Background: Deep learning related research works on website medical images have been actively conducted in the field of health care, however, articles related to the musculoskeletal system have been introduced insufficiently, deep learning-based studies on classifying orthopedic manual therapy images would also just be entered. Objectives: To create a deep learning model that categorizes cervical mobilization images and establish a web application to find out its clinical utility. Design: Research and development. Methods: Three types of cervical mobilization images (central posteroanterior (CPA) mobilization, unilateral posteroanterior (UPA) mobilization, and anteroposterior (AP) mobilization) were obtained using functions of ‘Download All Images’ and a web crawler. Unnecessary images were filtered from 'Auslogics Duplicate File Finder' to obtain the final 144 data (CPA=62, UPA=46, AP=36). Training classified into 3 classes was conducted in Teachable Machine. The next procedures, the trained model source was uploaded to the web application cloud integrated development environment (https://ide.goorm.io/) and the frame was built. The trained model was tested in three environments: Teachable Machine File Upload (TMFU), Teachable Machine Webcam (TMW), and Web Service webcam (WSW). Results: In three environments (TMFU, TMW, WSW), the accuracy of CPA mobilization images was 81-96%. The accuracy of the UPA mobilization image was 43~94%, and the accuracy deviation was greater than that of CPA. The accuracy of the AP mobilization image was 65-75%, and the deviation was not large compared to the other groups. In the three environments, the average accuracy of CPA was 92%, and the accuracy of UPA and AP was similar up to 70%. Conclusion: This study suggests that training of images of orthopedic manual therapy using machine learning open software is possible, and that web applications made using this training model can be used clinically.

Background: Recently, a new home-based dysphagia rehabilitation method using information and communications technology (ICT) has been reported, but clinical evidence is still lacking. Objectives: To investigate the effects of home-based dysphagia rehabilitation using ICT on tongue muscle strength and volume in patients with developed dysphagia after stroke. Design: Randomized controlled trial design. Methods: Twenty patients who developed dysphagia after stroke were enrolled. The experimental group received dysphagia rehabilitation in the form of ICT-based home care. In contrast, the control group received traditional rehabilitation based on swallowing under the supervision of occupational therapists. All interventions were conducted five times a week for four weeks. Results: Both groups showed statistically significant increases in tongue muscle strength and volume after the intervention (P<.05, both). However, there were no significant differences in tongue strength or volume between the two groups after the intervention (P>.05, both). Conclusion: Home-based dysphagia rehabilitation using ICT showed effects similar to those of conventional swallowing rehabilitation in patients who developed dysphagia after stroke. These findings suggest that dysphagia rehabilitation can be conducted at home without the help of a therapist.

Background: Vibration stimulation has emerged as a treatment tool to help reduce spasticity during physical therapy. Spasticity includes problems of reduced range of motion (ROM) and stiffness. However, the benefits of vibration rolling (VR) on interventions for stroke patients are unclear. Objectives: This study aimed to investigate the effect of VR intervention on the ankle ROM and ankle stiffness in stroke patients. Design: A randomized crossover study. Methods: Seven stroke patients completed two test sessions (one VR and one non-VR [NVR]) in a randomized order, with 48 hours of rest between each session. Participants completed intervention and its measurements on the same day. The measurements included ankle dorsiflexion and plantarflexion ROM and stiffness of ankle muscles, including the tibialis anterior, medial, and lateral gastrocnemius muscle. Results: After VR, ankle dorsiflexion ROM, lateral gastrocnemius stiffness, and medial gastrocnemius stiffness improved significantly (all P<.05). After NVR, only the lateral gastrocnemius stiffness improved significantly (P<.05). Furthermore, in the cases of changed values for ankle dorsiflexion ROM and lateral gastrocnemius stiffness were compared within groups, VR showed a more significant difference than NVR (P<.05) Conclusion: VR improved ankle ROM and muscle stiffness. Therefore, we suggest that practitioners need to consider VR as an intervention to improve dorsiflexion ROM and gastrocnemius stiffness in stroke patients.

Background: The spinal nerves, which start at the lumbar level, are connected to the nerve innervation in the knees. Currently, there is a lack of research on the treatment of knee pain through lumbar mobilization. Objectives: To investigate the effects of lumbar joint mobilization (LJM) and transcutaneous electronic nerve stimulation (TENS) on proprioception and muscular strength in volleyball players with chronic knee pain. Design: Two group pre-posttest. Methods: A total of 26 professional volleyball players with chronic knee pain were allocated to the LJM (n=13) and TENS (n=13) groups. In the LJM group, grade III - IV amplitude was applied 3 times for 1 minute (80 times per minute) at the affected lumbar (L2-3) facet joint in the prone position. In the TENS group, the TENS treatment device was used to directly apply or 15 minutes to the area of chronic knee pain (100 Hz, 150 ㎲). Proprioception was measured by knee flexion and extension angles, and muscle strength was evaluated using an isokinetic test. Measurements were taken before and after interventions. Results: In the eye opened conditiond, proprioception significantly increased during both knee extension and flexion after LJM, while only knee extension was significantly increased in the TENS group. There was also a significant difference in knee extension between the two groups. In the eye close conditiond, proprioception was significantly improved only during knee extension in the LJM group, and the difference in knee extension between the groups was also significant (P<.05). The maximum torque of the affected knee joint was significantly improved at 60°/sec in both groups (P<.05); however, there was no difference between the two groups. There was no significant difference in the maximum flexion torque within or between the groups. Conclusion: This study suggests that LJM improved proprioception and muscular strength in volleyball players with chronic knee pain.

Background: Exercise is necessary for the health of companion dogs. It is necessary to determine the relationship between height, weight, age and amount of exercise for the purpose of companion dog's health. Objectives: A survey was conducted in this study to small-dog owners living in Yongin city, Gyeonggi-do about their canine healthcare awareness. Design: Questionnaire design. Methods: The questionnaire was composed of exercise amount, type of exercise, and the necessity of exercise, general health condition, and environment. A total of 139 survey results were obtained. The average value of each item was analyzed and expressed in terms of frequency and percentage. Then, Pearson's correlation coefficients were used to find the relationship between these items. Results: The weight and height were not shown to have a significant difference in the amount of exercise in the results. The weight had a weak positive correlation with “exercise time of canine per day”. The age had a weak negative correlation with “the number of canine exercise per week” and “frequency of canine exercise per day”, while it had a weak positive correlation with “selfassessment of canine lack of exercise”. Conclusion: Based on this study, it is believed that in the future, various environments where dogs can exercise are believed to be necessary for the era of convergence.

Background: Physical therapy applied to stroke patients is recognized as a treatment that promotes function recovery, and it is a widely known fact that constant exercise should be performed. However, there are insufficient studies on exercise intensity and exercise time that can minimize side effects and maximize function recovery for exercise therapy. Objectives: To determine the effect of exercise variables on CPK generation during aerobic exercise in stroke patients and to discover how to use appropriate exercise intensity and time when conducting an exercise for function recovery in stroke patients. Design: Quasi-experimental research. Methods: This study classified subjects into three groups (low-intensity exercise group: LIE, moderate-intensity exercise group: MIE and high-intensity exercise group: HIE) according to exercise intensity, and was further classified into two groups (10-minute exercise group: 10MG and 20-minute exercise group: 20MG) according to exercise time variables within each exercise intensity group. After, the change in CPK according to exercise intensity and time was confirmed through hematological analysis. Results: In LIE and MIE, the CPK blood concentrations before and after exercise were increased in 10MG and 20MG, which was not statistically significant (P>.05). In HIE, the CPK blood concentrations before and after exercise were increased in 10MG, and it was statistically significant (P<.05). In HIE, the CPK blood concentrations before and after exercise were increased in 20MG, and it was statistically significant (P<.01). In 10MG and 20MG, the CPK blood concentrations before and after exercises were increased in all intensity group, and there was a statistically significant difference only in HIE. Conclusion: From the results of this study, considering CPK, it will be helpful to recover and improve function if the exercise intensity setting is applied in the type of moderate intensity exercise during physical therapy interventions in stroke patients.

Background: Patients with lumbar spinal stenosis show abnormal changes in muscle activity due to pain and limited range of motion of the lumbar spine. Excessive increased muscle tone and decreased muscle activity patterns threaten the patients’ quality of life. However, there have been a few studies showing how to improve muscle performance in patients with lumbar spinal stenosis. Among these, joint mobilization is one way of improving muscle performance through pain relief and increasing the range of motion. Objectives: To investigate the effect of lumbar mobilization by orthopedic manual physical therapy on paravertebral muscle activity and tone in patients with lumbar spinal stenosis. Design: A randomized controlled trial. Methods: In this study, 24 patients with lumbar spinal stenosis were randomized (1:1 ratio) into two groups. The experimental group underwent lumbar posteroanterior mobilization, and the control group underwent conventional physical therapy (conventional transcutaneous electrical nerve stimulation) for 15 minutes each. For outcome measures, MyotonⓇPRO was used to evaluate muscle tone when resting of the paravertebral muscle in the pain area. For muscle activity evaluation, the reference voluntary contraction of the paravertebral muscle was evaluated using surface electromyography. Results: Muscle tone and activity were significantly improved after intervention in both the experimental and control groups. In addition, the experimental group showed more significant decrease in muscle tone and activity than the control group. Conclusion: These results suggest that lumbar mobilization improving muscle performance in patients with lumbar spinal stenosis.