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

Errors occurring during blood pressure monitoring01:25

Errors occurring during blood pressure monitoring

568
Blood pressure monitoring is a crucial clinical procedure in diagnosing and managing various cardiovascular conditions. Despite its significance, the accuracy of blood pressure measurements can be compromised by multiple factors, potentially leading to either falsely high or low readings. These inaccuracies are critical as they can significantly impact patient care. So, it is vital to understand these challenges deeply and adopt strategic approaches to minimize errors.
Several factors...
568

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

Reply to Shankar regarding 'Antenatal lifestyle interventions to reduce gestational weight gain: Where should we start and how much will it cost?'

Public health·2026
Same author

Lipidomic profiling reveals a distinct lipidomic signature of early gestational diabetes.

Communications medicine·2026
Same author

Externally validated risk prediction models for gestational diabetes mellitus: A systematic review and meta-analysis.

Acta obstetricia et gynecologica Scandinavica·2026
Same author

Association Between Mental Health of Patients with Work-Related Injury and Their Compensation Claim Status: Exploratory Findings from the IMPRovE Trial.

Journal of occupational rehabilitation·2026
Same author

Implementing systems- and organisational-level change to advance gender equality in healthcare leadership: a mixed-methods implementation protocol.

Implementation science communications·2026
Same author

Pharmaceutical policy and off-label prescribing in pregnancy: A population-based historical cohort study analyzing inequality in access to antiemetics within Australia's Pharmaceutical Benefits Scheme.

Acta obstetricia et gynecologica Scandinavica·2026

相关实验视频

Updated: May 13, 2025

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

7.0K

机器学习模型的时间验证,以使用例行收集的母亲特征来预测妊娠前:一个验证研究.

Sofonyas Abebaw Tiruneh1, Daniel Lorber Rolnik2, Helena Teede1

  • 1Monash Centre for Health Research and Implementation, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia.

Computers in biology and medicine
|April 14, 2025
PubMed
概括

后勤回归和XGBoost模型显示了先兆子 (PE) 的稳定预测性能,但机器学习模型都没有超过后勤回归. 逻辑回归被推用于例行实践,作为PE的初始查工具.

关键词:
后勤回归的逻辑回归机器学习是机器学习.孕产妇产前症 孕产妇产前症预测 预测 预测随机的森林随机的森林在XGBoost中使用.

更多相关视频

Assessment of Maternal Vascular Remodeling During Pregnancy in the Mouse Uterus
06:55

Assessment of Maternal Vascular Remodeling During Pregnancy in the Mouse Uterus

Published on: December 5, 2015

13.2K
An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.0K

相关实验视频

Last Updated: May 13, 2025

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

7.0K
Assessment of Maternal Vascular Remodeling During Pregnancy in the Mouse Uterus
06:55

Assessment of Maternal Vascular Remodeling During Pregnancy in the Mouse Uterus

Published on: December 5, 2015

13.2K
An R-Based Landscape Validation of a Competing Risk Model
05:37

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

2.0K

科学领域:

  • 产科和妇科 产科和妇科
  • 医疗信息学 医疗信息学
  • 公共卫生 公共卫生

背景情况:

  • 孕前 (PE) 是全球主要的孕产妇和新生儿死亡原因之一.
  • 早期检测和干预对于减少PE并发症至关重要.
  • 现有的风险预测模型需要严格的验证才能用于临床应用.

研究的目的:

  • 暂时验证三种现有的孕前 (PE) 预测模型:两个机器学习 (ML) 模型 (XGBoost,随机森林) 和一个后勤回归模型.
  • 为了比较这些验证模型的预测性能.
  • 评估PE预测模型的临床实用性.

主要方法:

  • 使用澳大利亚墨尔本东南部 (2021年7月至2022年12月) 的产前数据对XGBoost,随机森林和后勤回归模型进行时间验证.
  • 使用接收器操作特征曲线 (AUC) 下的面积和使用斜率进行校准来评估歧视.
  • 通过引导和评估临床净益处来比较AUC.

主要成果:

  • 时间数据集包括12,549个怀孕,PE发病率为3.43%.
  • XGBoost (AUC 0.75) 和后勤回归 (AUC 0.76) 显示出类似的歧视;随机森林的AUC为0.71.
  • 后勤回归显示出优异的校准 (斜率1.02);XGBoost显示出更差的校准 (斜率1.15).
  • 时间验证后勤回归和XGBoost模型保持了稳定的歧视,优于随机森林.
  • 在特定风险值下,物流回归和XGBoost模型提供了比特定风险值的违约策略更好的临床净益.

结论:

  • 后勤回归和XGBoost模型在预兆前的时间验证后显示出稳定的预测性能.
  • 机器学习模型在PE预测中都没有明显优于逻辑回归模型.
  • 后勤回归是一种可行的选择,用于在两阶段的PE检测方法中进行例行,第一阶段的查,确定女性进行进一步评估.