Background: Artificial intelligence is being used for rehabilitation, including monitoring exercise compliance through sensor technology. AI classification of shoulder exercise wearing an IMU sensor has only been reported in normal (i.e. painless) subjects. To prove the feasibility of monitoring exercise compliance, we aimed to classify 11 types of shoulder rehabilitation exercises using an AI (artificial intelligence) algorithm in patients with shoulder pain. We had the patients wear an IMU-based sensor, collected data during exercise, and determined the accuracy of exercise classification. Methods: Data were collected from 58 patients (27 males, 31 females, age range 37–82 years) diagnosed with shoulder diseases such as adhesive capsulitis and rotator cuff disease. 11 types of shoulder pain rehabilitation exercise programs were developed and repeated each exercise ten times per session while wearing an IMU sensor. The study applied the Rectified Linear Unit (ReLU) and the SoftMax as the activation function for hidden layers, the output layer. Results: The acquired data was used to train a DNN model using the multilayer perceptron algorithm. The trained model was used to classify 11 types of shoulder pain rehabilitation exercises. The training accuracy was 0.975 and the test accuracy was 0.925. Conclusion: The study demonstrates that IMU sensor data can effectively classify shoulder pain rehabilitation exercises, providing more appropriate feedback for patients. The model can be utilized to establish a system for remotely monitoring patients’ exercise performance. The use of deep learning in patient monitoring and rehabilitation has significant potential to bring innovative changes to healthcare service delivery.

Gait disturbance is a common sequela of stroke. Conventional gait analysis has limitations in simultaneously assessing multiple joints. Therefore, we investigated the gait characteristics in stroke patients using hip-knee cyclograms, which have the advantage of simultaneously visualizing the gait kinematics of multiple joints. Stroke patients (n = 47) were categorized into two groups according to stroke severity, and healthy controls (n = 32) were recruited. An inertial measurement unit sensor-based gait analysis system, which requires placing seven sensors on the dorsum of both feet, the shafts of both tibias, the middle of both femurs, and the lower abdomen, was used for the gait analysis. Then, the hip-knee cyclogram parameters (range of motion, perimeter, and area) were obtained from the collected data. The coefficient of variance of the cyclogram parameters was obtained to evaluate gait variability. The cyclogram parameters differed between the stroke patients and healthy controls, and differences according to stroke severity were also observed. The gait variability parameters mainly differed in patients with more severe stroke, and specific visualized gait patterns of stroke patients were obtained through cyclograms. In conclusion, the hip-knee cyclograms, which show inter-joint coordination and visualized gait cycle in stroke patients, are clinically significant.

Objective To evaluate the efficacy and safety of mesenchymal stem cells (MSCs) therapy in patients with tendon disorders enrolled in prospective clinical studies.Methods We systematically searched prospective clinical studies that investigated the effects of MSC administration on human tendon disorders with at least a 6-month follow-up period in the PubMed-MEDLINE, EMBASE, and Cochrane Library databases. The primary outcome of interest was the change in pain on motion related to tendon disorders. Meta-regression analyses were performed to assess the relationship between MSC dose and pooled effect sizes in each cell dose.Results Four prospective clinical trials that investigated the effect of MSCs on tendon disorders were retrieved. MSCs showed a significant pooled effect size (overall Hedges’ g pooled standardized mean difference=1.868; 95% confidence interval, 1.274–2.462; p<0.001). The treatment with MSCs improved all the aspects analyzed, namely pain, functional scores, radiological parameters (magnetic resonance image or ultrasonography), and arthroscopic findings. In the meta-regression analysis, a significant cell dose-dependent response in pain relief (Q=9.06, p=0.029) was observed.Conclusion Our meta-analysis revealed that MSC therapy may improve pain, function, radiological, and arthroscopic parameters in patients with tendon disorders. A strong need for large-scale randomized controlled trials has emerged to confirm the long-term functional improvement and adverse effects of MSC therapies in tendon disorders.

Background: Although there have been many trials and interventions for reducing upper-extremity impairment in stroke survivors, it remains a challenge. A novel intervention is needed to provide high-repetition task-specific training early after stroke. Objective: This study aimed to investigate the effect of smart glove training (SGT) for upper-extremity rehabilitation in patients with subacute stroke. Methods: A prospective, multicenter, randomized, controlled study was conducted in patients with upper-extremity hemiparesis with Brunnstrom stage for arm 2–5 in the subacute phase after stroke. Eligible participants were randomly allocated to the SGT group or the control group. The SGT group underwent 30 min of standard occupational therapy plus 30 min of upper-extremity training with smart glove. The control group underwent standard occupational therapy for 30 min plus upper-extremity self-training (homework tasks at bedside) for 30 min. All participants underwent each intervention 5 days/week for 2 consecutive weeks. They were evaluated before, immediately after, and 4 weeks after the intervention. The primary outcome measure was the change in the score of the Fugl-Meyer assessment of the upper extremity (FMA-UE). Results: Twenty-three patients were enrolled. Repeated-measures analysis of covariance after controlling for age and disease duration showed significant time × group interaction effects in the FMA-UE, FMA-distal, and FMA-coordination/speed (p = 0.018, p = 0.002, p = 0.006). Repeated-measures analysis of variance showed significant time × group interaction effects in the FMA-UE, FMA-distal, and Box and Block Test (p = 0.034, p = 0.010, p = 0.046). Mann-Whitney U-test showed a statistically higher increase in the FMA-UE and FMA-distal in the SGT group than in the control group (p = 0.023, p = 0.032). Conclusion: Upper-extremity rehabilitation with a smart glove may reduce upper-extremity impairment in patients with subacute stroke. Clinical Trial Registration: ClinicalTrials.gov (NCT02592759).

Objective To develop a set of reference standards for tibial motor, common peroneal motor, sural sensory, and superficial peroneal sensory nerve conduction studies (NCSs) with expanded uncertainty in a healthy Korean population.Methods Standardized procedures were conducted for individual lower extremity NCSs of 199 healthy participants in their 20s (n=100) and 50s (n=99). Mean values and expanded uncertainties for parameters were analyzed with thorough consideration of multiple uncertainty factors under the International Guide to the Expression of Uncertainty in Measurement. In addition, side-to-side differences in onset latency, amplitude, and nerve conduction velocity (NCV) were analyzed.Results Mean (reference range) for distal onset latency, baseline to negative peak amplitude, NCV of tibial motor nerve in males in their 20s were 4.3 ms (3.1–5.4 ms), 7.1 mV (3.4–10.9 mV), and 50.7 m/s (42.2–59.3 m/s), respectively; sural sensory nerve baseline to negative peak amplitude in males in their 20s was 21.7 μV (8.3–35.2 μV). Including the aforementioned data, we present a vast dataset of normative mean values and expanded uncertainties for NCSs of the leg in a healthy Korean population. Furthermore, upper limits for normal side-to-side differences for onset latency, amplitude, and NCV of each nerve are suggested.Conclusion To our knowledge, this is the first study to present the reference standards of leg NCSs with consideration for multifactorial uncertainties in an Asian population. We expect these results to help practitioners make reliable and reproducible clinical decisions.