In this study, a wearable inertial measurement unit system was introduced to assess patients via the Berg balance scale (BBS), a clinical test for balance assessment. For this purpose, an automatic scoring algorithm was developed. The principal aim of this study is to improve the performance of the machine-learning-based method by introducing a deep-learning algorithm. A one-dimensional (1D) convolutional neural network (CNN) and a gated recurrent unit (GRU) that shows good performance in multivariate time-series data were used as model components to find the optimal ensemble model. Various structures were tested, and a stacking ensemble model with a simple meta-learner after two 1D-CNN heads and one GRU head showed the best performance. Additionally, model performance was enhanced by improving the dataset via preprocessing. The data were down sampled, an appropriate sampling rate was found, and the training and evaluation times of the model were improved. Using an augmentation process, the data imbalance problem was solved, and model accuracy was improved. The maximum accuracy of 14 BBS tasks using the model was 98.4%, which is superior to the results of previous studies.

To evaluate the effect of high-intensity interval training (HIIT) on psychological symptoms, activity states, and cardiovascular functions in patients with myocardial infarction (MI) of low and moderate risk stratification. This prospective study randomly allocated 44 patients with MI to 18 sessions of HIIT or conventional moderate-intensity continuous training (MICT). Outcome measures were assessed at baseline and after 18 sessions. Post-exercise cardiovascular and functional states, maximal oxygen uptake (VO2max), metabolic equivalents (METs), 6-Minute Walking Test (6MWT), and Korean Activity Scale/Index (KASI) scores were significantly improved in the HIIT group compared to those in the MICT group after 18 exercise sessions. In particular, VO2max was significantly (p<0.005) improved in the HIIT group (7.58 mL/kg/min) compared to that in the MICT group (2.42 mL/kg/min). In addition, post-exercise psychological states (i.e., scores of Fatigue Severity Scale [FSS] and depression items of the Hospital Anxiety and Depression Scale [HADS_D]) were significantly improved in the HIIT group compared to those in the MICT group after 18 exercise sessions. HADS-D was improved by 1.89 in the HIIT group compared to decrement of 0.47 in the MICT group. FSS was improved by 6.38 in the HIIT group compared to decrement of 0.77 in the MICT group (p<0.005). This study demonstrates that HIIT can improve cardiac function, psychological, and activity states in low and moderate risk MI patients. Compared to conventional MICT, HIIT can improve cardiovascular functions, activity states, depression, and fatigue more effectively.

Conservation of the ipsilateral upper limb function is important in stroke subjects with contralateral hemiplegia, because often it must serve as a compensatory tool for activities of daily livings (ADLs). However, the amount of functional loss and/o

Hong SE, et al. Ann Rehabil Med. 2017 Feb;41(1):16-24. https://doi.org/10.5535/arm.2017.41.1.16

Yim SY, et al. Ann Rehabil Med. 2017 Aug;41(4):638-649. https://doi.org/10.5535/arm.2017.41.4.638

Park YW, et al. Ann Rehabil Med. 2012 Aug;36(4):556-560. http://dx.doi.org/10.5535/arm.2012.36.4.556