BackgroundClinical scores for evaluating walking skills with lower limb exoskeletons are often based on a single variable, such as distance walked or speed, even in cases where a host of features are measured. We investigated how to combine multiple features such that the resulting score has high discriminatory power, in particular with few patients. A new score is introduced that allows quantifying the walking ability of patients with spinal cord injury when using a powered exoskeleton.MethodsFour spinal cord injury patients were trained to walk over ground with the ReWalk™ exoskeleton. Body accelerations during use of the device were recorded by a wearable accelerometer and 4 features to evaluate walking skills were computed. The new score is the Gaussian naïve Bayes surprise, which evaluates patients relative to the features’ distribution measured in 7 expert users of the ReWalk™. We compared our score based on all the features with a standard outcome measure, which is based on number of steps only.ResultsAll 4 patients improved over the course of training, as their scores trended towards the expert users’ scores. The combined score (Gaussian naïve surprise) was considerably more discriminative than the one using only walked distance (steps). At the end of training, 3 out of 4 patients were significantly different from the experts, according to the combined score (p < .001, Wilcoxon Signed-Rank Test). In contrast, all but one patient were scored as experts when number of steps was the only feature.ConclusionIntegrating multiple features could provide a more robust metric to measure patients’ skills while they learn to walk with a robotic exoskeleton. Testing this approach with other features and more subjects remains as future work.

No abstract

No abstract

No abstract

Background and Purpose: Multimodal physical therapy for mild traumatic brain injury (mTBI) has been shown to improve recovery. Due to the coronavirus disease-2019 (COVID-19) pandemic, a clinical trial assessing the timing of multimodal intervention was adapted for telerehabilitation. This pilot study explored feasibility and adoption of an in-person rehabilitation program for subacute mTBI delivered through telerehabilitation. Methods: Fifty-six in-person participants—9 males; mean (SD) age 34.3 (12.2); 67 (31) days post-injury—and 17 telerehabilitation participants—8 males; age 38.3 (12.7); 61 (37) days post-injury—with subacute mTBI (between 2 and 12 weeks from injury) were enrolled. Intervention included 8, 60-minute visits over 6 weeks and included subcategories that targeted cervical spine, cardiovascular, static balance, and dynamic balance impairments. Telerehabilitation was modified to be safely performed at home with minimal equipment. Outcome measures included feasibility (the number that withdrew from the study, session attendance, home exercise program adherence, adverse events, telerehabilitation satisfaction, and progression of exercises performed), and changes in mTBI symptoms pre- and post-rehabilitation were estimated with Hedges' g effect sizes. Results: In-person and telerehabilitation had a similar study withdrawal rate (13% vs 12%), high session attendance (92% vs 97%), and no adverse events. The telerehabilitation group found the program easy to use (4.2/5), were satisfied with care (4.7/5), and thought it helped recovery (4.7/5). The telerehabilitation intervention was adapted by removing manual therapy and cardiovascular portions and decreasing dynamic balance exercises compared with the in-person group. The in-person group had a large effect size (−0.94) in decreases in symptoms following rehabilitation, while the telerehabilitation group had a moderate effect size (−0.73). Discussion and Conclusions: Telerehabilitation may be feasible for subacute mTBI. Limited ability to address cervical spine, cardiovascular, and dynamic balance domains along with underdosage of exercise progression may explain group differences in symptom resolution. Video Abstract available for more insights from the authors (see the Video, Supplemental Digital Content 1, available at: http://links.lww.com/JNPT/A392).