Prediction of knee joint pain in Tai Chi practitioners: a cross-sectional machine learning approach.

OBJECTIVE: To build a supervised machine learning-based classifier, which can accurately predict whether Tai Chi practitioners may experience knee pain after years of exercise. DESIGN: A prospective approach was used. Data were collected using face-to-face through a self-designed questionnaire. SETTING: Single centre in Shanghai, China. PARTICIPANTS: A total of 1750 Tai Chi practitioners with a course of Tai Chi exercise over 5 years were randomly selected. MEASURES: 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. RESULTS: 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. CONCLUSION: 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.

Effectiveness of therapeutic massage for improving motor symptoms in Parkinson's disease: A systematic review and meta-analysis.

Background: Parkinson's disease (PD) causes movement disorders [called motor symptoms (MS)], and motor dysfunction poses a great barrier to the quality of life. Although pharmacological therapy like levodopa can relieve the symptoms, it can also cause complications, such as psychosis, nausea, and dyskinesia. A therapy with more minor side effects is needed for PD. Therapeutic massages are the most commonly used forms of complementary and alternative medicine (CAM), but no systematic review and meta-analysis have focused on the efficacy of massage on PD. Objective: To evaluate the quality of evidence and efficacy of therapeutic massage for improving MS in PD. Methods: We independently searched four electronic databases, including Chinese National Knowledge Infrastructure (CNKI), MEDLINE/PubMed, Embase, and Cochrane Library, for randomized controlled trials (RCTs) about therapeutic massage and other available manual therapies improving MS in PD from January 1, 2012, to December 31, 2021 (recent 10 years). The main outcome measures were total effectiveness and the Unified Parkinson's Disease Rating Scale (UPDRS), including UPDRS total, II, and III. For the statistical analysis, the risk ratio, standard mean difference, and 95% confidence interval (CI) were used to calculate effect sizes between groups. To determine heterogeneity, statistical index I 2 was used. Results: A total of 363 PD participants in seven RCTs and one randomized pilot-control study were included in this meta-analysis. The total effectiveness showed that therapeutic massage was more effective than the intervention of the control group for improving MS [ratio risk (RR): 1.33, 95% CI (1.14-1.55), p = 0.0002]. The UPDRS-III scores showed that massage improves motor function more than the control group [SMD = -0.46, 95% CI (-0.67, -0.24), p < 0.00001]. But we found that massage performed no better than the control group in improving daily life activities [SMD = -0.15, 95% CI (-0.40, 0.10), p = 0.23]. Conclusion: Therapeutic massage was effective in improving MS in PD. It is suggested to be an appropriate form of CAM in treating PD. Systematic Review Registration: https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=323182, identifier: CRD42022323182.