A Digital Intervention to Promote Self-Management Self-Efficacy Among Community-Dwelling Individuals With Stroke: Pilot Randomized Controlled Trial.

BACKGROUND: Digital interventions provided through smartphones or the internet that are guided by a coach have been proposed as promising solutions to support the self-management of chronic conditions. However, digital intervention for poststroke self-management is limited; we developed the interactive Self-Management Augmented by Rehabilitation Technologies (iSMART) intervention to address this gap. OBJECTIVE: This study aimed to examine the feasibility and initial effects of the iSMART intervention to improve self-management self-efficacy in people with stroke. METHODS: A parallel, 2-arm, nonblinded, randomized controlled trial of 12-week duration was conducted. A total of 24 participants with mild-to-moderate chronic stroke were randomized to receive either the iSMART intervention or a manual of stroke rehabilitation (attention control). iSMART was a coach-guided, technology-supported self-management intervention designed to support people managing chronic conditions and maintaining active participation in daily life after stroke. Feasibility measures included retention and engagement rates in the iSMART group. For both the iSMART intervention and active control groups, we used the Feasibility of Intervention Measure, Acceptability of Intervention Measure, and Intervention Appropriateness Measure to assess the feasibility, acceptability, and appropriateness, respectively. Health measures included the Participation Strategies Self-Efficacy Scale and the Patient-Reported Outcomes Measurement Information System's Self-Efficacy for Managing Chronic Conditions. RESULTS: The retention rate was 82% (9/11), and the engagement (SMS text message response) rate was 78% for the iSMART group. Mean scores of the Feasibility of Intervention Measure, Acceptability of Intervention Measure, and Intervention Appropriateness Measure were 4.11 (SD 0.61), 4.44 (SD 0.73), and 4.36 (SD 0.70), respectively, which exceeded our benchmark (4 out of 5), suggesting high feasibility, acceptability, and appropriateness of iSMART. The iSMART group showed moderate-to-large effects in improving self-efficacy in managing emotions (r=0.494), symptoms (r=0.514), daily activities (r=0.593), and treatments and medications (r=0.870), but the control group showed negligible-to-small effects in decreasing self-efficacy in managing emotions (r=0.252), symptoms (r=0.262), daily activities (r=0.136), and treatments and medications (r=0.049). In addition, the iSMART group showed moderate-to-large effects of increasing the use of participation strategies for management in the home (r=0.554), work (r=0.633), community (r=0.673), and communication activities (r=0.476). In contrast, the control group showed small-to-large effects of decreasing the use of participation strategies for management in the home (r=0.567), work (r=0.342, community (r=0.215), and communication activities (r=0.379). CONCLUSIONS: Our findings support the idea that iSMART was feasible to improve poststroke self-management self-efficacy. Our results also support using a low-cost solution, such as SMS text messaging, to supplement traditional therapeutic patient education interventions. Further evaluation with a larger sample of participants is still needed. TRIAL REGISTRATION: ClinicalTrials.gov 202004137; https://clinicaltrials.gov/study/NCT04743037?id=202004137&rank=1.

Using Intervention Mapping and Behavior Change Techniques to Develop a Digital Intervention for Self-Management in Stroke: Development Study.

BACKGROUND: Digital therapeutics, such as interventions provided via smartphones or the internet, have been proposed as promising solutions to support self-management in persons with chronic conditions. However, the evidence supporting self-management interventions through technology in stroke is scarce, and the intervention development processes are often not well described, creating challenges in explaining why and how the intervention would work. OBJECTIVE: This study describes a specific use case of using intervention mapping (IM) and the taxonomy of behavior change techniques (BCTs) in designing a digital intervention to manage chronic symptoms and support daily life participation in people after stroke. IM is an implementation science framework used to bridge the gap between theories and practice to ensure that the intervention can be implemented in real-world settings. The taxonomy of BCTs consists of a set of active ingredients designed to change self-management behaviors. METHODS: We used the first 4 steps of the IM process to develop a technology-supported self-management intervention, interactive Self-Management Augmented by Rehabilitation Technologies (iSMART), adapted from a face-to-face stroke-focused psychoeducation program. Planning group members were involved in adapting the intervention. They also completed 3 implementation measures to assess the acceptability, appropriateness, and feasibility of iSMART. RESULTS: In step 1, we completed a needs assessment consisting of assembling a planning group to codevelop the intervention, conducting telephone surveys of people after stroke (n=125) to identify service needs, and performing a systematic review of randomized controlled trials to examine evidence of the effectiveness of digital self-management interventions to improve patient outcomes. We identified activity scheduling, symptom management, stroke prevention, access to care resources, and cognitive enhancement training as key service needs after a stroke. The review suggested that digital self-management interventions, especially those using cognitive behavioral theory, effectively reduce depression, anxiety, and fatigue and enhance self-efficacy in neurological disorders. Step 2 identified key determinants, objectives, and strategies for self-management in iSMART, including knowledge, behavioral regulation, skills, self-efficacy, motivation, negative and positive affect, and social and environmental support. In step 3, we generated the intervention components underpinned by appropriate BCTs. In step 4, we developed iSMART with the planning group members. Especially, iSMART simplified the original psychoeducation program and added 2 new components: SMS text messaging and behavioral coaching, intending to increase the uptake by people after stroke. iSMART was found to be acceptable (mean score 4.63, SD 0.38 out of 5), appropriate (mean score 4.63, SD 0.38 out of 5), and feasible (mean score 4.58, SD 0.34 out of 5). CONCLUSIONS: We describe a detailed example of using IM and the taxonomy of BCTs for designing and developing a digital intervention to support people after stroke in managing chronic symptoms and maintaining active participation in daily life.

Predicting and Monitoring Upper-Limb Rehabilitation Outcomes Using Clinical and Wearable Sensor Data in Brain Injury Survivors.

OBJECTIVE: Rehabilitation specialists have shown considerable interest for the development of models, based on clinical data, to predict the response to rehabilitation interventions in stroke and traumatic brain injury survivors. However, accurate predictions are difficult to obtain due to the variability in patients' response to rehabilitation interventions. This study aimed to investigate the use of wearable technology in combination with clinical data to predict and monitor the recovery process and assess the responsiveness to treatment on an individual basis. METHODS: Gaussian Process Regression-based algorithms were developed to estimate rehabilitation outcomes (i.e., Functional Ability Scale scores) using either clinical or wearable sensor data or a combination of the two. RESULTS: The algorithm based on clinical data predicted rehabilitation outcomes with a Pearson's correlation of 0.79 compared to actual clinical scores provided by clinicians but failed to model the variability in responsiveness to the intervention observed across individuals. In contrast, the algorithm based on wearable sensor data generated rehabilitation outcome estimates with a Pearson's correlation of 0.91 and modeled the individual responses to rehabilitation more accurately. Furthermore, we developed a novel approach to combine estimates derived from the clinical data and the sensor data using a constrained linear model. This approach resulted in a Pearson's correlation of 0.94 between estimated and clinician-provided scores. CONCLUSION: This algorithm could enable the design of patient-specific interventions based on predictions of rehabilitation outcomes relying on clinical and wearable sensor data. SIGNIFICANCE: This is important in the context of developing precision rehabilitation interventions.

Enabling precision rehabilitation interventions using wearable sensors and machine learning to track motor recovery.

The need to develop patient-specific interventions is apparent when one considers that clinical studies often report satisfactory motor gains only in a portion of participants. This observation provides the foundation for "precision rehabilitation". Tracking and predicting outcomes defining the recovery trajectory is key in this context. Data collected using wearable sensors provide clinicians with the opportunity to do so with little burden on clinicians and patients. The approach proposed in this paper relies on machine learning-based algorithms to derive clinical score estimates from wearable sensor data collected during functional motor tasks. Sensor-based score estimates showed strong agreement with those generated by clinicians. Score estimates of upper-limb impairment severity and movement quality were marked by a coefficient of determination of 0.86 and 0.79, respectively. The application of the proposed approach to monitoring patients' responsiveness to rehabilitation is expected to contribute to the development of patient-specific interventions, aiming to maximize motor gains.

Can mHealth Technology Help Mitigate the Effects of the COVID-19 Pandemic?

Goal: The aim of the study herein reported was to review mobile health (mHealth) technologies and explore their use to monitor and mitigate the effects of the COVID-19 pandemic. Methods: A Task Force was assembled by recruiting individuals with expertise in electronic Patient-Reported Outcomes (ePRO), wearable sensors, and digital contact tracing technologies. Its members collected and discussed available information and summarized it in a series of reports. Results: The Task Force identified technologies that could be deployed in response to the COVID-19 pandemic and would likely be suitable for future pandemics. Criteria for their evaluation were agreed upon and applied to these systems. Conclusions: mHealth technologies are viable options to monitor COVID-19 patients and be used to predict symptom escalation for earlier intervention. These technologies could also be utilized to monitor individuals who are presumed non-infected and enable prediction of exposure to SARS-CoV-2, thus facilitating the prioritization of diagnostic testing.

Enabling Stroke Rehabilitation in Home and Community Settings: A Wearable Sensor-Based Approach for Upper-Limb Motor Training.

High-dosage motor practice can significantly contribute to achieving functional recovery after a stroke. Performing rehabilitation exercises at home and using, or attempting to use, the stroke-affected upper limb during Activities of Daily Living (ADL) are effective ways to achieve high-dosage motor practice in stroke survivors. This paper presents a novel technological approach that enables 1) detecting goal-directed upper limb movements during the performance of ADL, so that timely feedback can be provided to encourage the use of the affected limb, and 2) assessing the quality of motor performance during in-home rehabilitation exercises so that appropriate feedback can be generated to promote high-quality exercise. The results herein presented show that it is possible to detect 1) goal-directed movements during the performance of ADL with a [Formula: see text]-statistic of 87.0% and 2) poorly performed movements in selected rehabilitation exercises with an [Formula: see text]-score of 84.3%, thus enabling the generation of appropriate feedback. In a survey to gather preliminary data concerning the clinical adequacy of the proposed approach, 91.7% of occupational therapists demonstrated willingness to use it in their practice, and 88.2% of stroke survivors indicated that they would use it if recommended by their therapist.

Identifying predictors for postoperative clinical outcome in lumbar spinal stenosis patients using smart-shoe technology.

BACKGROUND: Approximately 33% of the patients with lumbar spinal stenosis (LSS) who undergo surgery are not satisfied with their postoperative clinical outcomes. Therefore, identifying predictors for postoperative outcome and groups of patients who will benefit from the surgical intervention is of significant clinical benefit. However, many of the studied predictors to date suffer from subjective recall bias, lack fine digital measures, and yield poor correlation to outcomes. METHODS: This study utilized smart-shoes to capture gait parameters extracted preoperatively during a 10 m self-paced walking test, which was hypothesized to provide objective, digital measurements regarding the level of gait impairment caused by LSS symptoms, with the goal of predicting postoperative outcomes in a cohort of LSS patients who received lumbar decompression and/or fusion surgery. The Oswestry Disability Index (ODI) and predominant pain level measured via the Visual Analogue Scale (VAS) were used as the postoperative clinical outcome variables. RESULTS: The gait parameters extracted from the smart-shoes made statistically significant predictions of the postoperative improvement in ODI (RMSE =0.13, r=0.93, and p<3.92×10-7) and predominant pain level (RMSE =0.19, r=0.83, and p<1.28×10-4). Additionally, the gait parameters produced greater prediction accuracy compared to the clinical variables that had been previously investigated. CONCLUSIONS: The reported results herein support the hypothesis that the measurement of gait characteristics by our smart-shoe system can provide accurate predictions of the surgical outcomes, assisting clinicians in identifying which LSS patient population can benefit from the surgical intervention and optimize treatment strategies.

Unobtrusive and Continuous Monitoring of Alcohol-impaired Gait Using Smart Shoes.

BACKGROUND: Alcohol ingestion influences sensory-motor function and the overall well-being of individuals. Detecting alcohol-induced impairments in gait in daily life necessitates a continuous and unobtrusive gait monitoring system. OBJECTIVES: This paper introduces the development and use of a non-intrusive monitoring system to detect changes in gait induced by alcohol intoxication. METHODS: The proposed system employed a pair of sensorized smart shoes that are equipped with pressure sensors on the insole. Gait features were extracted and adjusted based on individual's gait profile. The adjusted gait features were used to train a machine learning classifier to discriminate alcohol-impaired gait from normal walking. In experiment of pilot study, twenty participants completed walking trials on a 12 meter walkway to measure their sober walking and alcohol-impaired walking using smart shoes. RESULTS: The proposed system can detect alcohol-impaired gait with an accuracy of 86.2 % when pressure value analysis and person-dependent model for the classifier are applied, while statistical analysis revealed that no single feature was discriminative for the detection of gait impairment. CONCLUSIONS: Alcohol-induced gait disturbances can be detected with smart shoe technology for an automated monitoring in ubiquitous environment. We demonstrated that personal monitoring and machine learning-based prediction could be customized to detect individual variation rather than applying uniform boundary parameters of gait.

Recent machine learning advancements in sensor-based mobility analysis: Deep learning for Parkinson's disease assessment.

The development of wearable sensors has opened the door for long-term assessment of movement disorders. However, there is still a need for developing methods suitable to monitor motor symptoms in and outside the clinic. The purpose of this paper was to investigate deep learning as a method for this monitoring. Deep learning recently broke records in speech and image classification, but it has not been fully investigated as a potential approach to analyze wearable sensor data. We collected data from ten patients with idiopathic Parkinson's disease using inertial measurement units. Several motor tasks were expert-labeled and used for classification. We specifically focused on the detection of bradykinesia. For this, we compared standard machine learning pipelines with deep learning based on convolutional neural networks. Our results showed that deep learning outperformed other state-of-the-art machine learning algorithms by at least 4.6 % in terms of classification rate. We contribute a discussion of the advantages and disadvantages of deep learning for sensor-based movement assessment and conclude that deep learning is a promising method for this field.

Quantitative assessment of hand motor function in cervical spinal disorder patients using target tracking tests.

Cervical spondylotic myelopathy (CSM) is a chronic spinal disorder in the neck region. Its prevalence is growing rapidly in developed nations, creating a need for an objective assessment tool. This article introduces a system for quantifying hand motor function using a handgrip device and target tracking test. In those with CSM, hand motor impairment often interferes with essential daily activities. The analytic method applied machine learning techniques to investigate the efficacy of the system in (1) detecting the presence of impairments in hand motor function, (2) estimating the perceived motor deficits of CSM patients using the Oswestry Disability Index (ODI), and (3) detecting changes in physical condition after surgery, all of which were performed while ensuring test-retest reliability. The results based on a pilot data set collected from 30 patients with CSM and 30 nondisabled control subjects produced a c-statistic of 0.89 for the detection of impairments, Pearson r of 0.76 with p < 0.001 for the estimation of ODI, and a c-statistic of 0.82 for responsiveness. These results validate the use of the presented system as a means to provide objective and accurate assessment of the level of impairment and surgical outcomes.

Use of multivariate linear regression and support vector regression to predict functional outcome after surgery for cervical spondylotic myelopathy.

This study introduces the use of multivariate linear regression (MLR) and support vector regression (SVR) models to predict postoperative outcomes in a cohort of patients who underwent surgery for cervical spondylotic myelopathy (CSM). Currently, predicting outcomes after surgery for CSM remains a challenge. We recruited patients who had a diagnosis of CSM and required decompressive surgery with or without fusion. Fine motor function was tested preoperatively and postoperatively with a handgrip-based tracking device that has been previously validated, yielding mean absolute accuracy (MAA) results for two tracking tasks (sinusoidal and step). All patients completed Oswestry disability index (ODI) and modified Japanese Orthopaedic Association questionnaires preoperatively and postoperatively. Preoperative data was utilized in MLR and SVR models to predict postoperative ODI. Predictions were compared to the actual ODI scores with the coefficient of determination (R(2)) and mean absolute difference (MAD). From this, 20 patients met the inclusion criteria and completed follow-up at least 3 months after surgery. With the MLR model, a combination of the preoperative ODI score, preoperative MAA (step function), and symptom duration yielded the best prediction of postoperative ODI (R(2)=0.452; MAD=0.0887; p=1.17 × 10(-3)). With the SVR model, a combination of preoperative ODI score, preoperative MAA (sinusoidal function), and symptom duration yielded the best prediction of postoperative ODI (R(2)=0.932; MAD=0.0283; p=5.73 × 10(-12)). The SVR model was more accurate than the MLR model. The SVR can be used preoperatively in risk/benefit analysis and the decision to operate.

Utilization of a novel digital measurement tool for quantitative assessment of upper extremity motor dexterity: a controlled pilot study.

BACKGROUND: The current methods of assessing motor function rely primarily on the clinician's judgment of the patient's physical examination and the patient's self-administered surveys. Recently, computerized handgrip tools have been designed as an objective method to quantify upper-extremity motor function. This pilot study explores the use of the MediSens handgrip as a potential clinical tool for objectively assessing the motor function of the hand. METHODS: Eleven patients with cervical spondylotic myelopathy (CSM) were followed for three months. Eighteen age-matched healthy participants were followed for two months. The neuromotor function and the patient-perceived motor function of these patients were assessed with the MediSens device and the Oswestry Disability Index respectively. The MediSens device utilized a target tracking test to investigate the neuromotor capacity of the participants. The mean absolute error (MAE) between the target curve and the curve tracing achieved by the participants was used as the assessment metric. The patients' adjusted MediSens MAE scores were then compared to the controls. The CSM patients were further classified as either "functional" or "nonfunctional" in order to validate the system's responsiveness. Finally, the correlation between the MediSens MAE score and the ODI score was investigated. RESULTS: The control participants had lower MediSens MAE scores of 8.09%±1.60%, while the cervical spinal disorder patients had greater MediSens MAE scores of 11.24%±6.29%. Following surgery, the functional CSM patients had an average MediSens MAE score of 7.13%±1.60%, while the nonfunctional CSM patients had an average score of 12.41%±6.32%. The MediSens MAE and the ODI scores showed a statistically significant correlation (r=-0.341, p<1.14×10⁻5). A Bland-Altman plot was then used to validate the agreement between the two scores. Furthermore, the percentage improvement of the the two scores after receiving the surgical intervention showed a significant correlation (r=-0.723, p<0.04). CONCLUSIONS: The MediSens handgrip device is capable of identifying patients with impaired motor function of the hand. The MediSens handgrip scores correlate with the ODI scores and may serve as an objective alternative for assessing motor function of the hand.