Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Bridging Perceptions and Practice: HEOCs Leaders' Insights on the SHEPA Tool for Hospital Preparedness in Saudi Arabia.

Disaster medicine and public health preparedness·2026

Same author

Factors Associated with Childhood Vaccination in Sub-Saharan African Countries Experiencing Armed Conflicts: A Scoping Review.

Journal of epidemiology and global health·2026

Same author

Return to work after neurostimulation for chronic pain: a systematic review and meta-analysis.

Pain medicine (Malden, Mass.)·2026

Same author

Equipoise in Neurosurgical Trials: Ethical Considerations and Challenges for Trial Conduct.

Neurosurgery·2026

Same author

Hospital Medical Surge Capacity Assessment and Planning Tools for Disaster Response: A Systematic Review and Meta-analysis.

Disaster medicine and public health preparedness·2026

Same author

Enhancing reporting of process evaluations in health care: a preliminary checklist for reporting process evaluations, a Delphi study.

Journal of clinical epidemiology·2026

Search research articles

相关实验视频

Updated: Jul 17, 2025

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Published on: May 27, 2022

使用机器学习和行政数据预测创伤性脑损伤后返回工作.

Helena Van Deynse¹, Wilfried Cools², Viktor-Jan De Deken¹

¹Interuniversity Centre for Health Economics Research (I-CHER), Vrije Universiteit Brussel, Brussels, Belgium.

International journal of medical informatics

|September 1, 2023

概括

使用行政数据的机器学习模型可以预测创伤性脑损伤 (TBI) 后返回工作的准确率为83%. 伤害前的就业是关键预测因素,尽管数据限制需要进一步的信息来改善患者的预后.

更多相关视频

Development of an Uncomplicated Mild Traumatic Brain Injury Model Modified by Weight-Drop Method and Evidenced by Magnetic Resonance Imaging

Development of an Uncomplicated Mild Traumatic Brain Injury Model Modified by Weight-Drop Method and Evidenced by Magnetic Resonance Imaging

Published on: April 11, 2025

An Investigation of the Effects of Sports-related Concussion in Youth Using Functional Magnetic Resonance Imaging and the Head Impact Telemetry System

An Investigation of the Effects of Sports-related Concussion in Youth Using Functional Magnetic Resonance Imaging and the Head Impact Telemetry System

Published on: January 12, 2011

相关实验视频

Last Updated: Jul 17, 2025

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Systems Analysis of the Neuroinflammatory and Hemodynamic Response to Traumatic Brain Injury

Published on: May 27, 2022

Development of an Uncomplicated Mild Traumatic Brain Injury Model Modified by Weight-Drop Method and Evidenced by Magnetic Resonance Imaging

Development of an Uncomplicated Mild Traumatic Brain Injury Model Modified by Weight-Drop Method and Evidenced by Magnetic Resonance Imaging

Published on: April 11, 2025

An Investigation of the Effects of Sports-related Concussion in Youth Using Functional Magnetic Resonance Imaging and the Head Impact Telemetry System

An Investigation of the Effects of Sports-related Concussion in Youth Using Functional Magnetic Resonance Imaging and the Head Impact Telemetry System

Published on: January 12, 2011

科学领域:

医疗信息学医疗信息学
康复医学康复医学康复医学
公共卫生公共卫生

背景情况:

在创伤性脑损伤 (TBI) 后,准确的患者特异性预测对于临床实践和政策至关重要.
应用于大型行政数据集的机器学习 (ML) 为开发预测模型提供了一个有希望的途径.

研究的目的:

通过使用行政数据,评估预测TBI后一年返回工作的准确性.
探索模型性能和特征重要性在区分轻度和中度至重度TBI时如何变化.

主要方法:

利用基于人口的数据集,将2016年住院的TBI患者的比利时出院,索赔和社会保障数据结合起来.
采用了三个ML算法:弹性净物流回归,随机森林和梯度增强.
使用精度,灵敏度,特异性和ROC AUC.评估模型性能.

主要成果:

所有的算法都产生了相似的结果,实现了83%的准确性 (ROC AUC85%),用于雇佣/失业二元分类.
一个多类的就业结果的操作化达到76%的准确性 (ROC AUC 82%).
对轻度与中度至重度TBI的单独建模并没有显著改变模型性能或特征重要性;受伤前的就业是主要预测因素.

结论:

行政数据为TBI后返回工作预测提供了宝贵的见解.
提高患者特异性预后需要通过额外的信息来补充行政数据.