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

Differential COVID-19 Outcomes Across Lysosomal Disorders.

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

Bipolar Disorder Incidence During Pregnancy and in the Postpartum Period: A Population-Based Study.

Bipolar disorders·2026
Same author

Genetic architecture of postpartum psychosis: from common to rare genetic variation.

Molecular psychiatry·2026
Same author

Psychiatric History and Postpartum Depression: The Mediating Role of Obstetric Complications.

Acta psychiatrica Scandinavica·2026
Same author

The Cell Ontology in the age of single-cell omics.

Scientific data·2026
Same author

Oligonucleotide Ligation Assay (OLA)-Simple: Field Implementation, Usability, and Performance of a near Point-of-Care HIV Drug Resistance Assay in Kenya.

Laboratories·2026

相关实验视频

Updated: Jan 10, 2026

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
19:15

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Published on: August 25, 2014

87.5K

机器学习优化围产期抑郁查:最大影响,最小负担.

Eric Hurwitz1, Caroline Shell2, Kritika Chugh3

  • 1Department of Genetics, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States.

medRxiv : the preprint server for health sciences
|November 24, 2025
PubMed
概括
此摘要是机器生成的。

机器学习只使用两个爱丁堡产后抑郁量表 (EPDS) 问题,就能准确预测产后抑郁症. 这种简短的查工具可以改善对母亲心理健康状况的识别.

更多相关视频

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.9K
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.5K

相关实验视频

Last Updated: Jan 10, 2026

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale
19:15

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Published on: August 25, 2014

87.5K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.9K
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.5K

科学领域:

  • 围产期心理健康问题
  • 临床信息学是一种临床信息学.
  • 机器学习应用程序 机器学习应用程序

背景情况:

  • 围产期抑郁症影响了很大一部分孕妇和产后妇女,在COVID-19后的流行率增加.
  • 迅速识别受影响的妇女是临床优先事项.
  • 现有的查工具,如爱丁堡产后抑郁量表 (EPDS) 是漫长的,在繁忙的临床环境中提出了挑战.

研究的目的:

  • 开发和验证一种机器学习 (ML) 框架,用于使用缩短问题子集预测完整的10项EPDS分数.
  • 为了优化查的简短性,同时保持对围产期抑郁症的预测准确性.

主要方法:

  • 利用国家临床队列协作 (N3C) 数据 (n=22,924) 训练ML模型,从2-5项组合预测完整的EPDS分数.
  • 在多样化的队列中验证模型,包括产后妇女 (n=7,750) 和外部怀孕人口 (n=1,217).
  • 使用PHQ-9 (n=398,606) 评估了概括性,并通过决策曲线分析评估了临床效用.

主要成果:

  • 最佳的2个问题EPDS子集 (Q4+Q8,Q5+Q8) 实现了高预测精度 (R2=0.70).
  • 二元分类模型表现出强的性能 (灵敏度为0.68-0.72,特异性为0.98-0.99).
  • ML框架在验证队列中显示出强大的概括性,并在临床实用性方面超过了传统的评分方法.

结论:

  • 仅使用两个EPDS问题的机器学习框架可以保持与全10项级别可比的预测准确性.
  • 这种简化方法显著降低了患者和临床医生的评估负担.
  • 实施这种ML驱动的查可以提高临床实践中围产期抑郁症的识别,每年可能达到数百万女性.