Neurorehabilitation is progressively shifting from purely in-clinic treatment to therapy that is provided in both clinical and home-based settings. This transition generates a pressing need for assessments that can be performed across the entire continuum of care, a need that might be accommodated by application of wearable sensors. A first step toward ubiquitous assessments is to augment validated and well-understood standard clinical tests. This route has been pursued for the assessment of motor functioning, which in clinical research and practice is observation-based and requires specially trained personnel. In our study, 21 patients performed movement tasks of the Action Research Arm Test (ARAT), one of the most widely used clinical tests of upper limb motor functioning, while trained evaluators scored each task on pre-defined criteria. We collected data with just two wrist-worn inertial sensors to guarantee applicability across the continuum of care and used machine learning algorithms to estimate the ARAT task scores from sensor-derived features. Tasks scores were classified with approximately 80% accuracy. Linear regression between summed clinical task scores (across all tasks per patient) and estimates of sum task scores yielded a good fit (R² = 0.93; range reported in previous studies: 0.61–0.97). Estimates of the sum scores showed a mean absolute error of 2.9 points, 5.1% of the total score, which is smaller than the minimally detectable change and minimally clinically important difference of the ARAT when rated by a trained evaluator. We conclude that it is feasible to obtain accurate estimates of ARAT scores with just two wrist worn sensors. The approach enables administration of the ARAT in an objective, minimally supervised or remote fashion and provides the basis for a widespread use of wearable sensors in neurorehabilitation.

Spinal cord injury (SCI) patients suffer from diverse gait deficits depending on the severity of their injury. Gait assessments can objectively track the progress during rehabilitation and support clinical decision making, but a comprehensive gait analysis requires far more complex setups and time-consuming protocols that are not feasible in the daily clinical routine. As using inertial sensors for mobile gait analysis has started to gain ground, this work aimed to develop a sensor-based gait analysis for the specific population of SCI patients that measures the spatio-temporal parameters of typical gait laboratories for day-to-day clinical applications. The proposed algorithm uses shank-mounted inertial sensors and personalized thresholds to detect steps and gait events according to the individual gait profiles. The method was validated in nine SCI patients and 17 healthy controls walking on an instrumented treadmill while wearing reflective markers for motion capture used as a gold standard. The sensor-based algorithm (i) performed similarly well for the two cohorts and (ii) is robust enough to cover the diverse gait deficits of SCI patients, from slow (0.3 m/s) to preferred walking speeds.

Background: An incomplete spinal cord injury (SCI) refers to remaining sensorimotor function below the injury with the possibility for the patient to regain walking abilities. However, these patients often suffer from diverse gait deficits, which are not objectively assessed in the current clinical routine. Wearable inertial sensors are a promising tool to capture gait patterns objectively and started to gain ground for other neurological disorders such as stroke, multiple sclerosis, and Parkinson’s disease. In this work, we present a data-driven approach to assess walking for SCI patients based on sensor-derived outcome measures. We aimed to (i) characterize their walking pattern in more depth by identifying groups with similar walking characteristics and (ii) use sensor-derived gait parameters as predictors for future walking capacity. Methods: The dataset analyzed consisted of 66 SCI patients and 20 healthy controls performing a standardized gait test, namely the 6-min walking test (6MWT), while wearing a sparse sensor setup of one sensor attached to each ankle. A data-driven approach has been followed using statistical methods and machine learning models to identify relevant and non-redundant gait parameters. Results: Clustering resulted in 4 groups of patients that were compared to each other and to the healthy controls. The clusters did differ in terms of their average walking speed but also in terms of more qualitative gait parameters such as variability or parameters indicating compensatory movements. Further, using longitudinal data from a subset of patients that performed the 6MWT several times during their rehabilitation, a prediction model has been trained to estimate whether the patient’s walking speed will improve significantly in the future. Including sensor-derived gait parameters as inputs for the prediction model resulted in an accuracy of 80%, which is a considerable improvement of 10% compared to using only the days since injury, the present 6MWT distance, and the days until the next 6MWT as predictors. Conclusions: In summary, the work presented proves that sensor-derived gait parameters provide additional information on walking characteristics and thus are beneficial to complement clinical walking assessments of SCI patients. This work is a step towards a more deficit-oriented therapy and paves the way for better rehabilitation outcome predictions.

There is a high prevalence of shoulder problems in manual wheelchair users (MWUs) with a spinal cord injury. How shoulder load relates to shoulder problems remains unclear. This study aimed to develop a machine-learning-based methodology to estimate the shoulder load in wheelchair-related activities of daily living using wearable sensors. Ten able-bodied participants equipped with five inertial measurement units (IMU) on their thorax, right arm, and wheelchair performed activities exemplary of daily life of MWUs. Electromyography (EMG) was recorded from the long head of the biceps and medial part of the deltoid. A neural network was trained to predict the shoulder load based on IMU and EMG data. Different cross-validation strategies, sensor setups, and model architectures were examined. The predicted shoulder load was compared to the shoulder load determined with musculoskeletal modeling. A subject-specific biLSTM model trained on a sparse sensor setup yielded the most promising results (mean correlation coefficient = 0.74 ± 0.14, relative root-mean-squared error = 8.93% ± 2.49%). The shoulder-load profiles had a mean similarity of 0.84 ± 0.10 over all activities. This study demonstrates the feasibility of using wearable sensors and neural networks to estimate the shoulder load in wheelchair-related activities of daily living.

Introduction Shoulder problems like pain or pathology are highly prevalent in manual wheelchair users (MWU) with spinal cord injury, lead to limitations in participation, a reduced quality of life and are often associated with “shoulder overload” (Mercer et al., 2006). Laboratory based experiments have examined shoulder load for a variety of wheelchair related activities (WRA; van Drongelen et al., 2005), but no research has been conducted that investigates the actual shoulder load profile of MWU’s in daily conditions. Such a profile would help in understanding the relation of shoulder overload and shoulder problems and could thereby support clinical decision making in the prevention of shoulder problems. Inspired by recent work on machine learning (ML) prediction of joint load from wearable sensors, the current project's ultimate aim is to develop a generalizable ML algorithm that can predict shoulder load for a variety of WRA. Methods 10 able bodied participants were trained before the actual measurement of the WRA of interest: wheelchair propulsion (WCP) at 0.56 and 1.1 m/s at 0%, 0.56 m/s at 6%, WCP in restricted space, short ramp 12% up and down, weight relieve lift, manual material handling with 2 kg and desk work. Participants were equipped with five Shimmer3 sensors on wheelchair, wheel, thorax, upper arm and forearm; EMG was collected from the biceps and medial deltoid muscles. An 8 camera Qualisys system was used to obtain kinematics conform ISB recommendations (Wu et al., 2005). A SmartWheel (Out-Front) for collecting propulsion kinetics replaced the original wheel of a standard Kuschal wheelchair. From laboratory kinematics and kinetics 3D shoulder joint reaction forces (JRF) were estimated with an OpenSim based musculoskeletal model (Wu et al., 2016) (MSM), which consequently served as target for the training of a variety of ML algorithms, using sensor data (acceleration, angular velocity, EMG) as input. Results & Discussion Starting with simple input (upper arm sensors only) and a linear neural network (NN, one input, one hidden, one output layer for total JRF; iteratively trained following a Leave One Subject Out approach, a R² of around 60% was obtained between predicted JRF (NN) and target (MSM output), but results varied considerably over participants. In a next phase the complexity of the ML models was increased to deep learning models (recurrent NN) and more signals (e.g. forearm and thorax sensors) were added to the input, which, however, did not improve the overall performance considerably. Currently, it is explored whether using training the algorithms on individual datasets, for single tasks, can improve the performance. The explorative process will be presented and discussed in the light of the relevant results. References Mercer, J. L., Boninger, M., Koontz, A., Ren, D., Dyson-Hudson, T., & Cooper, R. (2006). Shoulder joint kinetics and pathology in manual wheelchair users. Clincal Biomechanics, 21(8), 781-789. https://doi.org/10.1016/j.clinbiomech.2006.04.010 van Drongelen, S., van der Woude, L. H., Janssen, T. W., Angenot, E. L., Chadwick, E. K., & Veeger, D. H. (2005). Glenohumeral contact forces and muscle forces evaluated in wheelchair-related activities of daily living in able-bodied subjects versus subjects with paraplegia and tetraplegia. Archives of Physical Medicine and Rehabilitation, 86(7), 1434-1440. https://doi.org/10.1016/j.apmr.2005.03.014 Wu, W., Lee, P. V. S., Bryant, A. L., Galea, M., & Ackland, D. C. (2016). Subject-specific musculoskeletal modeling in the evaluation of shoulder muscle and joint function. Journal of Biomechanics, 49(15), 3626-3634. https://doi.org/10.1016/j.jbiomech.2016.09.025 Wu, G., van der Helm, F. C., Veeger, H. E., Makhsous, M., Van Roy, P., Anglin, C., Nagels, J., Karduna, A. R., McQuade, K., Wang, X., Werner, F. W., Buchholz, B., & International Society of, B. (2005). ISB recommendation on definitions of joint coordinate systems of various joints for the reporting of human joint motion-Part II: Shoulder, elbow, wrist and hand. Journal of Biomechanics, 38(5), 981-992. https://doi.org/10.1016/j.jbiomech.2004.05.042