Shanjun Li

Objective: This review aims to synthesize the current evidence on the potential effects of Traditional Chinese Exercise (TCE) on cognition, sleep quality, and quality of life (QoL) in Parkinson’s disease (PD) patients, and to explore intervention characteristics that may be associated with beneficial outcomes. Methods: We searched five major databases (PubMed, Web of Science, EBSCO, Cochrane, and Scopus) for randomized controlled trials up to March 2025. Studies assessing TCE in patients with PD were included. Data were pooled using the standardized mean difference (SMD) and 95% confidence interval (CI). Results: Fifteen trials met the inclusion criteria. TCE demonstrated significant overall improvements in cognition (SMD = 0.87, 95% CI [0.56, 1.19]), sleep quality (SMD, −0.88, 95% CI [−1.41, −0.34]), and QoL (SMD, −0.48, 95% CI [−0.66, −0.29]). Subgroup analyses revealed that interventions lasting ≥12 weeks and totaling ≥180 min per week may be associated with more favorable outcomes, although these findings should be interpreted cautiously. For exercise type, Tai Chi was particularly effective for cognition (SMD, 0.91, p < 0.0001) and QoL (SMD, −0.70, p < 0.00001), while Health Qigong was highly effective for sleep quality (SMD, −0.92, p = 0.01). Benefits were also more pronounced in patients with a disease duration of 5 years or more. Conclusion: TCE may be beneficial for improving cognition, sleep quality, and QoL in patients with PD. Subgroup findings further suggest that intervention type, duration, and weekly exercise volume may be associated with differential outcomes.

Dynamic oxygen uptake (VO₂) reflects moment-to-moment changes in oxygen consumption during exercise and underpins training design, performance enhancement, and clinical decision-making. We tackled two key obstacles—the limited fusion of heterogeneous sensor data and inadequate modeling of long-range temporal patterns—by integrating wearable accelerometer and heart-rate streams with a convolutional neural network–LSTM (CNN-LSTM) architecture and optional attention modules. Physiological signals and VO₂ were recorded from 21 adults through resting assessment and cardiopulmonary exercise testing. The results showed that pairing accelerometer with heart-rate inputs improves prediction compared with considering the heart rate alone. The baseline CNN-LSTM reached R² = 0.946, outperforming a plain LSTM (R² = 0.926) thanks to stronger local spatio-temporal feature extraction. Introducing a spatial attention mechanism raised accuracy further (R² = 0.962), whereas temporal attention reduced it (R² = 0.930), indicating that attention success depends on how well the attended features align with exercise dynamics. Stacking both attentions (spatio-temporal) yielded R² = 0.960, slightly below the value for spatial attention alone, implying that added complexity does not guarantee better performance. Across all models, prediction errors grew during high-intensity bouts, highlighting a bottleneck in capturing non-linear physiological responses under heavy load. These findings inform architecture selection for wearable metabolic monitoring and clarify when attention mechanisms add value.