An official website of the United States government
BackgroundLow back pain (LBP) is a costly global health condition that affects individuals of all ages and genders. Physical therapy (PT) is a commonly used and effective intervention for the management of LBP and incorporates movement assessment and therapeutic exercise. A newly developed wearable, fabric-based sensor system, Motion Tape, uses novel sensing and data modeling to measure lumbar spine movements unobtrusively and thus offers potential benefits when used in conjunction with PT. However, physical therapists’ acceptance of Motion Tape remains unexplored. ObjectiveThe primary aim of this research study was to evaluate physical therapists’ acceptance of Motion Tape to be used for the management of LBP. The secondary aim was to explore physical therapists’ recommendations for future device development. MethodsLicensed physical therapists from the American Physical Therapy Association Academy of Leadership Technology Special Interest Group participated in this study. Overall, 2 focus groups (FGs; N=8) were conducted, in which participants were presented with Motion Tape samples and examples of app data output on a poster. Informed by the Technology Acceptance Model, we conducted semistructured FGs and explored the wearability, usefulness, and ease of use of and suggestions for improvements in Motion Tape for PT management of LBP. FG data were transcribed and analyzed using rapid qualitative analysis. ResultsRegarding wearability, participants perceived that Motion Tape would be able to adhere for several days, with some variability owing to external factors. Feedback was positive for the low-profile and universal fit, but discomfort owing to wires and potential friction with clothing was of concern. Other concerns included difficulty with self-application and potential skin sensitivity. Regarding usefulness, participants expressed that Motion Tape would enhance the efficiency and specificity of assessments and treatment. Regarding ease of use, participants stated that the app would be easy, but data management and challenges with interpretation were of concern. Physical therapists provided several recommendations for future design improvements including having a wireless system or removable wires, customizable sizes for the tape, and output including range of motion data and summary graphs and adding app features that consider patient input and context. ConclusionsSeveral themes related to Motion Tape’s wearability, usefulness, and ease of use were identified. Overall, physical therapists expressed acceptance of Motion Tape’s potential for assessing and monitoring low back posture and movement, both within and outside clinical settings. Participants expressed that Motion Tape would be a valuable tool for the personalized treatment of LBP but highlighted several future improvements needed for Motion Tape to be used in practice.
more »
« less
This content will become publicly available on December 1, 2027
Automatic multi-IMU-based deep learning evaluation of intensity during static standing balance training exercises
Abstract BackgroundEffective balance rehabilitation requires training at an appropriate level of exercise intensity given an individual’s needs and abilities. Typically balance intensity is assessed through in-clinic visual observation by physical therapists (PTs), which limits the ability to monitor and progress intensity during home-based components of training programs. The goal of this study was to train and evaluate machine learning models for estimating physical therapists’ perceived balance exercise intensity using data from full-body wearable sensors to support the development of home-based training exercise dosage monitoring. MethodsBalance exercise participants (n = 47) participated in a single-day balance training session where they were filmed performing static standing exercises at various levels of intensity. Kinematic data from 13 full-body wearable inertial measurement units (IMUs) and self-ratings of balance intensity were also collected. An additional cohort of PT participants (n = 42) was recruited to watch the videos of the balance exercise participants and provide ratings of balance intensity. The mean PT rating for each video was used as a ground truth (GT) label of balance intensity. We trained and evaluated Convolutional Neural Networks (CNN)-based models to predict balance intensity based on performance as captured through the IMUs. Model performance was evaluated by calculating the root-mean-square error (RMSE) of predications. A sensitivity analysis was also performed to assess the effect of the number of IMUs used on model performance. ResultsModels trained on orientation derived from all 13 IMUs achieved good predictive performance as indicated by a RMSE of 0.66 [0.62, 0.69], which was within the threshold defined by typical inter-rater variabilities between PTs (RMSE of 0.74 [0.72, 0.76]). Sensitivity analysis indicated that model performance stabilized at four sensors with the best performance corresponding to sensors placed on both thighs and the lower and upper back. ConclusionsFindings from this study indicated that balance intensity assessment can be achieved through wearable sensors and a CNN model, which could support the supervision and effectiveness of home-based balance rehabilitation.
more »
« less
- Award ID(s):
- 2125256
- PAR ID:
- 10698024
- Publisher / Repository:
- Springer Nature / BMC
- Date Published:
- Journal Name:
- Journal of NeuroEngineering and Rehabilitation
- Volume:
- 23
- Issue:
- 1
- ISSN:
- 1743-0003
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Physical therapy is often essential for complete recovery after injury. However, a significant population of patients fail to adhere to prescribed exercise regimens. Lack of motivation and inconsistent in-person visits to physical therapy are major contributing factors to suboptimal exercise adherence, slowing the recovery process. With the advancement of virtual reality (VR), researchers have developed remote virtual rehabilitation systems with sensors such as inertial measurement units. A functional garment with an integrated wearable sensor can also be used for real-time sensory feedback in VR-based therapeutic exercise and offers affordable remote rehabilitation to patients. Sensors integrated into wearable garments offer the potential for a quantitative range of motion measurements during VR rehabilitation. In this research, we developed and validated a carbon nanocomposite-coated knit fabric-based sensor worn on a compression sleeve that can be integrated with upper-extremity virtual rehabilitation systems. The sensor was created by coating a commercially available weft knitted fabric consisting of polyester, nylon, and elastane fibers. A thin carbon nanotube composite coating applied to the fibers makes the fabric electrically conductive and functions as a piezoresistive sensor. The nanocomposite sensor, which is soft to the touch and breathable, demonstrated high sensitivity to stretching deformations, with an average gauge factor of ~35 in the warp direction of the fabric sensor. Multiple tests are performed with a Kinarm end point robot to validate the sensor for repeatable response with a change in elbow joint angle. A task was also created in a VR environment and replicated by the Kinarm. The wearable sensor can measure the change in elbow angle with more than 90% accuracy while performing these tasks, and the sensor shows a proportional resistance change with varying joint angles while performing different exercises. The potential use of wearable sensors in at-home virtual therapy/exercise was demonstrated using a Meta Quest 2 VR system with a virtual exercise program to show the potential for at-home measurements.more » « less
-
Accurate estimation of upper-limb joint angles is essential in biomechanics, rehabilitation, and wearable robotics. While inertial measurement units (IMUs) offer portability and flexibility, systems requiring multiple inertial sensors can be intrusive and complex to deploy. In contrast, optical motion capture (MoCap) systems provide precise tracking but are constrained to controlled laboratory environments. This study presents a deep learning-based approach for estimating shoulder and elbow joint angles using only three IMU sensors positioned on the chest and both wrists, validated against reference angles obtained from a MoCap system. The input data includes Euler angles, accelerometer, and gyroscope data, synchronized and segmented into sliding windows. Two recurrent neural network architectures, Convolutional Neural Network with Long-short Term Memory (CNN-LSTM) and Bidirectional LSTM (BLSTM), were trained and evaluated using identical conditions. The CNN component enabled the LSTM to extract spatial features that enhance sequential pattern learning, improving angle reconstruction. Both models achieved accurate estimation performance: CNN-LSTM yielded lower Mean Absolute Error (MAE) in smooth trajectories, while BLSTM provided smoother predictions but underestimated some peak movements, especially in the primary axes of rotation. These findings support the development of scalable, deep learning-based wearable systems and contribute to future applications in clinical assessment, sports performance analysis, and human motion research.more » « less
-
Abstract IntroductionHigh-intensity gait training is widely recognized as an effective rehabilitation approach after stroke. Soft robotic exosuits that enhance post-stroke gait mechanics have the potential to improve the rehabilitative outcomes achieved by high-intensity gait training. The objective of thisdevelopment-of-conceptpilot crossover study was to evaluate the outcomes achieved by high-intensity gait training with versus without soft robotic exosuits. MethodsIn this 2-arm pilot crossover study, four individuals post-stroke completed twelve visits of speed-based, high-intensity gait training: six consecutive visits of Robotic Exosuit Augmented Locomotion (REAL) gait training and six consecutive visits without the exosuit (CONTROL). The intervention arms were counterbalanced across study participants and separated by 6 + weeks of washout. Walking function was evaluated before and after each intervention using 6-minute walk test (6MWT) distance and 10-m walk test (10mWT) speed. Moreover, 10mWT speeds were evaluated before each training visit, with the time-course of change in walking speed computed for each intervention arm. For each participant, changes in each outcome were compared to minimal clinically-important difference (MCID) thresholds. Secondary analyses focused on changes in propulsion mechanics and associated biomechanical metrics. ResultsLarge between-group effects were observed for 6MWT distance (d = 1.41) and 10mWT speed (d = 1.14). REAL gait training resulted in an average pre-post change of 68 ± 27 m (p = 0.015) in 6MWT distance, compared to a pre-post change of 30 ± 16 m (p = 0.035) after CONTROL gait training. Similarly, REAL training resulted in a pre-post change of 0.08 ± 0.03 m/s (p = 0.012) in 10mWT speed, compared to a pre-post change of 0.01 ± 06 m/s (p = 0.76) after CONTROL. For both outcomes, 3 of 4 (75%) study participants surpassed MCIDs after REAL training, whereas 1 of 4 (25%) surpassed MCIDs after CONTROL training. Across the training visits, REAL training resulted in a 1.67 faster rate of improvement in walking speed. Similar patterns of improvement were observed for the secondary gait biomechanical outcomes, with REAL training resulting in significantly improved paretic propulsion for 3 of 4 study participants (p < 0.05) compared to 1 of 4 after CONTROL. ConclusionSoft robotic exosuits have the potential to enhance the rehabilitative outcomes produced by high-intensity gait training after stroke. Findings of thisdevelopment-of-conceptpilot crossover trial motivate continued development and study of the REAL gait training program.more » « less
-
BackgroundStroke therapy is essential to reduce impairments and improve motor movements by engaging autogenous neuroplasticity. Traditionally, stroke rehabilitation occurs in inpatient and outpatient rehabilitation facilities. However, recent literature increasingly explores moving the recovery process into the home and integrating technology-based interventions. This study advances this goal by promoting in-home, autonomous recovery for patients who experienced a stroke through robotics-assisted rehabilitation and classifying stroke residual severity using machine learning methods. ObjectiveOur main objective is to use kinematics data collected during in-home, self-guided therapy sessions to develop supervised machine learning methods, to address a clinician’s autonomous classification of stroke residual severity–labeled data toward improving in-home, robotics-assisted stroke rehabilitation. MethodsIn total, 33 patients who experienced a stroke participated in in-home therapy sessions using Motus Nova robotics rehabilitation technology to capture upper and lower body motion. During each therapy session, the Motus Hand and Motus Foot devices collected movement data, assistance data, and activity-specific data. We then synthesized, processed, and summarized these data. Next, the therapy session data were paired with clinician-informed, discrete stroke residual severity labels: “no range of motion (ROM),” “low ROM,” and “high ROM.” Afterward, an 80%:20% split was performed to divide the dataset into a training set and a holdout test set. We used 4 machine learning algorithms to classify stroke residual severity: light gradient boosting (LGB), extra trees classifier, deep feed-forward neural network, and classical logistic regression. We selected models based on 10-fold cross-validation and measured their performance on a holdout test dataset using F1-score to identify which model maximizes stroke residual severity classification accuracy. ResultsWe demonstrated that the LGB method provides the most reliable autonomous detection of stroke severity. The trained model is a consensus model that consists of 139 decision trees with up to 115 leaves each. This LGB model boasts a 96.70% F1-score compared to logistic regression (55.82%), extra trees classifier (94.81%), and deep feed-forward neural network (70.11%). ConclusionsWe showed how objectively measured rehabilitation training paired with machine learning methods can be used to identify the residual stroke severity class, with efforts to enhance in-home self-guided, individualized stroke rehabilitation. The model we trained relies only on session summary statistics, meaning it can potentially be integrated into similar settings for real-time classification, such as outpatient rehabilitation facilities.more » « less
