Artificial Intelligence–Driven Elucidation of Mechanistic Links Between Proximal Joint Strength and Tibial Loading in Runners With Medial Tibial Stress Syndrome: Implications for Precision Rehabilitation

IF 4 2区 医学 Q1 REHABILITATION
Zeyi Zhang PhD, Ting Fan PhD, Youping Sun MSc
{"title":"Artificial Intelligence–Driven Elucidation of Mechanistic Links Between Proximal Joint Strength and Tibial Loading in Runners With Medial Tibial Stress Syndrome: Implications for Precision Rehabilitation","authors":"Zeyi Zhang PhD,&nbsp;Ting Fan PhD,&nbsp;Youping Sun MSc","doi":"10.1016/j.apmr.2026.05.023","DOIUrl":null,"url":null,"abstract":"<div><h3>Objectives</h3><div>This study leveraged machine learning algorithms to observationally elucidate how proximal joint muscle activation patterns—particularly those involving the trunk and hip—are associated with the modulation of tibial loading during running. These findings may provide preliminary theoretical insights into reducing tibial loading during running in individuals with medial tibial stress syndrome (MTSS) and in preventing recurrence.</div></div><div><h3>Design</h3><div>Cross-sectional design.</div></div><div><h3>Setting</h3><div>Biomechanics laboratory with musculoskeletal modeling and machine learning.</div></div><div><h3>Participants</h3><div>A total of 174 recreational runners diagnosed with MTSS underwent biomechanical assessment during running, during which tibial loading was quantified. OpenSim modeling was subsequently performed to estimate muscle-force production of proximal joints throughout the gait cycle.</div></div><div><h3>Interventions</h3><div>Not applicable.</div></div><div><h3>Main Outcome Measures</h3><div>Three machine learning models—extreme gradient boosting, random forest, and support vector regression—were developed and integrated with the SHapley Additive exPlanations framework to characterize the relationships between proximal muscle force and tibial loading.</div></div><div><h3>Results</h3><div>Among the 3 models, extreme gradient boosting demonstrated the highest predictive accuracy. The SHapley Additive exPlanations dependence plots further identified several model-derived inflection features, indicating that tibial loading increased markedly when ipsilateral external oblique muscle force exceeded 10.417 N/kg, gluteus minimus force decreased below 0.776 N/kg, or piriformis muscle force exceeded 1.952 N/kg. These values should be interpreted as exploratory, model-dependent reference points rather than definitive clinical thresholds.</div></div><div><h3>Conclusion</h3><div>Excessive force generated by the ipsilateral external oblique and piriformis, coupled with insufficient gluteus minimus force, markedly elevates tibial loading during running in individuals with MTSS. Based on these observational findings, we speculate that restoring bilateral balance in external oblique force and strengthening the hip abductors and internal rotators may help reduce tibial loading and thereby mitigate the risk of MTSS. However, this hypothesis requires confirmation in future intervention studies.</div></div>","PeriodicalId":8313,"journal":{"name":"Archives of physical medicine and rehabilitation","volume":"107 10","pages":"Pages 2860-2868"},"PeriodicalIF":4.0000,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Archives of physical medicine and rehabilitation","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0003999326007525","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2026/6/4 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"REHABILITATION","Score":null,"Total":0}
引用次数: 0

Abstract

Objectives

This study leveraged machine learning algorithms to observationally elucidate how proximal joint muscle activation patterns—particularly those involving the trunk and hip—are associated with the modulation of tibial loading during running. These findings may provide preliminary theoretical insights into reducing tibial loading during running in individuals with medial tibial stress syndrome (MTSS) and in preventing recurrence.

Design

Cross-sectional design.

Setting

Biomechanics laboratory with musculoskeletal modeling and machine learning.

Participants

A total of 174 recreational runners diagnosed with MTSS underwent biomechanical assessment during running, during which tibial loading was quantified. OpenSim modeling was subsequently performed to estimate muscle-force production of proximal joints throughout the gait cycle.

Interventions

Not applicable.

Main Outcome Measures

Three machine learning models—extreme gradient boosting, random forest, and support vector regression—were developed and integrated with the SHapley Additive exPlanations framework to characterize the relationships between proximal muscle force and tibial loading.

Results

Among the 3 models, extreme gradient boosting demonstrated the highest predictive accuracy. The SHapley Additive exPlanations dependence plots further identified several model-derived inflection features, indicating that tibial loading increased markedly when ipsilateral external oblique muscle force exceeded 10.417 N/kg, gluteus minimus force decreased below 0.776 N/kg, or piriformis muscle force exceeded 1.952 N/kg. These values should be interpreted as exploratory, model-dependent reference points rather than definitive clinical thresholds.

Conclusion

Excessive force generated by the ipsilateral external oblique and piriformis, coupled with insufficient gluteus minimus force, markedly elevates tibial loading during running in individuals with MTSS. Based on these observational findings, we speculate that restoring bilateral balance in external oblique force and strengthening the hip abductors and internal rotators may help reduce tibial loading and thereby mitigate the risk of MTSS. However, this hypothesis requires confirmation in future intervention studies.
人工智能驱动阐明胫骨内侧应激综合征跑步者近端关节强度和胫骨负荷之间的机制联系:对精确康复的影响。
目的:本研究利用机器学习算法来观察地阐明近端关节肌肉激活模式-特别是涉及躯干和臀部的那些-如何与跑步过程中胫骨负荷的调节相关。这些发现可能为减少内侧胫骨应激综合征(MTSS)患者跑步时的胫骨负荷和预防复发提供初步的理论见解。设计:横断面设计。设置:生物力学实验室与肌肉骨骼建模和机器学习。参与者:174名被诊断为MTSS的休闲跑步者在跑步过程中进行了生物力学评估,在此期间,胫骨负荷被量化。随后进行OpenSim建模,以估计在整个步态周期中近端关节的肌肉力量产生。干预措施:N / A。主要结果测量:开发了三种机器学习模型——极端梯度增强(XGBoost)、随机森林(RF)和支持向量回归(SVR),并将其与SHapley加性解释(SHAP)框架相结合,以表征近端肌肉力与胫骨负荷之间的关系。结果:在三个模型中,XGBoost的预测准确率最高。SHAP依赖性图进一步确定了几种模型衍生的屈伸特征,表明当同侧外斜肌力超过10.417 N/kg、臀小肌力低于0.776 N/kg或梨状肌力超过1.952 N/kg时,胫骨负荷显著增加。这些值应该被解释为探索性的、依赖于模型的参考点,而不是确定的临床阈值。结论:同侧外斜肌和梨状肌产生的力量过大,加上臀小肌力量不足,明显增加了MTSS患者跑步时的胫骨负荷。基于这些观察结果,我们推测恢复双侧外斜力平衡和加强髋关节外展肌和内旋肌可能有助于减少胫骨负荷,从而减轻MTSS的风险。然而,这一假设需要在未来的干预研究中得到证实。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
6.20
自引率
4.70%
发文量
495
审稿时长
38 days
期刊介绍: The Archives of Physical Medicine and Rehabilitation publishes original, peer-reviewed research and clinical reports on important trends and developments in physical medicine and rehabilitation and related fields. This international journal brings researchers and clinicians authoritative information on the therapeutic utilization of physical, behavioral and pharmaceutical agents in providing comprehensive care for individuals with chronic illness and disabilities. Archives began publication in 1920, publishes monthly, and is the official journal of the American Congress of Rehabilitation Medicine. Its papers are cited more often than any other rehabilitation journal.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书