{"title":"根据有外侧踝关节扭伤史的送货服务人员的踝关节力量、活动范围、姿势控制和解剖畸形,利用机器学习对慢性踝关节不稳定性进行分类。","authors":"Ui-jae Hwang , Oh-yun Kwon , Jun-hee Kim , Gyeong-tae Gwak","doi":"10.1016/j.msksp.2024.103230","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>Chronic ankle instability (CAI) frequently develops as a result of lateral ankle sprains (LAS) in delivery service workers (DSWs). Identifying risk factors for CAI is crucial for implementing targeted interventions. This study aimed to develop machine learning (ML) models for classifying CAI in DSWs with a history of LAS (DSWsLAS) and to identify key contributory factors.</div></div><div><h3>Design</h3><div>Exploratory, cross-sectional design.</div></div><div><h3>Setting</h3><div>and participants: A total of 121 DSWsLAS were screened for eligibility among 289 DSWs.</div></div><div><h3>Methods</h3><div>A total of 121 DSWsLAS were assessed for demographic characteristics, including ankle strength, range of motion, postural control, and anatomical deformities. Seven ML algorithms were trained and tested for classifying CAI. Principal component analysis (PCA) was used for feature extraction, and feature permutation importance (FPI) and Shapley additive explanations (SHAP) were employed to identify influential features.</div></div><div><h3>Main outcome measures</h3><div>Model performances were assessed using area under the curve (AUC). To interpret the classifications, we used FPI and SHAP values.</div></div><div><h3>Results</h3><div>PCA derived 7 principal components (PCs) accounting for 83.5% of the total variation in the data. The support vector machine (SVM) algorithm achieved the highest classifying performance (AUC = 0.817) among the ML models. FPI and SHAP revealed that PC1, PC2, PC5, and PC7 were the most influential features for classifying CAI in DSWsLAS.</div></div><div><h3>Conclusions</h3><div>The SVM algorithm, utilizing PCA-derived factors related to body mass index and ankle muscle strength demonstrated high classifying performance for diagnosis of CAI in DSWsLAS, emphasizing the importance of considering multiple contributory factors in the prevention and management of this condition.</div></div>","PeriodicalId":56036,"journal":{"name":"Musculoskeletal Science and Practice","volume":"75 ","pages":"Article 103230"},"PeriodicalIF":2.2000,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning for classifying chronic ankle instability based on ankle strength, range of motion, postural control and anatomical deformities in delivery service workers with a history of lateral ankle sprains\",\"authors\":\"Ui-jae Hwang , Oh-yun Kwon , Jun-hee Kim , Gyeong-tae Gwak\",\"doi\":\"10.1016/j.msksp.2024.103230\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Objective</h3><div>Chronic ankle instability (CAI) frequently develops as a result of lateral ankle sprains (LAS) in delivery service workers (DSWs). Identifying risk factors for CAI is crucial for implementing targeted interventions. This study aimed to develop machine learning (ML) models for classifying CAI in DSWs with a history of LAS (DSWsLAS) and to identify key contributory factors.</div></div><div><h3>Design</h3><div>Exploratory, cross-sectional design.</div></div><div><h3>Setting</h3><div>and participants: A total of 121 DSWsLAS were screened for eligibility among 289 DSWs.</div></div><div><h3>Methods</h3><div>A total of 121 DSWsLAS were assessed for demographic characteristics, including ankle strength, range of motion, postural control, and anatomical deformities. Seven ML algorithms were trained and tested for classifying CAI. Principal component analysis (PCA) was used for feature extraction, and feature permutation importance (FPI) and Shapley additive explanations (SHAP) were employed to identify influential features.</div></div><div><h3>Main outcome measures</h3><div>Model performances were assessed using area under the curve (AUC). To interpret the classifications, we used FPI and SHAP values.</div></div><div><h3>Results</h3><div>PCA derived 7 principal components (PCs) accounting for 83.5% of the total variation in the data. The support vector machine (SVM) algorithm achieved the highest classifying performance (AUC = 0.817) among the ML models. FPI and SHAP revealed that PC1, PC2, PC5, and PC7 were the most influential features for classifying CAI in DSWsLAS.</div></div><div><h3>Conclusions</h3><div>The SVM algorithm, utilizing PCA-derived factors related to body mass index and ankle muscle strength demonstrated high classifying performance for diagnosis of CAI in DSWsLAS, emphasizing the importance of considering multiple contributory factors in the prevention and management of this condition.</div></div>\",\"PeriodicalId\":56036,\"journal\":{\"name\":\"Musculoskeletal Science and Practice\",\"volume\":\"75 \",\"pages\":\"Article 103230\"},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2024-11-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Musculoskeletal Science and Practice\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2468781224003254\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"REHABILITATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Musculoskeletal Science and Practice","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2468781224003254","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"REHABILITATION","Score":null,"Total":0}
引用次数: 0
摘要
目的:慢性踝关节不稳定(CAI)经常因外侧踝关节扭伤(LAS)而在送餐服务人员(DSW)中出现。识别慢性踝关节不稳定的风险因素对于实施有针对性的干预措施至关重要。本研究旨在开发机器学习(ML)模型,用于对有外侧踝关节扭伤病史(DSWsLAS)的送餐服务人员的外侧踝关节扭伤进行分类,并确定关键的诱发因素:探索性横断面设计:在 289 名社工中筛选出 121 名符合条件的社工:共对 121 名 DSWsLAS 进行了人口统计学特征评估,包括踝关节力量、活动范围、姿势控制和解剖学畸形。为对 CAI 进行分类,对七种 ML 算法进行了训练和测试。主成分分析(PCA)用于特征提取,特征排列重要性(FPI)和夏普利加法解释(SHAP)用于识别有影响的特征:使用曲线下面积(AUC)评估模型性能。为了解释分类,我们使用了 FPI 和 SHAP 值:PCA得出了7个主成分(PC),占数据总变化的83.5%。在 ML 模型中,支持向量机(SVM)算法的分类性能最高(AUC = 0.817)。FPI和SHAP显示,PC1、PC2、PC5和PC7是对DSWsLAS中CAI分类最有影响的特征:结论:利用与体重指数和踝关节肌力相关的 PCA 导出因子的 SVM 算法在诊断 DSWsLAS 中的 CAI 时表现出了很高的分类性能,强调了在预防和管理这种疾病时考虑多种促成因素的重要性。
Machine learning for classifying chronic ankle instability based on ankle strength, range of motion, postural control and anatomical deformities in delivery service workers with a history of lateral ankle sprains
Objective
Chronic ankle instability (CAI) frequently develops as a result of lateral ankle sprains (LAS) in delivery service workers (DSWs). Identifying risk factors for CAI is crucial for implementing targeted interventions. This study aimed to develop machine learning (ML) models for classifying CAI in DSWs with a history of LAS (DSWsLAS) and to identify key contributory factors.
Design
Exploratory, cross-sectional design.
Setting
and participants: A total of 121 DSWsLAS were screened for eligibility among 289 DSWs.
Methods
A total of 121 DSWsLAS were assessed for demographic characteristics, including ankle strength, range of motion, postural control, and anatomical deformities. Seven ML algorithms were trained and tested for classifying CAI. Principal component analysis (PCA) was used for feature extraction, and feature permutation importance (FPI) and Shapley additive explanations (SHAP) were employed to identify influential features.
Main outcome measures
Model performances were assessed using area under the curve (AUC). To interpret the classifications, we used FPI and SHAP values.
Results
PCA derived 7 principal components (PCs) accounting for 83.5% of the total variation in the data. The support vector machine (SVM) algorithm achieved the highest classifying performance (AUC = 0.817) among the ML models. FPI and SHAP revealed that PC1, PC2, PC5, and PC7 were the most influential features for classifying CAI in DSWsLAS.
Conclusions
The SVM algorithm, utilizing PCA-derived factors related to body mass index and ankle muscle strength demonstrated high classifying performance for diagnosis of CAI in DSWsLAS, emphasizing the importance of considering multiple contributory factors in the prevention and management of this condition.
期刊介绍:
Musculoskeletal Science & Practice, international journal of musculoskeletal physiotherapy, is a peer-reviewed international journal (previously Manual Therapy), publishing high quality original research, review and Masterclass articles that contribute to improving the clinical understanding of appropriate care processes for musculoskeletal disorders. The journal publishes articles that influence or add to the body of evidence on diagnostic and therapeutic processes, patient centered care, guidelines for musculoskeletal therapeutics and theoretical models that support developments in assessment, diagnosis, clinical reasoning and interventions.