Department of Tuina, Yueyang Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai University of Traditional Chinese Medicine, Shanghai, China.
Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai, China.
BMJ Open. 2023 Aug 1;13(8):e067036. doi: 10.1136/bmjopen-2022-067036.
To build a supervised machine learning-based classifier, which can accurately predict whether Tai Chi practitioners may experience knee pain after years of exercise.
A prospective approach was used. Data were collected using face-to-face through a self-designed questionnaire.
Single centre in Shanghai, China.
A total of 1750 Tai Chi practitioners with a course of Tai Chi exercise over 5 years were randomly selected.
All participants were measured by a questionnaire survey including personal information, Tai Chi exercise pattern and Irrgang Knee Outcome Survey Activities of Daily Living Scale. The validity of the questionnaire was analysed by logical analysis and test, and the reliability of this questionnaire was mainly tested by a re-test method. Dataset 1 was established by whether the participant had knee pain, and dataset 2 by whether the participant's knee pain affected daily living function. Then both datasets were randomly assigned to a training and validating dataset and a test dataset in a ratio of 7:3. Six machine learning algorithms were selected and trained by our dataset. The area under the receiver operating characteristic curve was used to evaluate the performance of the trained models, which determined the best prediction model.
A total of 1703 practitioners completed the questionnaire and 47 were eliminated for lack of information. The total reliability of the scale is 0.94 and the KMO (Kaiser-Meyer-Olkin measure of sampling adequacy) value of the scale validity was 0.949 (>0.7). The CatBoost algorithm-based machine-learning model achieved the best predictive performance in distinguishing practitioners with different degrees of knee pain after Tai Chi practice. 'Having knee pain before Tai Chi practice', 'knee joint warm-up' and 'duration of each exercise' are the top three factors associated with pain after Tai Chi exercise in the model. 'Having knee pain before Tai Chi practice', 'Having Instructor' and 'Duration of each exercise' were most relevant to whether pain interfered with daily life in the model.
CatBoost-based machine learning classifier accurately predicts knee pain symptoms after practicing Tai Chi. This study provides an essential reference for practicing Tai Chi scientifically to avoid knee pain.
构建一个基于监督机器学习的分类器，以准确预测练习太极拳多年后是否会出现膝关节疼痛。
前瞻性方法。通过自行设计的问卷，面对面收集数据。
中国上海的一个单一中心。
共随机抽取 1750 名练习太极拳 5 年以上的太极拳练习者。
所有参与者均通过问卷调查进行测量，内容包括个人信息、太极拳运动模式和 Irrgang 膝关节结局调查日常生活量表。通过逻辑分析和测试对问卷的有效性进行分析，主要通过重测法测试问卷的信度。数据集 1 根据参与者是否有膝关节疼痛来建立，数据集 2 根据参与者的膝关节疼痛是否影响日常生活功能来建立。然后将两个数据集按照 7:3 的比例随机分配到训练和验证数据集和测试数据集。选择了 6 种机器学习算法，并使用我们的数据集进行训练。通过受试者工作特征曲线下的面积来评估训练模型的性能，从而确定最佳预测模型。
共有 1703 名从业者完成了问卷调查，有 47 人因信息缺失而被淘汰。该量表的总信度为 0.94，量表效度的 KMO（Kaiser-Meyer-Olkin 抽样充分性度量）值为 0.949（>0.7）。基于 CatBoost 算法的机器学习模型在区分太极拳练习者不同程度膝关节疼痛方面具有最佳的预测性能。“练习太极拳前有膝关节疼痛”“膝关节热身”和“每次运动的持续时间”是模型中与太极拳运动后疼痛相关的前三个因素。“练习太极拳前有膝关节疼痛”“有指导者”和“每次运动的持续时间”是模型中与疼痛是否影响日常生活最相关的三个因素。
基于 CatBoost 的机器学习分类器能准确预测练习太极拳后膝关节疼痛症状。本研究为科学练习太极拳避免膝关节疼痛提供了重要参考。
