Scholarlink

Background <p>Osteoarthritis (OA) of the hip is a progressive musculoskeletal disorder characterized by stiffness and limited passive range of motion. Hip OA patients experience mobility impairment and altered gait patterns when compared to healthy controls (HCs). Although various interventions have been designed to alleviate these symptoms, it is unclear if there is a reliable method to track biomechanical changes in patients with unilateral hip OA in a clinical setting.</p> Purpose <p>The purpose of this study is to evaluate the efficacy of lower extremity kinematic gait data for detecting and rating the severity of unilateral hip OA using machine learning algorithms.</p> Methods <p>First, a feature extraction framework is developed to derive several discriminative spatiotemporal and nonlinear features from lower extremity kinematic gait data. These features reflect the subtle disparity in gait characteristics, and can serve as indicators to distinguish between groups. Afterwards, the Shapley Additive exPlanations (SHAP) method is applied for feature selection and dimensionality reduction, providing detailed explanations of each feature’s contribution to classification performance. Second, a support vector machine (SVM) is used to classify gait patterns between unilateral hip OA patients and HCs. Finally, the effectiveness of this strategy is comprehensively validated on a publicly available gait dataset, containing 80 asymptomatic participants and 99 patients with unilateral hip OA, who are classified according to Grades 2, 3, and 4 of Kellgren and Lawrence (KL).</p> Results <p>Using a cross-validation scheme of 10-fold, the classification accuracy achieves 98.21% for hip OA detection (HCs <i>vs</i> hip OA patients) and 89.65% (HCs <i>vs</i> Grade2/3 <i>vs</i> Grade 4) and 87.54% (HCs <i>vs</i> Grade2 <i>vs</i> Grade 3 <i>vs</i> Grade 4) for severity rating.</p> Conclusion <p>The results demonstrate superior performance compared to other up-to-date methods, suggesting that the proposed method can serve as a supplementary tool to the KL grading scale for hip OA detection and severity assessment in clinical practice. Gait analysis provides objective data on the patient’s walking pattern and can detect subtle changes in gait that may not be apparent on a radiographic image.</p> Trial registration <p>ClinicalTrials. gov (NCT01907503). The registration date of the clinical trial is 17th July, 2013.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An interpretable machine learning approach for predicting and grading hip osteoarthritis using gait analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月1日

查看全文
  • Qing Yang,
  • Xinyu Ji,
  • Yuyan Zhang,
  • Shaoyi Du,
  • Bing Ji,
  • Wei Zeng

摘要

Background

Osteoarthritis (OA) of the hip is a progressive musculoskeletal disorder characterized by stiffness and limited passive range of motion. Hip OA patients experience mobility impairment and altered gait patterns when compared to healthy controls (HCs). Although various interventions have been designed to alleviate these symptoms, it is unclear if there is a reliable method to track biomechanical changes in patients with unilateral hip OA in a clinical setting.

Purpose

The purpose of this study is to evaluate the efficacy of lower extremity kinematic gait data for detecting and rating the severity of unilateral hip OA using machine learning algorithms.

Methods

First, a feature extraction framework is developed to derive several discriminative spatiotemporal and nonlinear features from lower extremity kinematic gait data. These features reflect the subtle disparity in gait characteristics, and can serve as indicators to distinguish between groups. Afterwards, the Shapley Additive exPlanations (SHAP) method is applied for feature selection and dimensionality reduction, providing detailed explanations of each feature’s contribution to classification performance. Second, a support vector machine (SVM) is used to classify gait patterns between unilateral hip OA patients and HCs. Finally, the effectiveness of this strategy is comprehensively validated on a publicly available gait dataset, containing 80 asymptomatic participants and 99 patients with unilateral hip OA, who are classified according to Grades 2, 3, and 4 of Kellgren and Lawrence (KL).

Results

Using a cross-validation scheme of 10-fold, the classification accuracy achieves 98.21% for hip OA detection (HCs vs hip OA patients) and 89.65% (HCs vs Grade2/3 vs Grade 4) and 87.54% (HCs vs Grade2 vs Grade 3 vs Grade 4) for severity rating.

Conclusion

The results demonstrate superior performance compared to other up-to-date methods, suggesting that the proposed method can serve as a supplementary tool to the KL grading scale for hip OA detection and severity assessment in clinical practice. Gait analysis provides objective data on the patient’s walking pattern and can detect subtle changes in gait that may not be apparent on a radiographic image.

Trial registration

ClinicalTrials. gov (NCT01907503). The registration date of the clinical trial is 17th July, 2013.