• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于YOLOX计算机模型评估重度膝关节骨关节炎患者膝关节功能与手动评估相比的可行性。

Feasibility of YOLOX computer model-based assessment of knee function compared with manual assessment for people with severe knee osteoarthritis.

作者信息

Yang Tao, Zhao Jie, Wang Ben, Wang Li, Bao Hengzhe, Li Bing, Luo Wen, Zhao Huiwen, Liu Jun

机构信息

Joint Surgery Department, Tianjin Hospital, No. 406, Jiefangnan Road, Tianjin, 300211, People's Republic of China.

College of Orthopedics, Tianjin Medical University, Tianjin, People's Republic of China.

出版信息

BMC Med Inform Decis Mak. 2025 Jan 24;25(1):40. doi: 10.1186/s12911-025-02877-0.

DOI:10.1186/s12911-025-02877-0
PMID:39856682
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11763141/
Abstract

OBJECTIVE

This study aimed to assess the feasibility of computer model-based evaluation of knee joint functional capacity in comparison with manual assessment.

METHODS

This study consisted of two phases: (1) developing an automatic knee joint action recognition and classification system on the basis of improved YOLOX and (2) analyzing the feasibility of assessment by the software system and doctors, identifying the knee joint function of patients, and determining the accuracy of the software system. We collected 40-50 samples for use in clinical experiments. The datasets used in this study were collected from patients admitted to the Joint Surgery Center. In this study, the knee joint assessment items included stair climbing, walking on uneven surfaces, and knee joint function. To assess the computer model's automatic evaluation of knee joint function, MedCalc 20 statistical software was used to analyze the consistency of the Lequesne functional index between the computer model's automated determinations and manual independent assessments.

RESULTS

The weighted kappa coefficients between the doctors' assessments and the software system's assessments were 0.76 (95% confidence intervals:0.59 ~ 0.92) for climbing up and down stairs, 0.64 (95% confidence intervals:0.45 ~ 0.82) for walking on uneven floors, and 0.68 (95% confidence intervals:0.53 ~ 0.84) for the Lequesne functional index, indicating good consistency between the assessments of the software system and doctors.

CONCLUSION

This paper introduces an automatic knee joint action recognition and classification method based on improved YOLOX. By comparing the results obtained by orthopedic doctors and the software system, the feasibility of this software system was validated in the clinic.

摘要

目的

本研究旨在评估基于计算机模型的膝关节功能能力评估与人工评估相比的可行性。

方法

本研究包括两个阶段：（1）基于改进的YOLOX开发自动膝关节动作识别与分类系统；（2）分析软件系统与医生评估的可行性，识别患者的膝关节功能，并确定软件系统的准确性。我们收集了40 - 50个样本用于临床实验。本研究中使用的数据集来自关节外科中心收治的患者。在本研究中，膝关节评估项目包括上下楼梯、在不平整地面行走以及膝关节功能。为评估计算机模型对膝关节功能的自动评估，使用MedCalc 20统计软件分析计算机模型自动测定结果与人工独立评估之间Lequesne功能指数的一致性。

结果

医生评估与软件系统评估之间的加权kappa系数，上下楼梯为0.76（95%置信区间：0.59 ~ 0.92），在不平整地面行走为0.64（95%置信区间：0.45 ~ 0.82），Lequesne功能指数为0.68（95%置信区间：0.53 ~ 0.84），表明软件系统与医生的评估之间具有良好的一致性。

结论

本文介绍了一种基于改进YOLOX的自动膝关节动作识别与分类方法。通过比较骨科医生和软件系统获得的结果，验证了该软件系统在临床中的可行性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/1effd2f2ae07/12911_2025_2877_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/72662d42f377/12911_2025_2877_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/25b8ca40de7e/12911_2025_2877_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/ffc03198c7a5/12911_2025_2877_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/c381353393f9/12911_2025_2877_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/b36b4509051b/12911_2025_2877_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/1effd2f2ae07/12911_2025_2877_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/72662d42f377/12911_2025_2877_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/25b8ca40de7e/12911_2025_2877_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/ffc03198c7a5/12911_2025_2877_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/c381353393f9/12911_2025_2877_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/b36b4509051b/12911_2025_2877_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/7ac7/11763141/1effd2f2ae07/12911_2025_2877_Fig6_HTML.jpg

相似文献

1
Feasibility of YOLOX computer model-based assessment of knee function compared with manual assessment for people with severe knee osteoarthritis.基于YOLOX计算机模型评估重度膝关节骨关节炎患者膝关节功能与手动评估相比的可行性。
BMC Med Inform Decis Mak. 2025 Jan 24;25(1):40. doi: 10.1186/s12911-025-02877-0.
2
Pain catastrophizing affects stair climbing ability in individuals with knee osteoarthritis.疼痛灾难化影响膝骨关节炎患者的爬楼梯能力。
Clin Rheumatol. 2020 Apr;39(4):1257-1264. doi: 10.1007/s10067-019-04881-y. Epub 2019 Dec 18.
3
Identification of Early Knee Osteoarthritis Based on Knee Joint Trajectory during Stair Climbing.基于爬楼梯过程中膝关节轨迹对早期膝关节骨关节炎的识别。
Int J Environ Res Public Health. 2022 Nov 15;19(22):15023. doi: 10.3390/ijerph192215023.
4
Biomechanical correlates of gait and stair climbing are associated with ex vivo cartilage quality in gonarthrotic patients.膝关节骨性关节炎患者的步态和爬楼梯的生物力学相关因素与离体软骨质量相关。
J Biomech. 2025 Mar;181:112546. doi: 10.1016/j.jbiomech.2025.112546. Epub 2025 Jan 22.
5
Gait Analysis Reveals that Total Hip Arthroplasty Increases Power Production in the Hip During Level Walking and Stair Climbing.步态分析显示，全髋关节置换术可增加髋关节在水平行走和爬楼梯时的动力输出。
Clin Orthop Relat Res. 2019 Aug;477(8):1839-1847. doi: 10.1097/CORR.0000000000000809.
6
Knee loading and joint pain during daily activities in people with knee osteoarthritis: A systematic review and meta-analysis.膝关节骨关节炎患者日常活动中的膝关节负荷与关节疼痛：一项系统评价和荟萃分析。
Clin Biomech (Bristol). 2025 Feb;122:106433. doi: 10.1016/j.clinbiomech.2025.106433. Epub 2025 Jan 11.
7
Examining BMI-knee angle relationship in healthy young adults during stair ambulation using Kinovea® software.使用 Kinovea® 软件检测健康年轻成年人在楼梯行走过程中的 BMI-膝关节角度关系。
Eur Rev Med Pharmacol Sci. 2024 May;28(10):3493-3502. doi: 10.26355/eurrev_202405_36283.
8
The complexity of human walking: a knee osteoarthritis study.人类行走的复杂性：一项膝关节骨关节炎研究。
PLoS One. 2014 Sep 18;9(9):e107325. doi: 10.1371/journal.pone.0107325. eCollection 2014.
9
HKA-Net: clinically-adapted deep learning for automated measurement of hip-knee-ankle angle on lower limb radiography for knee osteoarthritis assessment.HKA-Net：适用于临床的深度学习，用于自动测量下肢 X 线摄影中膝骨关节炎评估的髋膝踝角度。
J Orthop Surg Res. 2024 Nov 20;19(1):777. doi: 10.1186/s13018-024-05265-y.
10
[Kinetic mechanism of electroacupuncture for stair climbing in knee osteoarthritis patients].[电针对膝骨关节炎患者爬楼梯的动力学机制]
Zhongguo Zhen Jiu. 2017 Oct 12;37(10):1027-34. doi: 10.13703/j.0255-2930.2017.10.001.

本文引用的文献

1
LightPRA: A Lightweight Temporal Convolutional Network for Automatic Physical Rehabilitation Exercise Assessment.LightPRA：一种用于自动物理康复运动评估的轻量级时间卷积网络。
Comput Biol Med. 2024 May;173:108382. doi: 10.1016/j.compbiomed.2024.108382. Epub 2024 Mar 25.
2
Exploring the potential of the sit-to-stand test for self-assessment of physical condition in advanced knee osteoarthritis patients using computer vision.利用计算机视觉探索坐站测试在评估晚期膝骨关节炎患者身体状况自我评估中的潜力。
Front Public Health. 2024 Feb 7;12:1348236. doi: 10.3389/fpubh.2024.1348236. eCollection 2024.
3
Azure Kinect performance evaluation for human motion and upper limb biomechanical analysis.
用于人体运动和上肢生物力学分析的Azure Kinect性能评估
Heliyon. 2023 Nov 4;9(11):e21606. doi: 10.1016/j.heliyon.2023.e21606. eCollection 2023 Nov.
4
Beyond Human Detection: A Benchmark for Detecting Common Human Posture.超越人类检测：检测常见人体姿势的基准
Sensors (Basel). 2023 Sep 24;23(19):8061. doi: 10.3390/s23198061.
5
Artificial Intelligence for skeleton-based physical rehabilitation action evaluation: A systematic review.基于骨骼的物理康复动作评估的人工智能：一项系统综述。
Comput Biol Med. 2023 May;158:106835. doi: 10.1016/j.compbiomed.2023.106835. Epub 2023 Mar 31.
6
Reliability and validity of OpenPose for measuring hip-knee-ankle angle in patients with knee osteoarthritis.用于测量膝骨关节炎患者髋膝踝角度的 OpenPose 的可靠性和有效性。
Sci Rep. 2023 Feb 25;13(1):3297. doi: 10.1038/s41598-023-30352-1.
7
Prediction of Human Activities Based on a New Structure of Skeleton Features and Deep Learning Model.基于骨骼特征新结构和深度学习模型的人类活动预测。
Sensors (Basel). 2020 Sep 1;20(17):4944. doi: 10.3390/s20174944.
8
A review of computational approaches for evaluation of rehabilitation exercises.康复训练评估的计算方法综述
Comput Biol Med. 2020 Apr;119:103687. doi: 10.1016/j.compbiomed.2020.103687. Epub 2020 Mar 4.
9
Kinect and wearable inertial sensors for motor rehabilitation programs at home: state of the art and an experimental comparison.用于家庭中运动康复计划的 Kinect 和可穿戴惯性传感器：最新技术和实验比较。
Biomed Eng Online. 2020 Apr 23;19(1):25. doi: 10.1186/s12938-020-00762-7.
10
A Deep Learning Framework for Assessing Physical Rehabilitation Exercises.深度学习框架用于评估物理康复运动。
IEEE Trans Neural Syst Rehabil Eng. 2020 Feb;28(2):468-477. doi: 10.1109/TNSRE.2020.2966249. Epub 2020 Jan 13.