psychiatry·2026
Same author

Excessive Switching in OCD and Paranoia Arises From Different Deficits in Belief-Updating.

Computational psychiatry (Cambridge, Mass.)·2026
Same author

Maintenance of symptoms and weight-related gains following residential eating disorder treatment at discharge and one-year follow-up.

Eating disorders·2026
Same author

Regional, functional and transcriptomic decoding of multidimensional brain structure alterations in obsessive-compulsive disorder.

Nature communications·2026
Same author

Toward trustworthy clinical AI for obsessive-compulsive disorder: reliability, generalizability, and interpretability of a transformer model across the ENIGMA-OCD consortium.

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

Human claustrum neurons encode uncertainty and prediction errors during aversive learning.

bioRxiv : the preprint server for biology·2026

相关实验视频

Updated: May 20, 2025

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
06:40

Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

Published on: June 15, 2018

10.1K

使用卷积神经网络从静止状态EEG分类强迫症:一个试点研究

Brian A Zaboski, Sarah Kathryn Fineberg, Patrick D Skosnik

    medRxiv : the preprint server for health sciences
    |May 19, 2025
    PubMed
    概括

    卷积神经网络 (CNN) 有效地区分了强迫症 (OCD) 与使用静止电脑图 (EEG) 数据的对照. 深度学习显示了强迫症诊断的前景,教育水平可能会提高准确性.

    科学领域:

    • 神经科学是一个神经科学.
    • 计算精神病学是一种计算精神病学.
    • 机器学习 机器学习

    背景情况:

    • 使用大脑数据对强迫症 (OCD) 进行分类是具有挑战性的.
    • 静止电脑电图 (EEG) 是一种非侵入性,负担得起的神经成像技术.
    • 传统的机器学习方法在预测来自EEG的强迫症方面存在局限性.

    研究的目的:

    • 研究卷积神经网络 (CNN) 的有效性,用于使用最小处理的EEG时间频率表示来对强迫症进行分类.
    • 为了比较CNN的性能与传统的机器学习方法,如支持向量机 (SVM).
    • 探索多式联络融合对分类准确性的影响,包括临床和人口统计数据.

    主要方法:

    • 收集了20名参与者的静止状态EEG数据 (10名强迫症患者,10名健康对照).
    • 使用莫莱特波段将EEG段转换为时间频率表示.
    • 应用了2D CNN分类器,并进行了离开一个主体的交叉验证,并将其与训练在光谱带功率特征上的SVM进行了比较.

    主要成果:

    • 在CNN实现82.0%的准确性 (AUC:0.86),显著超过SVM基线 (49.0%的准确性,AUC:0.45).
    • 大多数临床变量并没有提高单独超出EEG数据的分类准确度 (80.0%准确度).

    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

    5.6K
    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
    06:37

    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

    Published on: July 14, 2023

    794

    相关实验视频

    Last Updated: May 20, 2025

    Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography
    06:40

    Microstate and Omega Complexity Analyses of the Resting-state Electroencephalography

    Published on: June 15, 2018

    10.1K
    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

    5.6K
    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
    06:37

    Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

    Published on: July 14, 2023

    794
  • 纳入教育水平提高了分类性能,达到85.0%的准确率 (AUC:0.89).

    • 结论:

    • 应用于静止状态EEG的CNN显示了诊断强迫症的巨大潜力,超过了传统方法.
    • 深度学习技术对精神病学应用有前途,尽管样本大小有限.
    • 教育水平可以作为强迫症分类的有价值的补充特征,在更大的队列中值得进一步研究.