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

Clinical and radiological factors associated with recurrent shoulder dislocation after conservative treatment of traumatic primary anterior shoulder dislocation.

Journal of orthopaedic surgery and research·2026
Same author

Geriatric nutritional risk index as an independent predictor of 1-year mortality in elderly patients with hip fractures.

PloS one·2026
Same author

Therapeutic effects of cinnamic acid in a rat model of collagenase-induced Achilles tendinopathy.

BMC complementary medicine and therapies·2025
Same author

Primary Purulent Infectious Myositis of the Extremities in Children.

Journal of pediatric orthopedics·2025
Same author

MRI-based evaluation of tibial tunnel proximity to the anterior horn of the lateral meniscus in remnant-preserving anterior cruciate ligament reconstruction.

Acta orthopaedica et traumatologica turcica·2025
Same author

Comparison of the clinical results of arthroscopic release and open release in the surgical treatment of lateral epicondylitis.

Archives of orthopaedic and trauma surgery·2025

相关实验视频

Updated: May 10, 2025

An Intramedullary Locking Nail for Standardized Fixation of Femur Osteotomies to Analyze Normal and Defective Bone Healing in Mice
07:41

An Intramedullary Locking Nail for Standardized Fixation of Femur Osteotomies to Analyze Normal and Defective Bone Healing in Mice

Published on: November 13, 2016

13.3K

机器学习模型用于预测骨内甲指甲长度.

Sercan Capkin1, Ali Ihsan Kilic2, Hakan Cici3

  • 1Faculty of Medicine, Department of Orthopaedics and Traumatology, Izmir Bakircay University, Izmir, 36665, Turkey. sercancapkn@gmail.com.

BMC musculoskeletal disorders
|April 21, 2025
PubMed
概括

在骨折治疗中,预测骨内甲钉 (IMN) 长度至关重要. 使用人体测量数据的机器学习模型,特别是带着结节至中等骨距离的线性回归,可以准确估计IMN长度,减少手术时间和辐射暴露.

关键词:
人类测量测量 人类测量测量测量线性回归是一种线性回归.机器学习是机器学习.进行手术前规划.甲内甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲甲

更多相关视频

The Tibial Fracture-Pin Model: A Clinically Relevant Mouse Model of Orthopedic Injury
00:05

The Tibial Fracture-Pin Model: A Clinically Relevant Mouse Model of Orthopedic Injury

Published on: July 28, 2022

1.6K
A Minimally Invasive Model to Analyze Endochondral Fracture Healing in Mice Under Standardized Biomechanical Conditions
06:41

A Minimally Invasive Model to Analyze Endochondral Fracture Healing in Mice Under Standardized Biomechanical Conditions

Published on: March 22, 2018

8.2K

相关实验视频

Last Updated: May 10, 2025

An Intramedullary Locking Nail for Standardized Fixation of Femur Osteotomies to Analyze Normal and Defective Bone Healing in Mice
07:41

An Intramedullary Locking Nail for Standardized Fixation of Femur Osteotomies to Analyze Normal and Defective Bone Healing in Mice

Published on: November 13, 2016

13.3K
The Tibial Fracture-Pin Model: A Clinically Relevant Mouse Model of Orthopedic Injury
00:05

The Tibial Fracture-Pin Model: A Clinically Relevant Mouse Model of Orthopedic Injury

Published on: July 28, 2022

1.6K
A Minimally Invasive Model to Analyze Endochondral Fracture Healing in Mice Under Standardized Biomechanical Conditions
06:41

A Minimally Invasive Model to Analyze Endochondral Fracture Healing in Mice Under Standardized Biomechanical Conditions

Published on: March 22, 2018

8.2K

科学领域:

  • 整形外科手术 整形外科手术
  • 生物医学工程 生物医学工程
  • 医学中的数据科学.

背景情况:

  • 骨内甲钉 (IMN) 是骨轴骨折的标准.
  • 准确的IMN长度的术前预测仍然是一个挑战.
  • 目前的方法通常依赖于手术内数据,增加手术时间和辐射暴露.

研究的目的:

  • 评估机器学习 (ML) 模型,用人类测量来预测骨IMN长度.
  • 在这个预测任务中比较不同ML模型的有效性.

主要方法:

  • 追溯分析了163名接受了部IMN的患者.
  • 收集的人类测量数据:身高,鞋子尺寸,大头骨到第五手指骨的距离 (OM),骨到中骨的距离 (TTMM).
  • 使用并评估了四种ML模型:线性回归,随机森林,决策树和XGBoost,使用MSE和R平方值.

主要成果:

  • 线性回归实现了最佳性能 (R平方=0.89,MSE=117.53).
  • TTMM显示与IMN长度 (r=0.911) 的相关性最强,其次是身高和OM.
  • 鞋子尺寸的相关性较弱,对预测准确性产生负面影响;非线性模型在线性回归上提供了有限的改进.

结论:

  • 将人体测量数据与线性回归模型结合起来,可以准确地预测骨IMN长度.
  • 这种方法可以优化术前规划,减少手术内测量,手术时间和辐射暴露.
  • 建议对更大,更多样化的数据集进行进一步验证.