Shape Memory Alloy-Based Reactive Tubular (SMART) Brake for Compact and Energy-Efficient Wearable Robot Design.

Soft wearable robots have been gaining increasing popularity for enhancing human physical abilities and assisting people who have physical limitations. These robots typically use tendon-driven mechanisms (TDMs) to enable remote actuation to provide better usability with compact design. TDMs comprise an actuator, an end-effector, and a transmission system by using cables or tendons to transfer forces from the actuator to the end-effector. Tendons are typically routed by frictionless guiding tubes to minimize force losses, variations in the force direction, and the volume. To make soft wearable robots even smaller, brakes need to be compacted because brakes are irreplaceable to ensure safety and energy efficiency. This study presents a shape memory alloy-based reactive tubular (SMART) brake for designing a compact and portable TDM-based device. The SMART brake actively adjusts the friction force between the brake and tendon, making it easy to achieve the desired friction state, ranging from low-friction states for free movement to high-friction states for effective braking. The brake is designed in a tubular shape, serving multifunctions as both a brake and a guiding tube. The brake's performance and theoretical model were validated through experiments and demonstrated by two wearable devices. The brake could hold a significant brake force of 19.37 N/11 mm while weighing only 0.3 g. These findings have major implications for the future development of TDM-based devices and soft wearable robots, paving the way for enhanced system portability, safety, and energy efficiency.

Comparative Analysis of Muscle Synergy between Patients with Shoulder Impingement Syndrome and Healthy Controls: A Preliminary Study.

Shoulder impingement syndrome can be caused by a muscle imbalance around the shoulder joint. It would be beneficial for therapy to implement rehabilitation exercises based on intermuscular coordination in order to achieve muscle balance. This study presents the muscle synergy characteristics of patients with shoulder impingement syndrome, which can be used to develop rehabilitation exercises. During pick and place task, the muscle synergy obtained from eight shoulder muscles in patients and healthy subjects was compared. The experimental results revealed that patients have low contributed muscle synergy structures for the serratus anterior and infraspinatus.Clinical relevance- This proposes that patients with shoulder impingement syndrome may have abnormal muscle synergy structure which can be used for assessment.

Development and Clinical Evaluation of a Web-Based Upper Limb Home Rehabilitation System Using a Smartwatch and Machine Learning Model for Chronic Stroke Survivors: Prospective Comparative Study.

BACKGROUND: Recent advancements in wearable sensor technology have shown the feasibility of remote physical therapy at home. In particular, the current COVID-19 pandemic has revealed the need and opportunity of internet-based wearable technology in future health care systems. Previous research has shown the feasibility of human activity recognition technologies for monitoring rehabilitation activities in home environments; however, few comprehensive studies ranging from development to clinical evaluation exist. OBJECTIVE: This study aimed to (1) develop a home-based rehabilitation (HBR) system that can recognize and record the type and frequency of rehabilitation exercises conducted by the user using a smartwatch and smartphone app equipped with a machine learning (ML) algorithm and (2) evaluate the efficacy of the home-based rehabilitation system through a prospective comparative study with chronic stroke survivors. METHODS: The HBR system involves an off-the-shelf smartwatch, a smartphone, and custom-developed apps. A convolutional neural network was used to train the ML algorithm for detecting home exercises. To determine the most accurate way for detecting the type of home exercise, we compared accuracy results with the data sets of personal or total data and accelerometer, gyroscope, or accelerometer combined with gyroscope data. From March 2018 to February 2019, we conducted a clinical study with two groups of stroke survivors. In total, 17 and 6 participants were enrolled for statistical analysis in the HBR group and control group, respectively. To measure clinical outcomes, we performed the Wolf Motor Function Test (WMFT), Fugl-Meyer Assessment of Upper Extremity, grip power test, Beck Depression Inventory, and range of motion (ROM) assessment of the shoulder joint at 0, 6, and 12 months, and at a follow-up assessment 6 weeks after retrieving the HBR system. RESULTS: The ML model created with personal data involving accelerometer combined with gyroscope data (5590/5601, 99.80%) was the most accurate compared with accelerometer (5496/5601, 98.13%) or gyroscope data (5381/5601, 96.07%). In the comparative study, the drop-out rates in the control and HBR groups were 40% (4/10) and 22% (5/22) at 12 weeks and 100% (10/10) and 45% (10/22) at 18 weeks, respectively. The HBR group (n=17) showed a significant improvement in the mean WMFT score (P=.02) and ROM of flexion (P=.004) and internal rotation (P=.001). The control group (n=6) showed a significant change only in shoulder internal rotation (P=.03). CONCLUSIONS: This study found that a home care system using a commercial smartwatch and ML model can facilitate participation in home training and improve the functional score of the WMFT and shoulder ROM of flexion and internal rotation in the treatment of patients with chronic stroke. This strategy can possibly be a cost-effective tool for the home care treatment of stroke survivors in the future. TRIAL REGISTRATION: Clinical Research Information Service KCT0004818; https://tinyurl.com/y92w978t.

Optimal Time-Window Derivation for Human-Activity Recognition Based on Convolutional Neural Networks of Repeated Rehabilitation Motions.

This paper analyses the time-window size required to achieve the highest accuracy of the convolutional neural network (CNN) in classifying periodic upper limb rehabilitation. To classify real-time motions by using CNN-based human activity recognition (HAR), data must be segmented using a time window. In particular, for the repetitive rehabilitation tasks, the relationship between the period of the repetitive tasks and optimal size of the time window must be analyzed. In this study, we constructed a data-collection system composed of a smartwatch and smartphone. Five upper limb rehabilitation motions were measured for various periods to classify the rehabilitation motions for a particular time-window size. 5-fold cross-validation technique was used to compare the performance. The results showed that the size of the time-window that maximizes the performance of CNN-based HAR is affected by the size and period of the sample used.

Design and Evaluation of Passive Shoulder Joint Tracking Module for Upper-Limb Rehabilitation Robots.

As the number of people suffering from shoulder movement disabilities increases, there is a rising demand for shoulder rehabilitation. The natural motion of the shoulder joint [glenohumeral (GH) joint] includes not only three-degrees-of-freedom (DOF) rotation but also three-DOF translation of the joint center due to simultaneous motion of the shoulder girdle. If the motion of the shoulder girdle is restricted, then the arm cannot be raised above a certain posture. This paper presents a passive shoulder joint tracking device that allows three-DOF translation of the shoulder joint while compensating for gravity. The single-DOF vertical tracker with a constant-force spring compensates for the gross weight of the user's arm, the upper limb rehabilitation device, and the tracker itself while allowing vertical tracking motion. The two-DOF horizontal tracker consists of two linear guides arranged perpendicular to each other. The tracker freely follows the shoulder joint in the horizontal plane. The effect of using the passive shoulder joint tracking device was evaluated by means of experiments by combining two popular commercial upper limb rehabilitation apparatuses with the proposed tracker. Nineteen subjects (8 healthy persons and 11 patients with shoulder impairments) participated in the evaluation study. The movement of the GH joint and the interactive force between the subject and the commercial rehabilitation device were analyzed when subjects made the following shoulder movements: flexion/extension and abduction/adduction. The improved tracker allowed a greater range of motion and reduced interaction. The tracker can be combined with existing commercial rehabilitation devices for more natural shoulder movement during rehabilitation tasks.

A Novel Approach to Calculating Small Intestine Length Based on Magnetic Resonance Enterography.

BACKGROUND: Bowel length is an important factor in the management of patients with intestinal failure and short bowel syndrome. However, it is difficult to accurately measure the length of the small intestine. Our aim was to demonstrate the feasibility of a dedicated software algorithm for calculating small intestine length based on magnetic resonance enterography (MRE) images. STUDY DESIGN: A custom algorithm for image thresholding, wall identification, segmentation, and path extraction was designed and implemented. Algorithm output included the Euclidean distance from the pylorus to the terminal ileum and coordinates of points along that route. For validation, 10 C57BL/6 mice underwent bowel preparation before MRE. After sacrifice, the entire small bowel was removed and the ex vivo small intestine length was measured in a standardized manner. Calculated and ex vivo length measurements were compared. RESULTS: Mean absolute difference and mean percentage difference between the 2 modalities were 1.8 ± 3.8 cm (p = 0.24) and 9.4% ± 6.0%, respectively. CONCLUSIONS: This study demonstrates the feasibility of a dedicated, computer-vision-based algorithm that can reliably and accurately calculate the length of the small intestine using MRE images. A validated, noninvasive approach to measuring small intestine length that can be implemented using available clinical imaging can have a dramatic clinical impact on management in patients with short bowel syndrome, Crohn's disease, and other intestinal disorders.