Multi-Day Recordings of Wearable Sensors Are Valid and Sensitive Measures of Function and Independence in Human Spinal Cord Injury

Assessing sensor-derived features from a wrist-worn wearable device as indicators of upper extremity function in individuals with cervical spinal cord injury

OBJECTIVE

To assess the relationship between sensor-derived features and upper extremity function in individuals with acute and chronic cervical spinal cord injury (cSCI) and to assess the reproducibility of these features in chronic cSCI.

DESIGN

Prospective, longitudinal study. Participants completed the Capabilities of Upper Extremity Test (CUE-T) - a measure of upper extremity function - at two time points, four weeks apart, while wearing a wrist-worn inertial measurement unit (IMU) device on their most-used upper extremity. The IMU recorded 3-axis accelerometer and gyroscope data from which metrics (features) were derived. Distance correlations (dCorr) assessed associations between features and CUE-T hand and arm function scores. Intraclass correlation coefficients (ICCs) assessed the reproducibility of CUE-T scores and features in the chronic subgroup.

SETTING

Inpatient rehabilitation facility (acute cSCI) and community (chronic cSCI).

PARTICIPANTS

Forty adults with cSCI were enrolled, and 33 provided data.

INTERVENTION

None.

MAIN OUTCOME MEASURES

Correlations between CUE-T scores and features; ICCs of CUE-T scores and features (chronic group).

RESULTS

At Time 1, two features showed strong correlations with CUE-T hand score (dCorr=0.53-0.58), while nine showed strong correlations with CUE-T arm score (dCorr=0.54-0.62). At Time 2, three features showed strong correlations with CUE-T hand score (dCorr=0.53-0.57), while 29 showed strong correlations with CUE-T arm score (dCorr=0.50-0.72). Types of features were distinct for hand and arm conditions. For the chronic subgroup, CUE-T scores showed excellent reproducibility (ICC=0.94-0.99), and 16 features demonstrated moderate to good reproducibility (ICC=0.50-0.77).

CONCLUSIONS

Sensor-derived features can indicate upper extremity function in cSCI, supporting their use for monitoring recovery and functional outcomes. Future research should focus on validating features of upper extremity function to support digital biomarker development and clinical adoption.

Quantifying States and Transitions of Emerging Postural Control for Children Not Yet Able to Sit Independently

Objective, quantitative postural data is limited for individuals who are non-ambulatory, especially for those who have not yet developed trunk control for sitting. There are no gold standard measurements to monitor the emergence of upright trunk control. Quantification of intermediate levels of postural control is critically needed to improve research and intervention for these individuals. Accelerometers and video were used to record postural alignment and stability for eight children with severe cerebral palsy aged 2 to 13 years, under two conditions, seated on a bench with only pelvic support and with additional thoracic support. This study developed an algorithm to classify vertical alignment and states of upright control; Stable, Wobble, Collapse, Rise and Fall from accelerometer data. Next, a Markov chain model was created to calculate a normative score for postural state and transition for each participant with each level of support. This tool allowed quantification of behaviors previously not captured in adult-based postural sway measures. Histogram and video recordings were used to confirm the output of the algorithm. Together, this tool revealed that providing external support allowed all participants: (1) to increase their time spent in the Stable state, and (2) to reduce the frequency of transitions between states. Furthermore, all participants except one showed improved state and transition scores when given external support.

Healthcare Monitoring Using Low-Cost Sensors to Supplement and Replace Human Sensation: Does It Have Potential to Increase Independent Living and Prevent Disease?

Continuous monitoring of health status has the potential to enhance the quality of life and life expectancy of people suffering from chronic illness and of the elderly. However, such systems can only come into widespread use if the cost of manufacturing is low. Advancements in material science and engineering technology have led to a significant decrease in the expense of developing healthcare monitoring devices. This review aims to investigate the progress of the use of low-cost sensors in healthcare monitoring and discusses the challenges faced when accomplishing continuous and real-time monitoring tasks. The major findings include (1) only a small number of publications (N = 50) have addressed the issue of healthcare monitoring applications using low-cost sensors over the past two decades; (2) the top three algorithms used to process sensor data include SA (Statistical Analysis, 30%), SVM (Support Vector Machine, 18%), and KNN (K-Nearest Neighbour, 12%); and (3) wireless communication techniques (Zigbee, Bluetooth, Wi-Fi, and RF) serve as the major data transmission tools (77%) followed by cable connection (13%) and SD card data storage (10%). Due to the small fraction (N = 50) of low-cost sensor-based studies among thousands of published articles about healthcare monitoring, this review not only summarises the progress of related research but calls for researchers to devote more effort to the consideration of cost reduction as well as the size of these components.

Physical Activity and Public Health among People with Disabilities: Research Gaps and Recommendations

Physical activity has become an integral component of public health systems modeling the public health core functions of assessment, policy development, and assurance. However, people with disabilities have often not been included in public health efforts to assess, develop policies, or evaluate the impact of physical activity interventions to promote health and prevent disease among people with disabilities. Addressing the core function of assessment, current physical activity epidemiology, and surveillance among people with disabilities across the globe highlights the paucity of surveillance systems that include physical activity estimates among people with disabilities. The status of valid and reliable physical activity measures among people with condition-specific disabilities is explored, including self-report measures along with wearable devices, and deficiencies in measurement of physical activity. The core functions of policy development and assurance are described in the context of community-based intervention strategies to promote physical activity among people with disabilities. The identification of research gaps in health behavior change, policy, and environmental approaches to promoting physical activity among people with disabilities is explored, along with recommendations based on the principles of inclusive and engaged research partnerships between investigators and the members of the disability community.

Technologies measuring manual wheelchair propulsion metrics: a scoping review

The aim of this review is to investigate existing and developing technologies assessing metrics of manual wheelchair propulsion. A scoping review of scientific and gray literature was performed. Five databases were searched - Medline, Scopus, CINAHL, Institute of Electrical and Electronics Engineers (IEEE), and Embase. The 38 retained articles identified 27 devices categorized into accelerometers, wheelchair-mounted devices, instrumented wheels, and wearables. The devices included in this review can be used by manual wheelchair users to monitor propulsion effort and activity goals, by clinicians to assess rehabilitation programs, and to inform and guide future research. The findings support a need for further research into the development of custom algorithms for manual wheelchair user populations as well as further validation in broader free-living environments with equitable participant populations.

Harnessing of real world data and real world evidence using digital tools: utility and potential models in rheumatology practice

The diversity of diseases in rheumatology and variability in disease prevalence necessitates greater data parity in disease presentation, treatment responses including adverse events to drugs and various co-morbidities. Randomized Controlled Trials (RCTs) are the gold standard for drug development and performance evaluation. However, when the drug is applied outside the controlled environment the outcomes may differ in patient population. In this context, the need to understand the macro and micro changes involved in disease evolution and progression becomes important and so is the need for harvesting and harnessing the Real-World Data (RWD) from various resources to use them in generating Real World Evidence (RWE). Digital tools with potential relevance to rheumatology can be potentially leveraged to obtain greater patient insights, greater information on disease progression and disease micro processes and even in the early diagnosis of diseases. Since the patients spend only a minuscule proportion of their time in hospital or in a clinic, using the modern digital tools to generate realistic, bias proof RWD in non-invasive patient friendly manner becomes critical. In this review we have appraised different digital mediums and mechanisms for collecting RWD and proposed digital care models for generating RWE in rheumatology.

Tenodesis Grasp Detection in Egocentric Video

OBJECTIVE

Cervical spinal cord injury (cSCI) can impair motor function in the upper limbs. Video from wearable cameras (egocentric video) has the potential to provide monitoring of rehabilitation outcomes at home, but methods for automated analysis of this data are needed. Wrist flexion and extension are essential elements to track grasping strategies after cSCI, as they may reflect the use of the tenodesis grasp, a common compensatory strategy. However, there is no established method to evaluate wrist flexion and extension from egocentric video.

METHODS

We propose a machine-learning-based approach comprising three steps-hand detection, pose estimation, and arm orientation estimation-to estimate wrist angle data, leading to the detection of tenodesis grasp.

RESULTS

The hand detection in conjunction with the pose estimation algorithm correctly located wrist and index finger metacarpophalangeal coordinates in 63% and 76% of 15,319 annotated frames, respectively, extracted from egocentric videos of individuals with cSCI performing activities of daily living in a home simulation laboratory. The arm orientation algorithm had a mean absolute error of 2.76 +/- 0.39 degrees in 12,863 labeled frames. Using these estimates, the presence of a tenodesis grasp was correctly detected in 72% +/- 11% of frames in videos of 6 activities.

CONCLUSION

The results provided a clear indication of which participants relied on tenodesis grasp and which did not.

SIGNIFICANCE

This paradigm provides the first method that can enable clinicians and researchers to monitor the use of the tenodesis grasp by individuals with cSCI at home, with implications for remote therapeutic guidance.

Noninvasive Continuous Monitoring of Vital Signs With Wearables: Fit for Medical Use?

BACKGROUND

Wearables (= wearable computer) enable continuous and noninvasive monitoring of a range of vital signs. Mobile and cost-effective devices, combined with powerful data analysis tools, open new dimensions in assessing body functions ("digital biomarkers").

METHODS

To answer the question whether wearables are ready for use in the medical context, a PubMed literature search and analysis for their clinical-scientific use using publications from the years 2008 to 2018 was performed.

RESULTS

A total of 79 out of 314 search hits were publications on clinical trials with wearables, of which 16 were randomized controlled trials. Motion sensors were most frequently used to measure defined movements, movement disorders, or general physical activity. Approximately 20% of the studies used sensors to detect cardiovascular parameters. As for the sensor location, the wrist was chosen in most studies (22.8%).

CONCLUSION

Wearables can be used in a precisely defined medical context, when taking into account complex influencing factors.

Digitizing clinical trials

Clinical trials are a fundamental tool used to evaluate the efficacy and safety of new drugs and medical devices and other health system interventions. The traditional clinical trials system acts as a quality funnel for the development and implementation of new drugs, devices and health system interventions. The concept of a "digital clinical trial" involves leveraging digital technology to improve participant access, engagement, trial-related measurements, and/or interventions, enable concealed randomized intervention allocation, and has the potential to transform clinical trials and to lower their cost. In April 2019, the US National Institutes of Health (NIH) and the National Science Foundation (NSF) held a workshop bringing together experts in clinical trials, digital technology, and digital analytics to discuss strategies to implement the use of digital technologies in clinical trials while considering potential challenges. This position paper builds on this workshop to describe the current state of the art for digital clinical trials including (1) defining and outlining the composition and elements of digital trials; (2) describing recruitment and retention using digital technology; (3) outlining data collection elements including mobile health, wearable technologies, application programming interfaces (APIs), digital transmission of data, and consideration of regulatory oversight and guidance for data security, privacy, and remotely provided informed consent; (4) elucidating digital analytics and data science approaches leveraging artificial intelligence and machine learning algorithms; and (5) setting future priorities and strategies that should be addressed to successfully harness digital methods and the myriad benefits of such technologies for clinical research.

Wearable Sensors in Ambulatory Individuals With a Spinal Cord Injury: From Energy Expenditure Estimation to Activity Recommendations

Inappropriate physical inactivity is a global health problem increasing the risk of cardiometabolic diseases. Wearable sensors show great potential to promote physical activity and thus a healthier lifestyle. While commercial activity trackers are available to estimate energy expenditure (EE) in non-disabled individuals, they are not designed for reliable assessments in individuals with an incomplete spinal cord injury (iSCI). Furthermore, activity recommendations for this population are currently rather vague and not tailored to their individual needs, and activity guidelines provided for the non-disabled population may not be easily translated for this population. However, especially in iSCI individuals with impaired abilities to stand and walk, the assessment of physical activities and appropriate recommendations for a healthy lifestyle are challenging. Therefore, the study aimed at developing an EE estimation model for iSCI individuals able to walk based on wearable sensor data. Additionally, the data collected within this study was used to translate common activity recommendations for the non-disabled population to easily understandable activity goals for ambulatory individuals with an iSCI. In total, 30 ambulatory individuals with an iSCI were equipped with wearable sensors while performing 12 different physical activities. EE was measured continuously and demographic and anthropometric variables, clinical assessment scores as well as wearable-sensor-derived features were used to develop different EE estimation models. The best EE estimation model comprised the estimation of resting EE using the updated Harris-Benedict equation, classifying activities using a k-nearest neighbor algorithm, and applying a multiple linear regression-based EE estimation model for each activity class. The mean absolute estimation error of this model was 15.2 ± 6.3% and the corresponding mean signed error was −3.4 ± 8.9%. Translating activity recommendations of global health institutions, we suggest a minimum of 2,000–3,000 steps per day for ambulatory individuals with an iSCI. If ambulatory individuals with an iSCI targeted the popular 10,000 steps a day recommendation for the non-disabled population, their equivalent would be around 8,000 steps a day. The combination of the presented dedicated EE estimation model for ambulatory individuals with an iSCI and the translated activity recommendations is an important step toward promoting an active lifestyle in this population.

Outcome Measures of Free-Living Activity in Spinal Cord Injury Rehabilitation

PURPOSE OF REVIEW

The purpose of this article was to describe the utilization of body worn activity monitors in the SCI population and discuss the challenges of using body worn sensors in rehabilitation research.

RECENT FINDINGS

Many activity monitor-based measures have been used and validated in the SCI population including stroke number, push frequency, upper limb activity counts and wheelchair propulsion distance measured from a sensor attached to the wheelchair.

SUMMARY

The ability to accurately measure physical activity in the free-living environment using body-worn sensors has the potential to enhance the understanding of barriers to adequate activity and identify possible effective interventions. As the use of activity monitors used in SCI rehabilitation research continues to grow, care must be taken to overcome challenges related to participant adherence and data quality.

Wearable Sensors to Monitor, Enable Feedback, and Measure Outcomes of Activity and Practice

PURPOSE OF REVIEW

Measurements obtained during real-world activity by wearable motion sensors may contribute more naturalistic accounts of clinically meaningful changes in impairment, activity, and participation during neurologic rehabilitation, but obstacles persist. Here we review the basics of wearable sensors, the use of existing systems for neurological and rehabilitation applications and their limitations, and strategies for future use.

RECENT FINDINGS

Commercial activity-recognition software and wearable motion sensors for community monitoring primarily calculate steps and sedentary time. Accuracy declines as walking speed slows below 0.8 m/s, less so if worn on the foot or ankle. Upper-extremity sensing is mostly limited to simple inertial activity counts. Research software and activity-recognition algorithms are beginning to provide ground truth about gait cycle variables and reveal purposeful arm actions. Increasingly, clinicians can incorporate inertial and other motion signals to monitor exercise, activities of daily living, and the practice of specific skills, as well as provide tailored feedback to encourage self-management of rehabilitation. Efforts are growing to create a compatible collection of clinically relevant sensor applications that capture the type, quantity, and quality of everyday activity and practice in known contexts. Such data would offer more ecologically sound measurement tools, while enabling clinicians to monitor and support remote physical therapies and behavioral modification when combined with telemedicine outreach.

The Best Digital Biomarkers Papers of 2017

The use and evaluation of digital biomarkers, objective and quantifiable measures of biology, and health collected through digital devices is growing rapidly. To highlight some of the most promising work in the field, we have compiled a list of the top digital biomarkers papers from the past year. Eligible papers reported on original research that evaluated a digital sensor (e.g., smartphone, wearable sensor, implantable device) in humans and was published in a peer-reviewed journal in 2017. Nominations were solicited from the editorial board of Digital Biomarkers and supplemented by papers the editorial team identified from Web of Science, Google Scholar, and PubMed. The editorial board then selected up to ten papers to be recognized among 28 nominations. Here, we present all of the nominated papers and profile the eight that received the most votes. The top eight papers evaluated 1,290 individuals with digital pills, smartwatches, wearable devices, and electronic inhalers in disease states ranging from dementia to diabetes and from Parkinson disease to pain.

Views of individuals with spinal cord injury on the use of wearable cameras to monitor upper limb function in the home and community

OBJECTIVE

Hand function impairment after cervical spinal cord injury (SCI) can significantly reduce independence. Unlike current hand function assessments, wearable camera systems could potentially measure functional hand usage at home, and thus benefit the development of neurorehabilitation strategies. The objective of this study was to understand the views of individuals with SCI on the use of wearable cameras to track neurorehabilitation progress and outcomes in the community.

DESIGN

Questionnaires.

SETTING

Home simulation laboratory.

PARTICIPANTS

Fifteen individuals with cervical SCI.

OUTCOME MEASURES

After using wearable cameras in the simulated home environment, participants completed custom questionnaires, comprising open-ended and structured questions.

RESULTS

Participants showed relatively low concerns related to data confidentiality when first-person videos are used by clinicians (1.93 ± 1.28 on a 5-point Likert scale) or researchers (2.00 ± 1.31). Storing only automatically extracted metrics reduced privacy concerns. Though participants reported moderate privacy concerns (2.53 ± 1.51) about wearing a camera in daily life due to certain sensitive situations (e.g. washrooms), they felt that information about their hand usage at home is useful for researchers (4.73 ± 0.59), clinicians (4.47 ± 0.83), and themselves (4.40 ± 0.83). Participants found the system moderately comfortable (3.27 ± 1.44), but expressed low desire to use it frequently (2.87 ± 1.36).

CONCLUSION

Despite some privacy and comfort concerns, participants believed that the information obtained would be useful. With appropriate strategies to minimize the data stored and recording duration, wearable cameras can be a well-accepted tool to track function in the home and community after SCI.

Monitoring Upper Limb Recovery after Cervical Spinal Cord Injury: Insights beyond Assessment Scores

BACKGROUND

Preclinical investigations in animal models demonstrate that enhanced upper limb (UL) activity during rehabilitation promotes motor recovery following spinal cord injury (SCI). Despite this, following SCI in humans, no commonly applied training protocols exist, and therefore, activity-based rehabilitative therapies (ABRT) vary in frequency, duration, and intensity. Quantification of UL recovery is limited to subjective questionnaires or scattered measures of muscle function and movement tasks.

OBJECTIVE

To objectively measure changes in UL activity during acute SCI rehabilitation and to assess the value of wearable sensors as novel measurement tools that are complimentary to standard clinical assessments tools.

METHODS

The overall amount of UL activity and kinematics of wheeling were measured longitudinally with wearable sensors in 12 thoracic and 19 cervical acute SCI patients (complete and incomplete). The measurements were performed for up to seven consecutive days, and simultaneously, SCI-specific assessments were made during rehabilitation sessions 1, 3, and 6 months after injury. Changes in UL activity and function over time were analyzed using linear mixed models.

RESULTS

During acute rehabilitation, the overall amount of UL activity and the active distance wheeled significantly increased in tetraplegic patients, but remained constant in paraplegic patients. The same tendency was shown in clinical scores with the exception of those for independence, which showed improvements at the beginning of the rehabilitation period, even in paraplegic subjects. In the later stages of acute rehabilitation, the quantity of UL activity in tetraplegic individuals matched that of their paraplegic counterparts, despite their greater motor impairments. Both subject groups showed higher UL activity during therapy time compared to the time outside of therapy time.

CONCLUSION

Tracking day-to-day UL activity is necessary to gain insights into the real impact of a patient's impairments on their UL movements during therapy and during their leisure time. In the future, this novel methodology may be used to reliably control and adjust ABRT and to evaluate the progress of UL rehabilitation in clinical trials.