Search

Artificial intelligence (AI) tools are increasingly able to learn from larger and more complex data, thus allowing clinicians and scientists to gain new insights from the information they collect about their patients every day. In rehabilitation medicine, AI can be used to find patterns in huge amounts of healthcare data. These patterns can then be leveraged at the individual level, to design personalized care strategies and interventions to optimize each patient's outcomes. However, building effective AI tools requires many careful considerations about how we collect and handle data, how we train the models, and how we interpret results. In this perspective, we discuss some of the current opportunities and challenges for AI in rehabilitation. We first review recent trends in AI for the screening, diagnosis, treatment, and continuous monitoring of disease or injury, with a special focus on the different types of healthcare data used for these applications. We then examine potential barriers to designing and integrating AI into the clinical workflow, and we propose an end-to-end framework to address these barriers and guide the development of effective AI for rehabilitation. Finally, we present ideas for future work to pave the way for AI implementation in real-world rehabilitation practices. [ABSTRACT FROM AUTHOR]

Abstract Purpose Materials and methods Results Conclusions Muscle activation often occurs in muscles ipsilateral to a voluntarily activated muscle and to a greater extent after stroke. In this study, we measured muscle activation in non-target, ipsilateral leg muscles and used transcranial magnetic stimulation (TMS) to provide insight into whether corticomotor pathways contribute to involuntary activation.Individuals with stroke performed unilateral isometric ankle dorsiflexion, ankle plantarflexion, knee extension, and knee flexion. To quantify involuntary muscle activation in non-target muscles, muscle activation was measured during contractions from the ipsilateral tibialis anterior (TA), medial gastrocnemius (MG), rectus femoris (RF), and biceps femoris (BF) and normalized to resting muscle activity. To provide insight into mechanisms of involuntary non-target muscle activation, TMS was applied to the contralateral hemisphere, and motor evoked potentials (MEPs) were recorded.We found significant muscle activation in nearly every non-target muscle during isometric unilateral contractions. MEPs were frequently observed in non-target muscles, but greater non-target MEP amplitude was not associated with greater non-target muscle activation.Our results suggest that non-target muscle activation occurs frequently in individuals with chronic stroke. The lack of association between non-target TMS responses and non-target muscle activation suggests that non-target muscle activation may have a subcortical or spinal origin. Non-target muscle activation has important clinical implications because it may impair torque production, out-of-synergy movement, and muscle activation timing. [ABSTRACT FROM AUTHOR]

Extracorporeal membrane oxygenation (ECMO) refers to specific mechanical devices used to temporarily support the failing heart and/or lung. Technological advances as well as growing collective knowledge and experience have resulted in increased ECMO use and improved outcomes. Veno-arterial (VA) ECMO is used in selected patients with various etiologies of cardiogenic shock and entails either central or peripheral cannulation. Central cannulation is frequently used in postcardiotomy cardiogenic shock and is associated with improved venous drainage and reduced concern for upper body hypoxemia as compared to peripheral cannulation. These concerns inherent to peripheral VA ECMO may be addressed through so-called triple cannulation approaches. Veno-venous (VV) ECMO is increasingly employed in selected patients with respiratory failure refractory to more conventional measures. Newer dual lumen VV ECMO cannulas may facilitate extubation and mobilization. In summary, the pathology being addressed impacts the ECMO approach that is deployed, and each ECMO implementation has distinct virtues and drawbacks. Understanding these considerations is crucial to safe and effective ECMO use. [ABSTRACT FROM AUTHOR]

Background and Purpose. Community mobility of individuals following lower limb amputation is highly variable and has a great impact on their quality of life. Currently, clinical assessments of ambulatory ability and motivation influence prosthetic prescription. However, these outcome measures do not effectively quantify community mobility (ie, mobility outside of the clinic) of individuals with an amputation. Advances in global positioning systems (GPSs) and other wearable step- monitoring devices allow for objective, quantifiable measurement of community mobility. This case report will examine the combined use of a GPS unit and a step activity monitor to quantify community mobility and social interaction of an individual with transfemoral amputation due to dysvascular disease. Case Description. A 76-year-old woman with a unilateral transfemoral amputation due to vascular disease carried a commercial GPS unit and step activity monitor to quantify her community mobility and social interaction every day over a period of 1 month. The step activity monitor was affixed to her prosthesis. The patient used a wheelchair as well as her prosthesis for everyday mobility. Outcome. Information from the GPS unit and step activity monitor provided quantitative details on the patient's steps taken in and out of the home, wheelchair use, prosthesis use, driving trips, and time spent on social and community trips. Discussion. This case report describes a potential clinical measurement procedure for quantifying community mobility and social interaction of an individual with lower limb amputation. Future efforts are needed to validate this measurement tool on large sample sizes and in individuals with different mobility levels. Additionally, automatization of data analysis and technological approaches to reduce compromised GPS signals may eventually lead to a practical, clinically useful tool. [ABSTRACT FROM AUTHOR]

The aim of this study was to use the rat moderate spinal cord contusion model to investigate the effects of incomplete spinal cord injury (SCI) on the muscle regeneration process, comparing regeneration of slow-twitch plantarflexor soleus muscle and fast-twitch dorsiflexor tibialis anterior (TA) muscle. Additionally, we wanted to examine the effect of a week of locomotor training following incomplete SCI on the muscle regeneration process in these muscles and also determine if a week of similar locomotor training is sufficient to initiate muscle regeneration in control, non-injured rats. Thirty-two, adult, female, Sprague-Dawley rats were chosen for the study. Moderate, midthoracic contusion SCIs were produced using a NYU (New York University) impactor in all rats except controls. Animals were randomly assigned to treadmill training or untrained groups. Rats in the treadmill training group were manually treadmill trained starting at 1 week after SCI, for 10 bouts (2 sessions of 20 min of actual stepping) over 5 days and control rats in the training group received similar training. Our results indicate that a muscle regenerative response was initiated only in the slow-twitch soleus muscle in the initial 2 weeks following SCI, the addition of 1 week of locomotor treadmill training led to a significant increase in soleus regenerative process. No significant regenerative process was observed in the fast-twitch TA. Increased muscle regeneration in soleus is suggested by our findings of increased expression of (1) insulin-like growth factor-1, involved in the activation of satellite cells; (2) Pax7, a marker of satellite cell activation; (3) myogenin, a muscle regulatory protein; and (4) embryonic myosin, an indicator of new muscle fiber formation. Locomotor training in control, non-injured animals did not induce similar changes towards the regenerative process. [ABSTRACT FROM AUTHOR]

• Mesophilic l -arabinose isomerase from Shewanella sp. ANA-3 was engineered to enhance d -galactose isomerase activity. • Substitution of bulky Phe residue with smaller hydrophilic residues increased the galactose isomerase activity. • Reduction in steric hindrance and formation of H-bond between d-galactose and F279N contribute to the enhanced activity. d -Tagatose, a potential low calorific substitute for sucrose, can be produced by bioconversion of d -galactose catalysed by l -arabinose isomerase. l -Arabinose isomerase from Shewanella sp. ANA-3 is unique for its ability to catalyse bioconversion reactions under mesophilic conditions. However, d -galactose not being a natural substrate for l -arabinose isomerase is catalysed at a slower rate. We attempted to increase the biocatalytic efficiency of Shewanella sp. l -arabinose isomerase by rational design to enhance galactose isomerisation activity. In silico molecular docking, analysis has revealed that F279 is sterically hindering the binding of d -galactose at the C6 position. Substitution of bulky Phe residue with smaller hydrophilic residues such as Asn and Thr increased the galactose isomerase activity by 86 % and 12 % respectively. At mesophilic conditions, F279N mutant catalysed the bioconversion of d -galactose more efficiently than l -arabinose, indicating a shift in substrate preference. [ABSTRACT FROM AUTHOR]

Introduction: Electronic versions of patient-reported outcome measures (PROMs) seem to have a clear administrative logging advantage to traditional paper versions. However, most of them have not been formally evaluated for their suitability to replace paper outcome measures for assessment of individuals with lower-limb amputations. The aim of this study is to examine the usability and equivalence of electronic to paper versions of PROMs suitable for use in prosthetic clinical care and research for persons with lower-limb loss. Methods: In this cross-sectional study, 10 participants remotely completed the following PROMs online and then on paper: Orthotic and Prosthetic User Survey (OPUS), Modified Falls Efficacy Scale (MFES), Prosthetic Evaluation Questionnaire (PEQ), Patient Health Questionnaire–9 (PHQ-9), and Community Participation Indicators (CPI). Participants also answered open-ended and standardized questions regarding the usability of the electronic surveys. Wilcoxon signed rank tests, comparisons to minimum detectable change, intraclass correlation coefficients, and Bland-Altman plots were used to evaluate differences between the two survey versions, meaningful changes in scores, reliability, and systematic biases, respectively. Results: Electronic surveys had fewer missing or ambiguous responses than paper surveys; however, the PEQ Social Burdens subscale could not be evaluated due to error in the creation of the electronic survey. No significant differences were found between scores of the two versions for any of the measures, but multiple participants had meaningful changes in the Appearance and Sounds PEQ subscales. All measures demonstrated acceptable reliability between versions, except the Appearance, Perceived Response, and Sounds subscales of the PEQ. No systematic biases in scores or usability concerns were found for any measures. Conclusions: This study analysis showed that most of the electronic PROMs studied are easily used and demonstrate equivalence to the paper versions. However, the PEQ Appearance, Perceived Response, Sounds, and Social Burden subscales require further evaluation. [ABSTRACT FROM AUTHOR]

Background: Neurodegenerative diseases, such as Parkinson's disease (PD), necessitate frequent clinical visits and monitoring to identify changes in motor symptoms and provide appropriate care. By applying machine learning techniques to video data, automated video analysis has emerged as a promising approach to track and analyze motor symptoms, which could facilitate more timely intervention. However, existing solutions often rely on specialized equipment and recording procedures, which limits their usability in unstructured settings like the home. In this study, we developed a method to detect PD symptoms from unstructured videos of clinical assessments, without the need for specialized equipment or recording procedures. Methods: Twenty-eight individuals with Parkinson's disease completed a video-recorded motor examination that included the finger-to-nose and hand pronation-supination tasks. Clinical staff provided ground truth scores for the level of Parkinsonian symptoms present. For each video, we used a pre-existing model called PIXIE to measure the location of several joints on the person's body and quantify how they were moving. Features derived from the joint angles and trajectories, designed to be robust to recording angle, were then used to train two types of machine-learning classifiers (random forests and support vector machines) to detect the presence of PD symptoms. Results: The support vector machine trained on the finger-to-nose task had an F1 score of 0.93 while the random forest trained on the same task yielded an F1 score of 0.85. The support vector machine and random forest trained on the hand pronation-supination task had F1 scores of 0.20 and 0.33, respectively. Conclusion: These results demonstrate the feasibility of developing video analysis tools to track motor symptoms across variable perspectives. These tools do not work equally well for all tasks, however. This technology has the potential to overcome barriers to access for many individuals with degenerative neurological diseases like PD, providing them with a more convenient and timely method to monitor symptom progression, without requiring a structured video recording procedure. Ultimately, more frequent and objective home assessments of motor function could enable more precise telehealth optimization of interventions to improve clinical outcomes inside and outside of the clinic. [ABSTRACT FROM AUTHOR]

Background: After stroke, restoring safe, independent, and efficient walking is a top rehabilitation priority. However, in nearly 70% of stroke survivors asymmetrical walking patterns and reduced walking speed persist. This case series study aims to investigate the effectiveness of transcutaneous spinal cord stimulation (tSCS) in enhancing walking ability of persons with chronic stroke. Methods: Eight participants with hemiparesis after a single, chronic stroke were enrolled. Each participant was assigned to either the Stim group (N = 4, gait training + tSCS) or Control group (N = 4, gait training alone). Each participant in the Stim group was matched to a participant in the Control group based on age, time since stroke, and self-selected gait speed. For the Stim group, tSCS was delivered during gait training via electrodes placed on the skin between the spinous processes of C5–C6, T11–T12, and L1–L2. Both groups received 24 sessions of gait training over 8 weeks with a physical therapist providing verbal cueing for improved gait symmetry. Gait speed (measured from 10 m walk test), endurance (measured from 6 min walk test), spatiotemporal gait symmetries (step length and swing time), as well as the neurophysiological outcomes (muscle synergy, resting motor thresholds via spinal motor evoked responses) were collected without tSCS at baseline, completion, and 3 month follow-up. Results: All four Stim participants sustained spatiotemporal symmetry improvements at the 3 month follow-up (step length: 17.7%, swing time: 10.1%) compared to the Control group (step length: 1.1%, swing time 3.6%). Additionally, 3 of 4 Stim participants showed increased number of muscle synergies and/or lowered resting motor thresholds compared to the Control group. Conclusions: This study provides promising preliminary evidence that using tSCS as a therapeutic catalyst to gait training may increase the efficacy of gait rehabilitation in individuals with chronic stroke. Trial registration NCT03714282 (clinicaltrials.gov), registration date: 2018-10-18. [ABSTRACT FROM AUTHOR]

Objective Inpatient rehabilitation represents a critical setting for stroke treatment, providing intensive, targeted therapy and task-specific practice to minimize a patient's functional deficits and facilitate their reintegration into the community. However, impairment and recovery vary greatly after stroke, making it difficult to predict a patient's future outcomes or response to treatment. In this study, the authors examined the value of early-stage wearable sensor data to predict 3 functional outcomes (ambulation, independence, and risk of falling) at rehabilitation discharge. Methods Fifty-five individuals undergoing inpatient stroke rehabilitation participated in this study. Supervised machine learning classifiers were retrospectively trained to predict discharge outcomes using data collected at hospital admission, including patient information, functional assessment scores, and inertial sensor data from the lower limbs during gait and/or balance tasks. Model performance was compared across different data combinations and was benchmarked against a traditional model trained without sensor data. Results For patients who were ambulatory at admission, sensor data improved the predictions of ambulation and risk of falling (with weighted F1 scores increasing by 19.6% and 23.4%, respectively) and maintained similar performance for predictions of independence, compared to a benchmark model without sensor data. The best-performing sensor-based models predicted discharge ambulation (community vs household), independence (high vs low), and risk of falling (normal vs high) with accuracies of 84.4%, 68.8%, and 65.9%, respectively. Most misclassifications occurred with admission or discharge scores near the classification boundary. For patients who were nonambulatory at admission, sensor data recorded during simple balance tasks did not offer predictive value over the benchmark models. Conclusion These findings support the continued investigation of wearable sensors as an accessible, easy-to-use tool to predict the functional recovery after stroke. Impact Accurate, early prediction of poststroke rehabilitation outcomes from wearable sensors would improve our ability to deliver personalized, effective care and discharge planning in the inpatient setting and beyond. [ABSTRACT FROM AUTHOR]

Background: Recent evidence suggests that disinhibition and/or hyperexcitation of the brainstem descending pathways and intraspinal motor network diffuse spastic synergistic activation patterns after stroke. This results in simplified or merged muscle sets (i.e., muscle modules or synergies) compared to non-impaired individuals and this leads to poor walking performance. However, the relations of how these neuromuscular deficits influence gait quality (e.g., symmetry or natural walking patterns) are still unclear. The objective of this exploratory study was to investigate the relations of modular neuromuscular framework and gait quality measures in chronic stroke individuals.Methods: Sixteen chronic post-stroke individuals participated in this study. Full lower body three-dimensional kinematics and electromyography (EMG) were concurrently measured during overground walking at a comfortable speed. We first examined changes in gait quality measures across the number of muscle modules using linear regression model. Then, a stepwise multiple regression was used to investigate the optimal combination of the neuromuscular parameters that associates with gait quality measures.Results: We observed that subjects who had a lower number of muscle modules revealed reduced function (i.e., speed) and greater asymmetry in the kinematic parameters including limb length, footpath area, knee flexion/extension, and hip abduction/adduction (all p < 0.05). We also found that the combination of input variables from the modular neuromuscular control framework significantly associated with gait quality measures (average [Formula: see text]). Those variables included variability accounted for ([Formula: see text]) information from the muscle modules and area under the EMG envelope curves of the quadriceps (i.e., rectus femoris and vastus lateralis) and tibialis anterior muscles.Conclusions: The results suggest that there exists a significant correlation between the neuromuscular control framework and the gait quality measures. This study helps to understand the underlying mechanism of disturbances in gait quality and provides insight for a more comprehensive outcome measure to assess gait impairment after stroke. [ABSTRACT FROM AUTHOR]

This study investigated the Comil as a dry-coating process to enhance the flowability of pharmaceutical powders. As a major novelty, the mean residence time was measured and the effect of processing conditions on the extent of flowability enhancement was evaluated. As opposed to previous work which used a "multi-pass" approach to increase residence time and to improve the effectiveness of the Comil, this study reduces the open area of the screen. This simple modification to the screen increases residence time and allowed the Comil to improve flowability of a model cohesive powder, Avicel PH 105, as effectively as the LabRAM blender which was used as a benchmarking dry-coating device. The comilling process was applied to four fine and poorly flowing APIs which were subsequently used in high drug loading (50% w /w) formulations. In comparison to conventional blending, it was shown that comilling can significantly enhance the manufacturability of the formulations. Unlabelled Image • The Co-mill was used as a dry-coating process to enhance powder flowability. • A short residence time for the Co-mill process results in sub-optimal flowability. • Co-mill screens were modified by blocking open area to increase residence time. • Co-milling with the modified screen significantly improves powder flowability. • Co-milling may enable direct compaction for high drug loading formulations. [ABSTRACT FROM AUTHOR]

Background: Despite family carepartners of individuals post-stroke experiencing high levels of strain and reduced quality of life, stroke rehabilitation interventions rarely address carepartner well-being or offer training to support their engagement in therapeutic activities. Our group has developed creative intervention approaches to support families during stroke recovery, thereby improving physical and psychosocial outcomes for both carepartners and stroke survivors. The purpose of this study is to test the feasibility of an adapted, home-based intervention (Carepartner Collaborative Integrative Therapy for Gait-CARE-CITE-Gait) designed to facilitate positive carepartner involvement during home-based training targeting gait and mobility. Methods: This two-phased design will determine the feasibility of CARE-CITE-Gait, a novel intervention that leverages principles from our previous carepartner-focused upper extremity intervention. During the 4-week CARE-CITE-Gait intervention, carepartners review online video-based modules designed to illustrate strategies for an autonomy-supportive environment during functional mobility task practice, and the study team completes two 2-h home visits for dyad collaborative goal setting. In phase I, content validity, usability, and acceptability of the CARE-CITE-Gait modules will be evaluated by stroke rehabilitation content experts and carepartners. In phase II, feasibility (based on measures of recruitment, retention, intervention adherence, and safety) will be measured. Preliminary effects of the CARE-CITE-Gait will be gathered using a single-group, quasi-experimental design with repeated measures (two baseline visits 1 week apart, posttest, and 1-month follow-up) with 15 carepartner and stroke survivor dyads. Outcome data collectors will be blinded. Outcomes include psychosocial variables (family conflict surrounding stroke recovery, strain, autonomy support, and quality of life) collected from carepartners and measures of functional mobility, gait speed, stepping activity, and health-related quality of life collected from stroke survivors. Discussion: The findings of the feasibility testing and preliminary data on the effects of CARE-CITE-Gait will provide justification and information to guide a future definitive randomized clinical trial. The knowledge gained from this study will enhance our understanding of and aid the development of rehabilitation approaches that address both carepartner and stroke survivor needs during the stroke recovery process. Trial registration: ClinicalTrials.gov, NCT 05257928. Registered 25 February 2022. Trial status: This trial was registered on ClinicalTrials.gov (NCT 05257928) on March 25, 2022. Recruitment of participants was initiated on May 18, 2022. [ABSTRACT FROM AUTHOR]

Introduction Clinical knowledge surrounding functional outcomes of a powered knee–ankle (PKA) device is limited, particularly among younger and active populations with limb loss. Here, three service members (SM) with unilateral transfemoral limb loss received an optimally tuned PKA prosthesis and device-specific training. Materials and Methods Once proficiency with the PKA device was demonstrated on benchmark activities, and outcomes with the PKA and standard-of-care (SoC) prostheses were obtained via a modified graded treadmill test, 6-minute walk test, and overground gait assessment. Results All SM demonstrated proficiency with the PKA prosthesis within the minimum three training sessions. With the PKA versus SoC prosthesis, cost of transport during the modified graded treadmill test was 4.0% ± 5.2% lower at slower speeds (i.e. 0.6-1.2 m/s), but 7.0% ± 5.1% greater at the faster walking speeds (i.e. ≥1.4 m/s). For the 6-minute walk test, SM walked 83.9 ± 13.2 m shorter with the PKA versus SoC prosthesis. From the overground gait assessment, SM walked with 20.6% ± 10.5% greater trunk lateral flexion and 31.8% ± 12.8% greater trunk axial rotation ranges of motion, with the PKA versus SoC prosthesis. Conclusions Compared to prior work with the PKA in a civilian cohort, although SM demonstrated faster device proficiency (3 versus 12 sessions), SM walked with greater compensatory motions compared to their SoC prostheses (contrary to the civilian cohort). As such, it is important to understand patient-specific factors among various populations with limb loss for optimizing device-specific training and setting functional goals for occupational and/or community reintegration, as well as reducing the risk for secondary complications over the long term. [ABSTRACT FROM AUTHOR]

Introduction: Developmental disabilities and neuromotor delay adversely affect long-term neuromuscular function and quality of life. Current evidence suggests that early therapeutic intervention reduces the severity of motor delay by harnessing neuroplastic potential during infancy. To date, most early therapeutic intervention trials are of limited duration and do not begin soon after birth and thus do not take full advantage of early neuroplasticity. The Corbett Ryan–Northwestern–Shirley Ryan AbilityLab–Lurie Children's Infant Early Detection, Intervention and Prevention Project (Project Corbett Ryan) is a multi-site longitudinal randomized controlled trial to evaluate the efficacy of an evidence-based physical therapy intervention initiated in the neonatal intensive care unit (NICU) and continuing to 12 months of age (corrected when applicable). The study integrates five key principles: active learning, environmental enrichment, caregiver engagement, a strengths-based approach, and high dosage (ClinicalTrials.gov identifier NCT05568264). Methods: We will recruit 192 infants at risk for neuromotor delay who were admitted to the NICU. Infants will be randomized to either a standard-of-care group or an intervention group; infants in both groups will have access to standard-of-care services. The intervention is initiated in the NICU and continues in the infant's home until 12 months of age. Participants will receive twice-weekly physical therapy sessions and caregiver-guided daily activities, assigned by the therapist, targeting collaboratively identified goals. We will use various standardized clinical assessments (General Movement Assessment; Bayley Scales of Infant and Toddler Development, 4th Edition (Bayley-4); Test of Infant Motor Performance; Pediatric Quality of Life Inventory Family Impact Module; Alberta Infant Motor Scale; Neurological, Sensory, Motor, Developmental Assessment; Hammersmith Infant Neurological Examination) as well as novel technology-based tools (wearable sensors, video-based pose estimation) to evaluate neuromotor status and development throughout the course of the study. The primary outcome is the Bayley-4 motor score at 12 months; we will compare scores in infants receiving the intervention vs. standard-of-care therapy. [ABSTRACT FROM AUTHOR]

Although ongoing exercise is known to reduce disability in people with multiple sclerosis (MS), participation in lower-extremity exercise programs can be limited by their existing mobility impairments. Lower-extremity exoskeletons could address this problem by facilitating home and community locomotion and enhancing exercise capability but little data is available on the potential of this technology for reducing disability of people with MS. We evaluated the Keeogo™ exoskeleton for people with MS using an open-label randomised cross-over design. The trial design allowed us to quantify rehabilitation effects (tested without device) and training effects (tested with device) using functional outcomes: 6-minute walk test (6MWT), timed stair test (TST), and timed up-and-go (TUG). Baseline and post-study self-report instruments included Medical Outcomes Survey Short Form-36 (SF36), MS Walking Scale (MSWS), and others. Amount of home use was documented by daily activity log. Partial correlation analysis was used to explore the relationships between changes in functional outcomes and self-report disability, controlling for amount of home use of the device. Twenty-nine participants with MS completed the trial. Change scores for MSWS, SF36 physical function and SF36 emotional well-being correlated positively with changes in 6MWT which was explained by amount of home use. The benefits in physical functioning and emotional well-being from using the exoskeleton at home were linked to amount of device usage. Low-profile robotic exoskeletons could be used to deliver facilitated exercise while assisting with locomotor activities of daily living, such as walking and stair climbing in the home and community environment. Exoskeletons for home use may have the potential to benefit people with MS in terms of physical functioning and emotional well-being. The benefits in physical functioning and emotional well-being appeared to be linked to amount of usage. Exoskeletons might be useful for delivering facilitated exercise while assisting with walking and stair climbing in the home. [ABSTRACT FROM AUTHOR]

The availability of smartphone and wearable sensor technology is leading to a rapid accumulation of human subject data, and machine learning is emerging as a technique to map those data into clinical predictions. As machine learning algorithms are increasingly used to support clinical decision making, it is vital to reliably quantify their prediction accuracy. Cross-validation (CV) is the standard approach where the accuracy of such algorithms is evaluated on part of the data the algorithm has not seen during training. However, for this procedure to be meaningful, the relationship between the training and the validation set should mimic the relationship between the training set and the dataset expected for the clinical use. Here we compared two popular CV methods: record-wise and subject-wise. While the subject-wise method mirrors the clinically relevant use-case scenario of diagnosis in newly recruited subjects, the record-wise strategy has no such interpretation. Using both a publicly available dataset and a simulation, we found that record-wise CV often massively overestimates the prediction accuracy of the algorithms. We also conducted a systematic review of the relevant literature, and found that this overly optimistic method was used by almost half of the retrieved studies that used accelerometers, wearable sensors, or smartphones to predict clinical outcomes. As we move towards an era of machine learning-based diagnosis and treatment, using proper methods to evaluate their accuracy is crucial, as inaccurate results can mislead both clinicians and data scientists. [ABSTRACT FROM AUTHOR]

Background: Few, if any estimates of cost-effectiveness for locomotor training strategies following spinal cord injury (SCI) are available. The purpose of this study was to estimate the cost-effectiveness of locomotor training strategies following spinal cord injury (overground robotic locomotor training versus conventional locomotor training) by injury status (complete versus incomplete) using a practice-based cohort. Methods: A probabilistic cost-effectiveness analysis was conducted using a prospective, practice-based cohort from four participating Spinal Cord Injury Model System sites. Conventional locomotor training strategies (conventional training) were compared to overground robotic locomotor training (overground robotic training). Conventional locomotor training included treadmill-based training with body weight support, overground training, and stationary robotic systems. The outcome measures included the calculation of quality adjusted life years (QALYs) using the EQ-5D and therapy costs. We estimate cost-effectiveness using the incremental cost utility ratio and present results on the cost-effectiveness plane and on cost-effectiveness acceptability curves. Results: Participants in the prospective, practice-based cohort with complete EQ-5D data (n = 99) qualified for the analysis. Both conventional training and overground robotic training experienced an improvement in QALYs. Only people with incomplete SCI improved with conventional locomotor training, 0.045 (SD 0.28), and only people with complete SCI improved with overground robotic training, 0.097 (SD 0.20). Costs were lower for conventional training, $1758 (SD $1697) versus overground robotic training $3952 (SD $3989), and lower for those with incomplete versus complete injury. Conventional overground training was more effective and cost less than robotic therapy for people with incomplete SCI. Overground robotic training was more effective and cost more than conventional training for people with complete SCI. The incremental cost utility ratio for overground robotic training for people with complete spinal cord injury was $12,353/QALY. Conclusions: The most cost-effective locomotor training strategy for people with SCI differed based on injury completeness. Conventional training was more cost-effective than overground robotic training for people with incomplete SCI. Overground robotic training was more cost-effective than conventional training for people with complete SCI. The effect estimates may be subject to limitations associated with small sample sizes and practice-based evidence methodology. These estimates provide a baseline for future research. [ABSTRACT FROM AUTHOR]

Background: Despite the benefits of physical activity for healthy physical and cognitive aging, 35% of adults over the age of 75 in the United States are inactive. Robotic exoskeleton-based exercise studies have shown benefits in improving walking function, but most are conducted in clinical settings with a neurologically impaired population. Emerging technology is starting to enable easy-to-use, lightweight, wearable robots, but their impact in the otherwise healthy older adult population remains mostly unknown. For the first time, this study investigates the feasibility and efficacy of using a lightweight, modular hip exoskeleton for in-community gait training in the older adult population to improve walking function. Methods: Twelve adults over the age of 65 were enrolled in a gait training intervention involving twelve 30-min sessions using the Gait Enhancing and Motivating System for Hip in their own senior living community. Results: Performance-based outcome measures suggest clinically significant improvements in balance, gait speed, and endurance following the exoskeleton training, and the device was safe and well tolerated. Gait speed below 1.0 m/s is an indicator of fall risk, and two out of the four participants below this threshold increased their self-selected gait speed over 1.0 m/s after intervention. Time spent in sedentary behavior also decreased significantly. Conclusions: This intervention resulted in greater improvements in speed and endurance than traditional exercise programs, in significantly less time. Together, our results demonstrated that exoskeleton-based gait training is an effective intervention and novel approach to encouraging older adults to exercise and reduce sedentary time, while improving walking function. Future work will focus on whether the device can be used independently long-term by older adults as an everyday exercise and community-use personal mobility device. Trial registration This study was retrospectively registered with ClinicalTrials.gov (ID: NCT05197127). [ABSTRACT FROM AUTHOR]

Exoskeletons are externally worn motorized devices that assist with sit-to-stand and walking in individuals with motor and functional impairments. The Food & Drug Administration (FDA) has approved several of these technologies for clinical use however, there is limited evidence to guide optimal utilization in every day clinical practice. With the diversity of technologies & equipment available, it presents a challenge for clinicians to decide which device to use, when to initiate, how to implement these technologies with different patient presentations, and when to wean off the devices. Thus, we present a clinical utilization framework specific to exoskeletons with four aims.These aims are to assist with clinical decision making of when exoskeleton use is clinically indicated, identification of which device is most appropriate based on patient deficits and device characteristics, providing guidance on dosage parameters within a plan of care and guidance for reflection following utilization. This framework streamlines how clinicians can approach implementation through the synthesis of published evidence with appropriate clinical assessment & device selection to reflection for success and understanding of these innovative & complex technologies. [ABSTRACT FROM AUTHOR]

We created an overall assessment metric using a deep learning autoencoder to directly compare clinical outcomes in a comparison of lower limb amputees using two different prosthetic devices—a mechanical knee and a microprocessor-controlled knee. Eight clinical outcomes were distilled into a single metric using a seven-layer deep autoencoder, with the developed metric compared to similar results from principal component analysis (PCA). The proposed methods were used on data collected from ten participants with a dysvascular transfemoral amputation recruited for a prosthetics research study. This single summary metric permitted a cross-validated reconstruction of all eight scores, accounting for 83.29% of the variance. The derived score is also linked to the overall functional ability in this limited trial population, as improvements in each base clinical score led to increases in this developed metric. There was a highly significant increase in this autoencoder-based metric when the subjects used the microprocessor-controlled knee (p < 0.001, repeated measures ANOVA). A traditional PCA metric led to a similar interpretation but captured only 67.3% of the variance. The autoencoder composite score represents a single-valued, succinct summary that can be useful for the holistic assessment of highly variable, individual scores in limited clinical datasets. [ABSTRACT FROM AUTHOR]

Sleep plays a critical role in stroke recovery. However, there are limited practices to measure sleep for individuals with stroke, thus inhibiting our ability to identify and treat poor sleep quality. Wireless, body-worn sensors offer a solution for continuous sleep monitoring. In this study, we explored the feasibility of (1) collecting overnight biophysical data from patients with subacute stroke using a simple sensor system and (2) constructing machine-learned algorithms to detect sleep stages. Ten individuals with stroke in an inpatient rehabilitation hospital wore two wireless sensors during a single night of sleep. Polysomnography served as ground truth to classify different sleep stages. A population model, trained on data from multiple patients and tested on data from a separate patient, performed poorly for this limited sample. Personal models trained on data from one patient and tested on separate data from the same patient demonstrated markedly improved performance over population models and research-grade wearable devices to detect sleep/wake. Ultimately, the heterogeneity of biophysical signals after stroke may present a challenge in building generalizable population models. Personal models offer a provisional method to capture high-resolution sleep metrics from simple wearable sensors by leveraging a single night of polysomnography data. [ABSTRACT FROM AUTHOR]

Background: Falls are a common complication experienced after a stroke and can cause serious detriments to physical health and social mobility, necessitating a dire need for intervention. Among recent advancements, wearable airbag technology has been designed to detect and mitigate fall impact. However, these devices have not been designed nor validated for the stroke population and thus, may inadequately detect falls in individuals with stroke-related motor impairments. To address this gap, we investigated whether population-specific training data and modeling parameters are required to pre-detect falls in a chronic stroke population.Methods: We collected data from a wearable airbag's inertial measurement units (IMUs) from individuals with (n = 20 stroke) and without (n = 15 control) history of stroke while performing a series of falls (842 falls total) and non-falls (961 non-falls total) in a laboratory setting. A leave-one-subject-out crossvalidation was used to compare the performance of two identical machine learned models (adaptive boosting classifier) trained on cohort-dependent data (control or stroke) to pre-detect falls in the stroke cohort.Results: The average performance of the model trained on stroke data (recall = 0.905, precision = 0.900) had statistically significantly better recall (P = 0.0035) than the model trained on control data (recall = 0.800, precision = 0.944), while precision was not statistically significantly different. Stratifying models trained on specific fall types revealed differences in pre-detecting anterior-posterior (AP) falls (stroke-trained model's F1-score was 35% higher, P = 0.019). Using activities of daily living as non-falls training data (compared to near-falls) significantly increased the AUC (Area under the receiver operating characteristic) for classifying AP falls for both models (P < 0.04). Preliminary analysis suggests that users with more severe stroke impairments benefit further from a stroke-trained model. The optimal lead time (time interval pre-impact to detect falls) differed between control- and stroke-trained models.Conclusions: These results demonstrate the importance of population sensitivity, non-falls data, and optimal lead time for machine learned pre-impact fall detection specific to stroke. Existing fall mitigation technologies should be challenged to include data of neurologically impaired individuals in model development to adequately detect falls in other high fall risk populations. Trial registration https://clinicaltrials.gov/ct2/show/NCT05076565 ; Unique Identifier: NCT05076565. Retrospectively registered on 13 October 2021. [ABSTRACT FROM AUTHOR]

Background: Stroke is a leading cause of serious gait impairments and restoring walking ability is a major goal of physical therapy interventions. Soft robotic exosuits are portable, lightweight, and unobtrusive assistive devices designed to improve the mobility of post-stroke individuals through facilitation of more natural paretic limb function during walking training. However, it is unknown whether long-term gait training using soft robotic exosuits will clinically impact gait function and quality of movement post-stroke.Objective: The objective of this pilot study was to examine the therapeutic effects of soft robotic exosuit-augmented gait training on clinical and biomechanical gait outcomes in chronic post-stroke individuals.Methods: Five post-stroke individuals received high intensity gait training augmented with a soft robotic exosuit, delivered in 18 sessions over 6-8 weeks. Performance based clinical outcomes and biomechanical gait quality parameters were measured at baseline, midpoint, and completion.Results: Clinically meaningful improvements were observed in walking speed ([Formula: see text] < 0.05) and endurance ([Formula: see text] < 0.01) together with other traditional gait related outcomes. The gait quality measures including hip ([Formula: see text] < 0.01) and knee ([Formula: see text] < 0.05) flexion/extension exhibited an increase in range of motion in a symmetric manner ([Formula: see text] < 0.05). We also observed an increase in bilateral ankle angular velocities ([Formula: see text] < 0.05), suggesting biomechanical improvements in walking function.Conclusions: The results in this study offer preliminary evidence that a soft robotic exosuit can be a useful tool to augment high intensity gait training in a clinical setting. This study justifies more expanded research on soft exosuit technology with a larger post-stroke population for more reliable generalization. Trial registration This study is registered with ClinicalTrials.gov (ID: NCT04251091). [ABSTRACT FROM AUTHOR]

Abstract: Objective: Muscle weakness develops rapidly after stroke, adversely affecting motor performance, and contributing to reduced functional ability. While the contributions of structural and functional alterations in skeletal muscle to post-stroke weakness have been well described, the relationship between motor pathway integrity, measured using both radiological and electrophysiological techniques, and post-stroke muscle weakness is not clear. This study sought to determine the role of corticospinal tract (CST) integrity on knee extensor weakness in chronic stroke survivors. Methods: Knee extensor strength and activation testing were performed at 90° of knee flexion using an interpolated triplet technique. CST integrity was evaluated using data obtained from Diffusion Tensor Imaging and transcranial magnetic stimulation. Results: Recordings in nine stroke subjects indicated substantial knee extensor weakness and activation deficits in the paretic legs of the stroke survivors. Regression analysis revealed that asymmetry in CST integrity was strongly related to between-leg differences in knee strength. Conclusions: The results of this study suggest a strong link between CST integrity and lower extremity strength, and add to the growing evidence of substantial knee extensor weakness and activation impairments in stroke survivors. Significance: The findings from this study further our understanding of the anatomical and neurophysiological contributions to motor impairments after stroke, which may benefit clinicians and researchers in the field of stroke rehabilitation. [Copyright &y& Elsevier]

Non-technical summary Individuals with a motor incomplete spinal cord injury (SCI) present clinically with partial control of muscles below the site of the injury, but experience profound weakness which can limit the ability to perform functional tasks such as walking. Interestingly, when individuals with an incomplete SCI are asked to maximally and repeatedly contract their quadriceps muscles, they demonstrate an increase in the peak force generated; individuals without SCI experience a decline in force, or 'fatigue'. Following these repeated maximal efforts, reflex responses to electrical stimulation over the quadriceps muscle elicited amplified and prolonged, involuntary motor activity. Such responses were not observed prior to the maximal contractions, and were not observed in neurologically intact subjects. This finding suggests that increases in spinal excitability following these maximal efforts may enhance force generating capacity, and provides insight into possible novel therapeutic interventions to restore function following SCI. [ABSTRACT FROM AUTHOR]

The objective of this study was to determine the impact of treadmill locomotor training on the expression of insulin-like growth factor I (IGF1) and changes in myogenic regulatory factors (MRFs) in rat soleus muscle following spinal cord injury (SCI). Moderate, midthoracic (T(8)) contusion SCIs were produced using a NYU (New York University) impactor. Animals were randomly assigned to treadmill training or untrained groups. Rats in the training group were trained starting at 1 week after SCI, for either 3 bouts of 20 min over 1.5 days or 10 bouts over 5 days. Five days of treadmill training completely prevented the decrease in soleus fiber size resulting from SCI. In addition, treadmill training triggered increases in IGF1, MGF and IGFBP4 mRNA expression, and a concurrent reduction of IGFBP5 mRNA in skeletal muscle. Locomotor training also caused an increase in markers of muscle regeneration, including small muscle fibers expressing embryonic myosin and Pax7 positive nuclei and increased expression of the MRFs, myogenin and MyoD. We concluded that treadmill locomotor training ameliorated muscle atrophy in moderate contusion SCI rats. Training-induced muscle regeneration and fiber hypertrophy following SCI was associated with an increase in IGF1, an increase in Pax7 positive nuclei, and upregulation of MRFs. [ABSTRACT FROM AUTHOR]

Background: Falls are a leading cause of accidental deaths and injuries worldwide. The risk of falling is especially high for individuals suffering from balance impairments. Retrospective surveys and studies of simulated falling in lab conditions are frequently used and are informative, but prospective information about real-life falls remains sparse. Such data are essential to address fall risks and develop fall detection and alert systems. Here we present the results of a prospective study investigating a proof-of-concept, smartphone-based, online system for fall detection and notification.Methods: The system uses the smartphone's accelerometer and gyroscope to monitor the participants' motion, and falls are detected using a regularized logistic regression. Data on falls and near-fall events (i.e., stumbles) is stored in a cloud server and fall-related variables are logged onto a web portal developed for data exploration, including the event time and weather, fall probability, and the faller's location and activity before the fall.Results: In total, 23 individuals with an elevated risk of falling carried the phones for 2070 days in which the model classified 14,904,000 events. The system detected 27 of the 37 falls that occurred (sensitivity = 73.0 %) and resulted in one false alarm every 46 days (specificity > 99.9 %, precision = 37.5 %). 42.2 % of the events falsely classified as falls were validated as stumbles.Conclusions: The system's performance shows the potential of using smartphones for fall detection and notification in real-life. Apart from functioning as a practical fall monitoring instrument, this system may serve as a valuable research tool, enable future studies to scale their ability to capture fall-related data, and help researchers and clinicians to investigate real-falls. [ABSTRACT FROM AUTHOR]

Background: Individuals with transfemoral amputations who are considered to be limited community ambulators are classified as Medicare functional classification (MFCL) level K2. These individuals are usually prescribed a non-microprocessor controlled knee (NMPK) with an appropriate foot for simple walking functions. However, existing research suggests that these individuals can benefit from using a microprocessor controlled knee (MPK) and appropriate foot for their ambulation, but cannot obtain one due to insurance policy restrictions. With a steady increase in older adults with amputations due to vascular conditions, it is critical to evaluate whether advanced prostheses can provide better safety and performance capabilities to maintain and improve quality of life in individuals who are predominantly designated MFCL level K2. To decipher this we conducted a 13 month longitudinal clinical trial to determine the benefits of using a C-Leg and 1M10 foot in individuals at K2 level with transfemoral amputation due to vascular disease. This longitudinal clinical trial incorporated recommendations prescribed by the lower limb prosthesis workgroup to design a study that can add evidence to improve reimbursement policy through clinical outcomes using an MPK in K2 level individuals with transfemoral amputation who were using an NMPK for everyday use.Methods: Ten individuals (mean age: 63 ± 9 years) with unilateral transfemoral amputation due to vascular conditions designated as MFCL K2 participated in this longitudinal crossover randomized clinical trial. Baseline outcomes were collected with their current prosthesis. Participants were then randomized to one of two groups, either an intervention with the MPK with a standardized 1M10 foot or their predicate NMPK with a standardized 1M10 foot. On completion of the first intervention, participants crossed over to the next group to complete the study. Each intervention lasted for 6 months (3 months of acclimation and 3 months of take-home trial to monitor home use). At the end of each intervention, clinical outcomes and self-reported outcomes were collected to compare with their baseline performance. A generalized linear model ANOVA was used to compare the performance of each intervention with respect to their own baseline.Results: Statistically significant and clinically meaningful improvements were observed in gait performance, safety, and participant-reported measures when using the MPK C-Leg + 1M10 foot. Most participants were able to achieve higher clinical scores in gait speed, balance, self-reported mobility, and fall safety, while using the MPK + 1M10 combination. The improvement in scores were within range of scores achieved by individuals with K3 functional level as reported in previous studies.Conclusions: Individuals with transfemoral amputation from dysvascular conditions designated MFCL level K2 benefited from using an MPK + appropriate foot. The inference and evidence from this longitudinal clinical trial will add to the knowledgebase related to reimbursement policy-making. Trial registration This study is registered on clinical trials.gov with the study title "Functional outcomes in dysvascular transfemoral amputees" and the associated ClinicalTrials.gov Identifier: NCT01537211. The trial was retroactively registered on February 7, 2012 after the first participant was enrolled. [ABSTRACT FROM AUTHOR]

Purpose: To describe appraisals of robotic exoskeletons for locomotion by potential users with spinal cord injuries, their perceptions of device benefits and limitations, and recommendations for manufacturers and therapists regarding device use. Materials and methods: We conducted focus groups at three regional rehabilitation hospitals and used thematic analysis to define themes. Results: Across four focus groups, 35 adults participated; they were predominantly middle-aged, male, and diverse in terms of race and ethnicity, well educated, and not working. Participants had been living with SCI an average of two decades. Most participants were aware of exoskeletons. Some were enthusiastic about the usability of the devices while others were more circumspect. They had many questions about device affordability and usability, and were discerning in their appraisal of benefits and suitability to their particular circumstances. They reflected on device cost, the need for caregiver assistance, use of hands, and environmental considerations. They weighed the functional benefits relative to the cost of preferred activities. Their recommendations focused on cost, battery life, and independent use. Conclusions: Potential users' appraisals of mobility technology reflect a nuanced appreciation of device costs; functional, social, and psychological benefits; and limitations. Results provide guidance to therapists and manufacturers regarding device use. Potential users of robotic locomotor exoskeletons with spinal cord injuries appreciate the functional, social, and psychological benefits that these devices may offer. Their appraisals reflect nuanced consideration of device cost and features, and the suitability of the assistive technology to their circumstances. They recommend that manufacturers focus on reducing cost, extending battery life, and features that allow independent use. [ABSTRACT FROM AUTHOR]

Gyroscopic actuators are appealing for wearable applications due to their ability to provide overground balance support without obstructing the legs. Multiple wearable robots using this actuation principle have been proposed, but none has yet been evaluated with humans. Here we use the GyBAR, a backpack-like prototype portable robot, to investigate the hypothesis that the balance of both healthy and chronic stroke subjects can be augmented through moments applied to the upper body. We quantified balance performance in terms of each participant's ability to walk or remain standing on a narrow support surface oriented to challenge stability in either the frontal or the sagittal plane. By comparing candidate balance controllers, it was found that effective assistance did not require regulation to a reference posture. A rotational viscous field increased the distance healthy participants could walk along a 30mm-wide beam by a factor of 2.0, compared to when the GyBAR was worn but inactive. The same controller enabled individuals with chronic stroke to remain standing for a factor of 2.5 longer on a narrow block. Due to its wearability and versatility of control, the GyBAR could enable new therapy interventions for training and rehabilitation. [ABSTRACT FROM AUTHOR]

Background: Atypical walking in the months and years after stroke constrain community reintegration and reduce mobility, health, and quality of life. The ReWalk ReStore™ is a soft robotic exosuit designed to assist the propulsion and ground clearance subtasks of post-stroke walking by actively assisting paretic ankle plantarflexion and dorsiflexion. Previous proof-of-concept evaluations of the technology demonstrated improved gait mechanics and energetics and faster and farther walking in users with post-stroke hemiparesis. We sought to determine the safety, reliability, and feasibility of using the ReStore™ during post-stroke rehabilitation.Methods: A multi-site clinical trial (NCT03499210) was conducted in preparation for an application to the United States Food and Drug Administration (FDA). The study included 44 users with post-stroke hemiparesis who completed up to 5 days of training with the ReStore™ on the treadmill and over ground. In addition to primary and secondary endpoints of safety and device reliability across all training activities, an exploratory evaluation of the effect of multiple exposures to using the device on users' maximum walking speeds with and without the device was conducted prior to and following the five training visits.Results: All 44 study participants completed safety and reliability evaluations. Thirty-six study participants completed all five training days. No device-related falls or serious adverse events were reported. A low rate of device malfunctions was reported by clinician-operators. Regardless of their reliance on ancillary assistive devices, after only 5 days of walking practice with the device, study participants increased both their device-assisted (Δ: 0.10 ± 0.03 m/s) and unassisted (Δ: 0.07 ± 0.03 m/s) maximum walking speeds (P's < 0.05).Conclusions: When used under the direction of a licensed physical therapist, the ReStore™ soft exosuit is safe and reliable for use during post-stroke gait rehabilitation to provide targeted assistance of both paretic ankle plantarflexion and dorsiflexion during treadmill and overground walking.Trial Registration: NCT03499210. Prospectively registered on March 28, 2018. [ABSTRACT FROM AUTHOR]

Background: In clinical practice, therapists often rely on clinical outcome measures to quantify a patient's impairment and function. Predicting a patient's discharge outcome using baseline clinical information may help clinicians design more targeted treatment strategies and better anticipate the patient's assistive needs and discharge care plan. The objective of this study was to develop predictive models for four standardized clinical outcome measures (Functional Independence Measure, Ten-Meter Walk Test, Six-Minute Walk Test, Berg Balance Scale) during inpatient rehabilitation.Methods: Fifty stroke survivors admitted to a United States inpatient rehabilitation hospital participated in this study. Predictors chosen for the clinical discharge scores included demographics, stroke characteristics, and scores of clinical tests at admission. We used the Pearson product-moment and Spearman's rank correlation coefficients to calculate correlations among clinical outcome measures and predictors, a cross-validated Lasso regression to develop predictive equations for discharge scores of each clinical outcome measure, and a Random Forest based permutation analysis to compare the relative importance of the predictors.Results: The predictive equations explained 70-77% of the variance in discharge scores and resulted in a normalized error of 13-15% for predicting the outcomes of new patients. The most important predictors were clinical test scores at admission. Additional variables that affected the discharge score of at least one clinical outcome were time from stroke onset to rehabilitation admission, age, sex, body mass index, race, and diagnosis of dysphasia or speech impairment.Conclusions: The models presented in this study could help clinicians and researchers to predict the discharge scores of clinical outcomes for individuals enrolled in an inpatient stroke rehabilitation program that adheres to U.S. Medicare standards. [ABSTRACT FROM AUTHOR]

Background: Parkinson's disease (PD) is a progressive neurological disease, with characteristic motor symptoms such as tremor and bradykinesia. There is a growing interest to continuously monitor these and other symptoms through body-worn sensor technology. However, limited battery life and memory capacity hinder the potential for continuous, long-term monitoring with these devices. There is little information available on the relative value of adding sensors, increasing sampling rate, or computing complex signal features, all of which may improve accuracy of symptom detection at the expense of computational resources. Here we build on a previous study to investigate the relationship between data measurement characteristics and accuracy when using wearable sensor data to classify tremor and bradykinesia in patients with PD.Methods: Thirteen individuals with PD wore a flexible, skin-mounted sensor (collecting tri-axial accelerometer and gyroscope data) and a commercial smart watch (collecting tri-axial accelerometer data) on their predominantly affected hand. The participants performed a series of standardized motor tasks, during which a clinician scored the severity of tremor and bradykinesia in that limb. Machine learning models were trained on scored data to classify tremor and bradykinesia. Model performance was compared when using different types of sensors (accelerometer and/or gyroscope), different data sampling rates (up to 62.5 Hz), and different categories of pre-engineered features (up to 148 features). Performance was also compared between the flexible sensor and smart watch for each analysis.Results: First, there was no effect of device type for classifying tremor symptoms (p > 0.34), but bradykinesia models incorporating gyroscope data performed slightly better (up to 0.05 AUROC) than other models (p = 0.01). Second, model performance decreased with sampling frequency (p < 0.001) for tremor, but not bradykinesia (p > 0.47). Finally, model performance for both symptoms was maintained after substantially reducing the feature set.Conclusions: Our findings demonstrate the ability to simplify measurement characteristics from body-worn sensors while maintaining performance in PD symptom detection. Understanding the trade-off between model performance and data resolution is crucial to design efficient, accurate wearable sensing systems. This approach may improve the feasibility of long-term, continuous, and real-time monitoring of PD symptoms by reducing computational burden on wearable devices. [ABSTRACT FROM AUTHOR]

Background: We know little about the budget impact of integrating robotic exoskeleton over-ground training into therapy services for locomotor training. The purpose of this study was to estimate the budget impact of adding robotic exoskeleton over-ground training to existing locomotor training strategies in the rehabilitation of people with spinal cord injury.Methods: A Budget Impact Analysis (BIA) was conducted using data provided by four Spinal Cord Injury (SCI) Model Systems rehabilitation hospitals. Hospitals provided estimates of therapy utilization and costs about people with spinal cord injury who participated in locomotor training in the calendar year 2017. Interventions were standard of care walking training including body-weight supported treadmill training, overground training, stationary robotic systems (i.e., treadmill-based robotic gait orthoses), and overground robotic exoskeleton training. The main outcome measures included device costs, training costs for personnel to use the device, human capital costs of locomotor training, device demand, and the number of training sessions per person with SCI.Results: Robotic exoskeletons for over-ground training decreased hospital costs associated with delivering locomotor training in the base case analysis. This analysis assumed no difference in intervention effectiveness across locomotor training strategies. Providing robotic exoskeleton overground training for 10% of locomotor training sessions over the course of the year (range 226-397 sessions) results in decreased annual locomotor training costs (i.e., net savings) between $1114 to $4784 per annum. The base case shows small savings that are sensitive to parameters of the BIA model which were tested in one-way sensitivity analyses, scenarios analyses, and probability sensitivity analyses. The base case scenario was more sensitive to clinical utilization parameters (e.g., how often devices sit idle and the substitution of high cost training) than device-specific parameters (e.g., robotic exoskeleton device cost or device life). Probabilistic sensitivity analysis simultaneously considered human capital cost, device cost, and locomotor device substitution. With probabilistic sensitivity analysis, the introduction of a robotic exoskeleton only remained cost saving for one facility.Conclusions: Providing robotic exoskeleton for over-ground training was associated with lower costs for the locomotor training of people with SCI in the base case analyses. The analysis was sensitive to parameter assumptions. [ABSTRACT FROM AUTHOR]

Gait and balance impairments are linked with reduced mobility and increased risk of falling. Wearable sensing technologies, such as inertial measurement units (IMUs), may augment clinical assessments by providing continuous, high-resolution data. This study tested and validated the utility of a single IMU to quantify gait and balance features during routine clinical outcome tests, and evaluated changes in sensor-derived measurements with age, sex, height, and weight. Age-ranged, healthy individuals (N = 49, 20–70 years) wore a lower back IMU during the 10 m walk test (10MWT), Timed Up and Go (TUG), and Berg Balance Scale (BBS). Spatiotemporal gait parameters computed from the sensor data were validated against gold standard measures, demonstrating excellent agreement for stance time, step time, gait velocity, and step count (intraclass correlation (ICC) > 0.90). There was good agreement for swing time (ICC = 0.78) and moderate agreement for step length (ICC = 0.68). A total of 184 features were calculated from the acceleration and angular velocity signals across these tests, 36 of which had significant correlations with age. This approach was also demonstrated for an individual with stroke, providing higher resolution information about balance, gait, and mobility than the clinical test scores alone. Leveraging mobility data from wireless, wearable sensors can help clinicians and patients more objectively pinpoint impairments, track progression, and set personalized goals during and after rehabilitation. [ABSTRACT FROM AUTHOR]

Background: Although physical activity and exercise is known to benefit people with multiple sclerosis (MS), the ability of these individuals to participate in such interventions is difficult due to the mobility impairments caused by the disease. Keeogo is a lower-extremity powered exoskeleton that may be a potential solution for enabling people with MS to benefit from physical activity and exercise.Methods: An open-label, randomized, cross-over trial was used to examine the immediate performance effects when using the device, and the potential benefits of using the device in a home setting for 2 weeks. Clinical performance tests with and without the device included the 6 min walk test, timed up and go test and the 10-step stair test (up and down). An activity monitor was also used to measure physical activity at home, and a patient-reported questionnaire was used to determine the amount and extent of home use. Generalized linear models were used to test for trial effects, and correlation analysis used to examine relationships between trial effects and usage.Results: Twenty-nine patients with MS participated. All measures showed small decrements in performance while wearing the device compared to not wearing the device. However, significant improvements in unassisted (Rehab effect) performance were found after using the device at home for 2 weeks, compared to 2 weeks at home without the device, and participants improved their ability to use the device over the trial period (Training effect). Rehab and Training effects were related to the self-reported extent that participants used Keeogo at home.Conclusions: Keeogo appears to deliver an exercise-mediated benefit to individuals with MS that improved their unassisted gait endurance and stair climbing ability. Keeogo might be a useful tool for delivering physical activity interventions to individuals with mobility impairment due to MS.Trial Registration: ClinicalTrials.gov : NCT02904382 . Registered 19 September 2016 - Retrospectively registered. [ABSTRACT FROM AUTHOR]

BACKGROUND: Sleep disturbance is a common sequela after traumatic brain injury (TBI). Many of the impairments following TBI may be exacerbated by impaired sleep-wake cycle regulation. OBJECTIVES: To investigate the relationship between total sleep time (TST), measured by wrist actigraphy and observational sleep logs, and neurobehavioral impairments during inpatient rehabilitation after TBI. METHODS: Twenty-five subjects undergoing inpatient rehabilitation for traumatic brain injury were included. TST was measured using wrist actigraphy and observational sleep logs. Neurobehavioral impairments were assessed using the Neurobehavioral Rating Scale-Revised (NRS-R), a multidimensional clinician-based assessment. RESULTS: Of 25 subjects enrolled, 23 subjects completed the study. A significant negative correlation was found between total NRS-R and TST calculated by observational sleep logs (r = –0.28, p = 0.007). The association between total NRS-R and TST, as calculated by actigraphy, was not significantly correlated (R = –0.01, p = 0.921). CONCLUSIONS: Sleep disturbance during inpatient rehabilitation is associated with neurobehavioral impairments after TBI. TST measured by actigraphy may be limited by sleep detection algorithms that have not been validated in certain patient populations. Considerations should be made regarding the feasibility of using wearable sensors in patients with cognitive and behavioral impairments. Challenges regarding actigraphy for sleep monitoring in the brain injury population are discussed. [ABSTRACT FROM AUTHOR]

Objective: The objective of rehabilitation after spinal cord injury is to enable successful function in everyday life and independence at home. Clinical tests can assess whether patients are able to execute functional movements but are limited in assessing such information at home. A prototype system is developed that detects stand-to-reach activities, a movement with important functional implications, at multiple locations within a mock kitchen. Design: Ten individuals with incomplete spinal cord injuries performed a sequence of standing and reaching tasks. The system monitored their movements by combining two sources of information: a triaxial accelerometer, placed on the subject's thigh, detected sitting or standing, and a network of radio frequency tags, wirelessly connected to a wrist-worn device, detected reaching at three locations. A threshold-based algorithm detected execution of the combined tasks and accuracy was measured by the number of correctly identified events. Results: The system was shown to have an average accuracy of 98% for inferring when individuals performed stand-to-reach activities at each tag location within the same room. Conclusions: The combination of accelerometry and tags yielded accurate assessments of functional stand-to-reach activities within a home environment. Optimization of this technology could simplify patient compliance and allow clinicians to assess functional home activities. [ABSTRACT FROM AUTHOR]

This three-part review takes a detailed look at the complexities of cross-validation, fostered by the peer review of Saeb et al.'s paper entitled "The need to approximate the use-case in clinical machine learning." It contains perspectives by reviewers and by the original authors that touch upon cross-validation: the suitability of different strategies and their interpretation. [ABSTRACT FROM AUTHOR]

Background: Although commercially available activity trackers can aid in tracking therapy and recovery of patients, most devices perform poorly for patients with irregular movement patterns. Standard machine learning techniques can be applied on recorded accelerometer signals in order to classify the activities of ambulatory subjects with incomplete spinal cord injury in a way that is specific to this population and the location of the recording-at home or in the clinic.Methods: Subjects were instructed to perform a standardized set of movements while wearing a waist-worn accelerometer in the clinic and at-home. Activities included lying, sitting, standing, walking, wheeling, and stair climbing. Multiple classifiers and validation methods were used to quantify the ability of the machine learning techniques to distinguish the activities recorded in-lab or at-home.Results: In the lab, classifiers trained and tested using within-subject cross-validation provided an accuracy of 91.6%. When the classifier was trained on data collected in the lab but tested on at home data, the accuracy fell to 54.6% indicating distinct movement patterns between locations. However, the accuracy of the at-home classifications, when training the classifier with at-home data, improved to 85.9%.Conclusion: Individuals with unique movement patterns can benefit from using tailored activity recognition algorithms easily implemented using modern machine learning methods on collected movement data. [ABSTRACT FROM AUTHOR]

Background: Clinical 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.Methods: Four 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.Results: All 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.Conclusion: Integrating 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. [ABSTRACT FROM AUTHOR]

Background: Robots offer an alternative, potentially advantageous method of providing repetitive, high-dosage, and high-intensity training to address the gait impairments caused by stroke. In this study, we compared the effects of the Stride Management Assist (SMA®) System, a new wearable robotic device developed by Honda R&D Corporation, Japan, with functional task specific training (FTST) on spatiotemporal gait parameters in stroke survivors. Methods: A single blinded randomized control trial was performed to assess the effect of FTST and task-specific walking training with the SMA® device on spatiotemporal gait parameters. Participants (n = 50) were randomly assigned to FTST or SMA. Subjects in both groups received training 3 times per week for 6–8 weeks for a maximum of 18 training sessions. The GAITRite® system was used to collect data on subjects' spatiotemporal gait characteristics before training (baseline), at mid-training, post-training, and at a 3-month follow-up. Results: After training, significant improvements in gait parameters were observed in both training groups compared to baseline, including an increase in velocity and cadence, a decrease in swing time on the impaired side, a decrease in double support time, an increase in stride length on impaired and non-impaired sides, and an increase in step length on impaired and non-impaired sides. No significant differences were observed between training groups; except for SMA group, step length on the impaired side increased significantly during self-selected walking speed trials and spatial asymmetry decreased significantly during fast-velocity walking trials. Conclusions: SMA and FTST interventions provided similar, significant improvements in spatiotemporal gait parameters; however, the SMA group showed additional improvements across more parameters at various time points. These results indicate that the SMA® device could be a useful therapeutic tool to improve spatiotemporal parameters and contribute to improved functional mobility in stroke survivors. Further research is needed to determine the feasibility of using this device in a home setting vs a clinic setting, and whether such home use provides continued benefits. Trial registration: This study is registered under the title "Development of walk assist device to improve community ambulation" and can be located in clinicaltrials.gov with the study identifier: NCT01994395. [ABSTRACT FROM AUTHOR]

Stem/progenitor cells, including cardiac-derived c-kit+ progenitor cells (CPCs), are under clinical evaluation for treatment of cardiac disease. Therapeutic efficacy of cardiac cell therapy can be attributed to paracrine signaling and the release of extracellular vesicles (EVs) carrying diverse cargo molecules. Despite some successes and demonstrated safety, large variation in cell populations and preclinical/clinical outcomes remains a problem. Here, we investigated this variability by sequencing coding and non-coding RNAs of CPCs and CPC-EVs from 30 congenital heart disease patients and used machine learning methods to determine potential mechanistic insights. CPCs retained RNAs related to extracellular matrix organization and exported RNAs related to various signaling pathways to CPC-EVs. CPC-EVs are enriched in miRNA clusters related to cell proliferation and angiogenesis. With network analyses, we identified differences in non-coding RNAs which give insight into age-dependent functionality of CPCs. By taking a quantitative computational approach, we aimed to uncover sources of CPC cell therapy variability. • C-kit+ progenitor cells retain and release specific RNAs to EVs. • CPC-EVs contain miRNA related to cell proliferation, not found in other cell type EVs. • CPCs derived from older patients are enriched in non-coding RNA. [ABSTRACT FROM AUTHOR]

Common goals in the development of human-machine interface (HMI) technology are to reduce cognitive workload and increase function. However, objective and quantitative outcome measures assessing cognitive workload have not been standardized for HMI research. The present study examines the efficacy of a simple event-related potential (ERP) measure of cortical effort during myoelectric control of a virtual limb for use as an outcome tool. Participants trained and tested on two methods of control, direct control (DC) and pattern recognition control (PRC), while electroencephalographic (EEG) activity was recorded. Eighteen healthy participants with intact limbs were tested using DC and PRC under three conditions: passive viewing, easy, and hard. Novel auditory probes were presented at random intervals during testing, and significant task-difficulty effects were observed in the P200, P300, and a late positive potential (LPP), supporting the efficacy of ERPs as a cognitive workload measure in HMI tasks. LPP amplitude distinguished DC from PRC in the hard condition with higher amplitude in PRC, consistent with lower cognitive workload in PRC relative to DC for complex movements. Participants completed trials faster in the easy condition using DC relative to PRC, but completed trials more slowly using DC relative to PRC in the hard condition. The results provide promising support for ERPs as an outcome measure for cognitive workload in HMI research such as prosthetics, exoskeletons, and other assistive devices, and can be used to evaluate and guide new technologies for more intuitive HMI control. [ABSTRACT FROM AUTHOR]

Purpose: Muscle paralysis after spinal cord injury leads to muscle atrophy, enhanced muscle fatigue, and increased energy demands for functional activities. Phosphorus magnetic resonance spectroscopy ((31)P-MRS) offers a unique non-invasive alternative of measuring energy metabolism in skeletal muscle and is especially suitable for longitudinal investigations. We determined the impact of spinal cord contusion on in vivo muscle bioenergetics of the rat hind limb muscle using (31)P-MRS.Methods: A moderate spinal cord contusion injury (cSCI) was induced at the T8-T10 thoracic spinal segments. (31)P-MRS measurements were performed weekly in the rat hind limb muscles for 3 weeks. Spectra were acquired in a Bruker 11 T/470 MHz spectrometer using a 31P surface coil. The sciatic nerve was electrically stimulated by subcutaneous needle electrodes. Spectra were acquired at rest (5 min), during stimulation (6 min), and recovery (20 min). Phosphocreatine (PCr) depletion rates and the pseudo first-order rate constant for PCr recovery (k PCr) were determined. The maximal rate of PCr resynthesis, the in vivo maximum oxidative capacity (V max) and oxidative adenosine triphosphate (ATP) synthesis rate (Q max) were subsequently calculated.Results: One week after cSCI, there was a decline in the resting total creatine of the paralyzed muscle. There was a significant reduction (~24 %) in k PCr measures of the paralyzed muscle, maximum in vivo mitochondrial capacity (V max) and the maximum oxidative ATP synthesis rate (Q max) at 1 week post-cSCI. During exercise, the PCr depletion rates in the paralyzed muscle one week after injury were rapid and to a greater extent than in a healthy muscle.Conclusions: Using in vivo MRS assessments, we reveal an acute oxidative metabolic defect in the paralyzed hind limb muscle. These altered muscle bioenergetics might contribute to the host of motor dysfunctions seen after cSCI. [ABSTRACT FROM AUTHOR]

Purpose: Muscle paralysis after spinal cord injury leads to muscle atrophy, enhanced muscle fatigue, and increased energy demands for functional activities. Phosphorus magnetic resonance spectroscopy (P-MRS) offers a unique non-invasive alternative of measuring energy metabolism in skeletal muscle and is especially suitable for longitudinal investigations. We determined the impact of spinal cord contusion on in vivo muscle bioenergetics of the rat hind limb muscle using P-MRS. Methods: A moderate spinal cord contusion injury (cSCI) was induced at the T8-T10 thoracic spinal segments. P-MRS measurements were performed weekly in the rat hind limb muscles for 3 weeks. Spectra were acquired in a Bruker 11 T/470 MHz spectrometer using a 31P surface coil. The sciatic nerve was electrically stimulated by subcutaneous needle electrodes. Spectra were acquired at rest (5 min), during stimulation (6 min), and recovery (20 min). Phosphocreatine (PCr) depletion rates and the pseudo first-order rate constant for PCr recovery ( k) were determined. The maximal rate of PCr resynthesis, the in vivo maximum oxidative capacity ( V) and oxidative adenosine triphosphate (ATP) synthesis rate ( Q) were subsequently calculated. Results: One week after cSCI, there was a decline in the resting total creatine of the paralyzed muscle. There was a significant reduction (~24 %) in k measures of the paralyzed muscle, maximum in vivo mitochondrial capacity ( V) and the maximum oxidative ATP synthesis rate ( Q) at 1 week post-cSCI. During exercise, the PCr depletion rates in the paralyzed muscle one week after injury were rapid and to a greater extent than in a healthy muscle. Conclusions: Using in vivo MRS assessments, we reveal an acute oxidative metabolic defect in the paralyzed hind limb muscle. These altered muscle bioenergetics might contribute to the host of motor dysfunctions seen after cSCI. [ABSTRACT FROM AUTHOR]

To be effective, a prescribed prosthetic device must match the functional requirements and capabilities of each patient. These capabilities are usually assessed by a clinician and reported by the Medicare K-level designation of mobility. However, it is not clear how the K-level designation objectively relates to the use of prostheses outside of a clinical environment. Here, we quantify participant activity using mobile phones and relate activity measured during real world activity to the assigned K-levels. We observe a correlation between K-level and the proportion of moderate to high activity over the course of a week. This relationship suggests that accelerometry-based technologies such as mobile phones can be used to evaluate real world activity for mobility assessment. Quantifying everyday activity promises to improve assessment of real world prosthesis use, leading to a better matching of prostheses to individuals and enabling better evaluations of future prosthetic devices. [ABSTRACT FROM AUTHOR]