Direct measurement of human movement by accelerometry

A Novel Parameterisation of Phase Plots for Monitoring of Parkinson's Disease

Parkinson's Disease (PD) can lead to impaired/slowed movement, gait impairments and increased risk of falling. Wearable technology-based gait analysis is emerging as a powerful tool to detect early disease and monitor progression. Here we present a novel approach to producing an objective, compact and personalised overview of a patient's gait pattern. Phase plots were constructed in 41 people with PD and 38 controls (CL) from accelerometry data collected during straight intermittent walks with a single triaxial accelerometer placed on the lower back. Phase plots were analysed using bivariate Gaussian mixture models and classified based on several apparent features derived from the parameters of said model. Significant differences in phase plot form were found between and PD and CL subjects; with a very high within-subject consistency (reproducibility) (p <; 0.0001). PD and CL subjects differ in the types of phase plots produced (p <; 0.001). Strong connections between spatio-temporal (ST) gait characteristics and phase plot types were found. The presented novel methodology not only showed to be sensitive to pathology (PD vs CL), but can quickly produce a unique fingerprint of a person's gait. This work presents encouraging results for clinical application of an objective, personalised gait feature for disease monitoring and clinical applications.

Feasibility of using acceleration-derived jerk to quantify bimanual arm use

BACKGROUND

Accelerometers have become common for evaluating the efficacy of rehabilitation for patients with neurologic disorders. For example, metrics like use ratio (UR) and magnitude ratio (MR) have been shown to differentiate movement patterns of children with cerebral palsy (CP) compared to typically-developing (TD) peers. However, these metrics are calculated from "activity counts" - a measure based on proprietary algorithms that approximate movement duration and intensity from raw accelerometer data. Algorithms used to calculate activity counts vary between devices, limiting comparisons of clinical and research results. The goal of this research was to develop complementary metrics based on raw accelerometer data to analyze arm movement after neurologic injury.

METHOD

We calculated jerk, the derivative of acceleration, to evaluate arm movement from accelerometer data. To complement current measures, we calculated jerk ratio (JR) as the relative jerk magnitude of the dominant (non-paretic) and non-dominant (paretic) arms. We evaluated the JR distribution between arms and calculated the 50th percentile of the JR distribution (JR50). To evaluate these metrics, we analyzed bimanual accelerometry data for five children with hemiplegic CP who underwent Constraint-Induced Movement Therapy (CIMT) and five typically developing (TD) children. We compared JR between the CP and TD cohorts, and to activity count metrics.

RESULTS

The JR50 differentiated between the CP and TD cohorts (CP = 0.578 ± 0.041 before CIMT, TD = 0.506 ± 0.026), demonstrating increased reliance on the dominant arm for the CP cohort. Jerk metrics also quantified changes in arm use during and after therapy (e.g., JR50 = 0.378 ± 0.125 during CIMT, 0.591 ± 0.057 after CIMT). The JR was strongly correlated with UR and MR (r = - 0.92, 0.89) for the CP cohort. For the TD cohort, JR50 was repeatable across three data collection periods with an average similarity of 0.945 ± 0.015.

CONCLUSIONS

Acceleration-derived jerk captured differences in motion between TD and CP cohorts and correlated with activity count metrics. The code for calculating and plotting JR is open-source and available for others to use and build upon. By identifying device-independent metrics that can quantify arm movement in daily life, we hope to facilitate collaboration for rehabilitation research using wearable technologies.

Detection and analysis of pulse waves during sleep via wrist-worn actigraphy

The high temporal and intensity resolution of modern accelerometers gives the opportunity of detecting even tiny body movements via motion-based sensors. In this paper, we demonstrate and evaluate an approach to identify pulse waves and heartbeats from acceleration data of the human wrist during sleep. Specifically, we have recorded simultaneously full-night polysomnography and 3d wrist actigraphy data of 363 subjects during one night in a clinical sleep laboratory. The acceleration data was segmented and cleaned, excluding body movements and separating episodes with different sleep positions. Then, we applied a bandpass filter and a Hilbert transform to uncover the pulse wave signal, which worked well for an average duration of 1.7 h per subject. We found that 81 percent of the detected pulse wave intervals could be correctly associated with the R peak intervals from independently recorded ECGs and obtained a median Pearson cross-correlation of 0.94. While the low-frequency components of both signals were practically identical, the high-frequency component of the pulse wave interval time series was increased, indicating a respiratory modulation of pulse transit times, probably as an additional contribution to respiratory sinus arrhythmia. Our approach could be used to obtain long-term nocturnal heartbeat interval time series and pulse wave signals from wrist-worn accelerometers without the need of recording ECG or photoplethysmography. This is particularly useful for an ambulatory monitoring of high-risk cardiac patients as well as for assessing cardiac dynamics in large cohort studies solely with accelerometer devices that are already used for activity tracking and sleep pattern analysis.

Optimization and Validation of an Adjustable Activity Classification Algorithm for Assessment of Physical Behavior in Elderly

Due to a lack of transparency in both algorithm and validation methodology, it is difficult for researchers and clinicians to select the appropriate tracker for their application. The aim of this work is to transparently present an adjustable physical activity classification algorithm that discriminates between dynamic, standing, and sedentary behavior. By means of easily adjustable parameters, the algorithm performance can be optimized for applications using different target populations and locations for tracker wear. Concerning an elderly target population with a tracker worn on the upper leg, the algorithm is optimized and validated under simulated free-living conditions. The fixed activity protocol (FAP) is performed by 20 participants; the simulated free-living protocol (SFP) involves another 20. Data segmentation window size and amount of physical activity threshold are optimized. The sensor orientation threshold does not vary. The validation of the algorithm is performed on 10 participants who perform the FAP and on 10 participants who perform the SFP. Percentage error (PE) and absolute percentage error (APE) are used to assess the algorithm performance. Standing and sedentary behavior are classified within acceptable limits (±10% error) both under fixed and simulated free-living conditions. Dynamic behavior is within acceptable limits under fixed conditions but has some limitations under simulated free-living conditions. We propose that this approach should be adopted by developers of activity trackers to facilitate the activity tracker selection process for researchers and clinicians. Furthermore, we are convinced that the adjustable algorithm potentially could contribute to the fast realization of new applications.

Sleep assessment devices: types, market analysis, and a critical view on accuracy and validation

Introduction: Sleep assessment devices are essential for the detection, diagnosis, and monitoring of sleep disorders. This paper provides a state-of-the-art review and comparison of sleep assessment devices and a market analysis.Areas covered: Hardware devices are classified into contact and contactless devices. For each group, the underlying technologies are presented, paying special attention to their limitations. A systematic literature review has been carried out by comparing the most important validation studies of sleep tracking devices in terms of sensitivity and specificity. A market analysis has also been carried out in order to list the most used, best-selling, and most highly-valued devices. Software apps have also been compared with regards to the market.Expert opinion: Thanks to technological advances, the reliability and accuracy of sensors has been significantly increased in recent years. According to validation studies, some actigraphs present a sensibility higher than 90%. However, the market analysis reveals that many hardware devices have not been validated, and especially software devices should be studied before their clinical use.

Identification of Gait Motion Patterns Using Wearable Inertial Sensor Network

Gait signifies the walking pattern of an individual. It may be normal or abnormal, depending on the health condition of the individual. This paper considers the development of a gait sensor network system that uses a pair of wireless inertial measurement unit (IMU) sensors to monitor the gait cycle of a user. The sensor information is used for determining the normality of movement of the leg. The sensor system places the IMU sensors on one of the legs to extract the three-dimensional angular motions of the hip and knee joints while walking. The wearable sensor is custom-made at San Diego State University with wireless data transmission capability. The system enables the user to collect gait data at any site, including in a non-laboratory environment. The paper also presents the mathematical calculations to decompose movements experienced by a pair of IMUs into individual and relative three directional hip and knee joint motions. Further, a new approach of gait pattern classification based on the phase difference angles between hip and knee joints is presented. The experimental results show a potential application of the classification method in the areas of smart detection of abnormal gait patterns.

Variations in glenohumeral movement control when implementing an auditory feedback system: A pilot study

Introduction: Human motor control requires a learning process and it can be trained by means of various sensory feedback sources.Objective: To determine variations in glenohumeral movement control by learning in young adults exposed to an auditory feedback system while they perform object translation tasks classified by difficulty level.Materials and methods: The study involved 45 volunteers of both sexes (22 women), aged between 18 and 32 years. Glenohumeral movement control was measured by means of the root mean square (RMS) of the accelerometry signal, while task execution speed (TES) was measured using an accelerometer during the execution of the task according to its difficulty (easy, moderate and hard) in four stages of randomized intervention (control, pre-exposure, exposure-with auditory feedback, and post-exposure).Results: Statistically significant differences (p<0.001) were found between the pre-exposure and exposure stages and between pre-exposure and post-exposure stages. A significant increase (p <0.001) in TES was identified between the pre-exposure and exposure stages for tasks classified as easy and hard, respectively.Conclusion: The use of an auditory feedback system in young adults without pathologies enhanced learning and glenohumeral movement control without reducing TES. This effect was maintained after the feedback, so the use of this type of feedback system in healthy individuals could result in a useful strategy for the training of motor control of the shoulder.

Computer Vision-Based Unobtrusive Physical Activity Monitoring in School by Room-Level Physical Activity Estimation: A Method Proposition

As sedentary lifestyles and childhood obesity are becoming more prevalent, research in the field of physical activity (PA) has gained much momentum. Monitoring the PA of children and adolescents is crucial for ascertaining and understanding the phenomena that facilitate and hinder PA in order to develop effective interventions for promoting physically active habits. Popular individual-level measures are sensitive to social desirability bias and subject reactivity. Intrusiveness of these methods, especially when studying children, also limits the possible duration of monitoring and assumes strict submission to human research ethics requirements and vigilance in personal data protection. Meanwhile, growth in computational capacity has enabled computer vision researchers to successfully use deep learning algorithms for real-time behaviour analysis such as action recognition. This work analyzes the weaknesses of existing methods used in PA research; gives an overview of relevant advances in video-based action recognition methods; and proposes the outline of a novel action intensity classifier utilizing sensor-supervised learning for estimating ambient PA. The proposed method, if applied as a distributed privacy-preserving sensor system, is argued to be useful for monitoring the spatio-temporal distribution of PA in schools over long periods and assessing the efficiency of school-based PA interventions.

Estimation of Knee Joint Forces in Sport Movements Using Wearable Sensors and Machine Learning

Knee joint forces (KJF) are biomechanical measures used to infer the load on knee joint structures. The purpose of this study is to develop an artificial neural network (ANN) that estimates KJF during sport movements, based on data obtained by wearable sensors. Thirteen participants were equipped with two inertial measurement units (IMUs) located on the right leg. Participants performed a variety of movements, including linear motions, changes of direction, and jumps. Biomechanical modelling was carried out to determine KJF. An ANN was trained to model the association between the IMU signals and the KJF time series. The ANN-predicted KJF yielded correlation coefficients that ranged from 0.60 to 0.94 (vertical KJF), 0.64 to 0.90 (anterior-posterior KJF) and 0.25 to 0.60 (medial-lateral KJF). The vertical KJF for moderate running showed the highest correlation (0.94 ± 0.33). The summed vertical KJF and peak vertical KJF differed between calculated and predicted KJF across all movements by an average of 5.7% ± 5.9% and 17.0% ± 13.6%, respectively. The vertical and anterior-posterior KJF values showed good agreement between ANN-predicted outcomes and reference KJF across most movements. This study supports the use of wearable sensors in combination with ANN for estimating joint reactions in sports applications.

Sedentary Thresholds for Accelerometry-Based Mean Amplitude Deviation and Electromyography Amplitude in 7-11 Years Old Children

We investigated the ability of energy expenditure, movement sensing, and muscle activity to discriminate sedentary and non-sedentary activities in children. Thirty-five 7–11-year-old children participated in the study. Simultaneous assessment of oxygen uptake (V̇O₂), triaxial accelerometry, and thigh muscle electromyography (EMG) were performed during eight different sedentary and non-sedentary activities including lying down, sitting-, standing-, and walking-related activities, which were performed in a random order. Mean values of V̇O₂, accelerometry, and EMG from the concurrent 2 min epochs during each activity were computed. Resting energy expenditure (REE) was measured during 30 min supine rest. Directly measured metabolic equivalent of tasks (METs, V̇O₂ in activities/V̇O₂ in REE) were calculated for each activity. Mean amplitude deviation (MAD) was computed for accelerometry. EMG was normalized for mean muscle activity during self-paced walking. The classification accuracy of METs, MAD, and EMG to discriminate sedentary activities from physical activities was investigated by receiver operating characteristic curves and optimal cut-offs based on maximal sensitivity and specificity. Mean (SD) REE was 5.0 ± 0.8 ml/kg/min. MET, MAD, and EMG values ranged from 1.0 to 4.9, 0.0020 to 0.4146 g, and 4.3 to 133.9% during lying down and walking at 6 km/h, respectively. Optimal cut-offs to discriminate sedentary activities from non-sedentary activities were 1.3 for METs (sensitivity = 82%, specificity = 88%), 0.0033 g for MAD (sensitivity = 80%, specificity = 91%), and 11.9% for EMG (sensitivity = 79%, specificity = 92%). In conclusion, this study provides applicable thresholds to differentiate sitting and standing and sedentary and non-sedentary activities based on METs, MAD, and EMG in young children.

Smartphone-Based Assessment of Gait During Straight Walking, Turning, and Walking Speed Modulation in Laboratory and Free-Living Environments

As turns and walking speed modulation are crucial for functional mobility, development of a field-based tool to objectively evaluate non-steady-state gait is essential. This study aimed to quantify spatiotemporal gait using three Android smartphones during steady-state walking, turns, and gait speed modulation in laboratory and free-living environments. In total, 24 adults ambulated along a 10-m walkway in both environments under seven conditions: straight walking, 90° left or right turn, and modulating gait speed from usual-slow, usual-fast, slow-fast, and fast-slow. Two smartphones were attached to the body, with another phone placed in a shoulder bag. Gait velocity, step time, step length, cadence, and symmetry were computed from smartphone-based tri-axial accelerometers and validated with motion capture and video, in laboratory and free-living environments, respectively. Validity was assessed using Pearson's correlation and Bland-Altman analysis. Gait velocity results revealed moderate to very high validity across all walking conditions, smartphone models, smartphone locations, and environments. Correlations for gait velocity ranged between 0.87-0.91 and 0.79-0.83 for straight walking, 0.86-0.95 and 0.86-0.89 for turning, and 0.51-0.90 and 0.67-0.89 for speed modulation trials, in laboratory and free-living environments, respectively. Step time, step length, and cadence demonstrated high to very high correlations for straight walking and turns. However, symmetry results revealed high correlations only during straight walking in the laboratory. Conditions that included slow walking showed negligible to moderate validity with a high bias. In conclusion, smartphones can be employed as field-based devices to assess steady-state walking, turning, and speed modulation across environment, model, and placement when walking faster than 0.5 m/s.

Sleep tracking: A systematic review of the research using commercially available technology

PURPOSE OF REVIEW

To systematically review the available research studies that characterize the benefits, uncertainty, or weaknesses of commercially-available sleep tracking technology.

RECENT FINDINGS

Sleep is a vital component of health and well-being. Research shows that tracking sleep using commercially available sleep tracking technology (e.g., wearable or smartphone-based) is increasingly popular in the general population.

METHODS

Systematic literature searches were conducted using PubMed/Medline, Embase (Ovid) the Cochrane Library, PsycINFO (Ovid), CINAHL, and Web of Science Plus (which included results from Biosis Citation Index, INSPEC, and Food, Science & Technology Abstracts) (n=842).

STUDY INCLUSION AND EXCLUSION CRITERIA

Three independent reviewers reviewed eligible articles that administered a commercially-available sleep tracker to participants and reported on sleep parameters as captured by the tracker, including either sleep duration or quality. Eligible articles had to include sleep data from users for >=4 nights.

Classifying Diverse Physical Activities Using "Smart Garments"

Physical activities can have important impacts on human health. For example, a physically active lifestyle, which is one of the most important goals for overall health promotion, can diminish the risk for a range of physical disorders, as well as reducing health-related expenditures. Thus, a long-term goal is to detect different physical activities, and an important initial step toward this goal is the ability to classify such activities. A recent and promising technology to discriminate among diverse physical activities is the smart textile system (STS), which is becoming increasingly accepted as a low-cost activity monitoring tool for health promotion. Accordingly, our primary aim was to assess the feasibility and accuracy of using a novel STS to classify physical activities. Eleven participants completed a lab-based experiment to evaluate the accuracy of an STS that featured a smart undershirt (SUS) and commercially available smart socks (SSs) in discriminating several basic postures (sitting, standing, and lying down), as well as diverse activities requiring participants to walk and run at different speeds. We trained three classification methods—K-nearest neighbor, linear discriminant analysis, and artificial neural network—using data from each smart garment separately and in combination. Overall classification performance (global accuracy) was ~98%, which suggests that the STS was effective for discriminating diverse physical activities. We conclude that, overall, smart garments represent a promising area of research and a potential alternative for discriminating a range of physical activities, which can have positive implications for health promotion.

A Combination of Indoor Localization and Wearable Sensor-Based Physical Activity Recognition to Assess Older Patients Undergoing Subacute Rehabilitation: Baseline Study Results

Background

Health care, in recent years, has made great leaps in integrating wireless technology into traditional models of care. The availability of ubiquitous devices such as wearable sensors has enabled researchers to collect voluminous datasets and harness them in a wide range of health care topics. One of the goals of using on-body wearable sensors has been to study and analyze human activity and functional patterns, thereby predicting harmful outcomes such as falls. It can also be used to track precise individual movements to form personalized behavioral patterns, to standardize the concept of frailty, well-being/independence, etc. Most wearable devices such as activity trackers and smartwatches are equipped with low-cost embedded sensors that can provide users with health statistics. In addition to wearable devices, Bluetooth low-energy sensors known as BLE beacons have gained traction among researchers in ambient intelligence domain. The low cost and durability of newer versions have made BLE beacons feasible gadgets to yield indoor localization data, an adjunct feature in human activity recognition. In the studies by Moatamed et al and the patent application by Ramezani et al, we introduced a generic framework (Sensing At-Risk Population) that draws on the classification of human movements using a 3-axial accelerometer and extracting indoor localization using BLE beacons, in concert.

Objective

The study aimed to examine the ability of combination of physical activity and indoor location features, extracted at baseline, on a cohort of 154 rehabilitation-dwelling patients to discriminate between subacute care patients who are re-admitted to the hospital versus the patients who are able to stay in a community setting.

Methods

We analyzed physical activity sensor features to assess activity time and intensity. We also analyzed activities with regard to indoor localization. Chi-square and Kruskal-Wallis tests were used to compare demographic variables and sensor feature variables in outcome groups. Random forests were used to build predictive models based on the most significant features.

Results

Standing time percentage (P<.001, d=1.51), laying down time percentage (P<.001, d=1.35), resident room energy intensity (P<.001, d=1.25), resident bed energy intensity (P<.001, d=1.23), and energy percentage of active state (P=.001, d=1.24) are the 5 most statistically significant features in distinguishing outcome groups at baseline. The energy intensity of the resident room (P<.001, d=1.25) was achieved by capturing indoor localization information. Random forests revealed that the energy intensity of the resident room, as a standalone attribute, is the most sensitive parameter in the identification of outcome groups (area under the curve=0.84).

Conclusions

This study demonstrates that a combination of indoor localization and physical activity tracking produces a series of features at baseline, a subset of which can better distinguish between at-risk patients that can gain independence versus the patients that are rehospitalized.

Inertial wearables as pragmatic tools in dementia

Dementia is a critically important issue due to its wide impact on health services as well as its personal and societal costs. Limitations exist for current dementia protocols, and there are calls to introduce modern technology that facilitates the addition of digital biomarkers to routine clinical practice. Wearable technology (wearables) are nearly ubiquitous in everyday life, gathering discrete and continuous digital data on habitual activities, but their utility in modern medicine remains low. Due to advances in data analytics, wearables are now commonly discussed as pragmatic tools to aid the diagnosis and treatment of a range of neurological disorders. Inertial sensor-based wearables are one such technology; they offer a low-cost approach to quantify routine movements that are fundamental to normal activities of daily living, most notably postural control and gait. Here, we provide a narrative review of how wearables are providing useful postural control and gait data to facilitate the capture of digital markers to aid dementia research. We outline the history of wearables, from their humble beginnings to their current use beyond the clinic, and explore their integration into modern systems, as well as the ongoing standardisation and regulatory efforts to integrate their use in clinical trials.

Associations between self-reported and objectively measured physical activity and overweight/obesity among adults in Kota Bharu and Penang, Malaysia

BACKGROUND

For the past decades, Malaysia has seen an increased prevalence of overweight and obesity which leads to significant health threats. Physical activity is beneficial in maintaining healthy body weight. The objective of this study was to measure physical activity of adults in Malaysia using objective measurement (accelerometer) and self-reported methods, as well as to determine their associations with (body mass index (BMI) and waist circumference (WC) measurements.

METHODS

Four-hundred and ninety Malaysian adults (n = 490) aged 20 to 65 years old participated in this cross-sectional study. Their body weight, height, and WC measurements were measured according to standard procedures. Physical activity was assessed objectively with accelerometers for five to seven consecutive days. The International Physical Activity Questionnaire (IPAQ) was used to estimate the amount of time spent on various domains of physical activity. Mixed models were used to determine the associations between physical activity variables and both BMI and WC.

RESULTS

The mean value of objectively measured moderate-to-vigorous physical activity (MVPA) was 13.5 min per day, in which male participants recorded a significantly higher amount of time compared to females. On the other hand, the mean self-reported total physical activity was 380 min per week; male participants reported a significantly higher amount of time on physical activity in the occupation/work and leisure/recreation domains while female participants spent significantly more time in the domestic/household chores domain. We also observed that the mean values of objectively measured total MVPA, self-reported time spent on walking for leisure/recreation, and total time amount of time spent on MVPA for leisure/recreation were significantly higher among participants with BMI of less than 25 kg/m2. The final statistical model yielded a significant negative association between objectively measured total MVPA and BMI, but not with WC measurement. No significant association was reported between self-reported total physical activity with BMI and WC measurement.

CONCLUSIONS

Objectively measured MVPA was inversely associated with BMI, but not WC measurement. No significant association was observed between self-reported total physical activity and physical activity time measures across domains with both BMI and WC measurement.

On Placement, Location and Orientation of Wrist-Worn Tri-Axial Accelerometers during Free-Living Measurements

Wearable accelerometers have recently become a standalone tool for the objective assessment of physical activity (PA). In free-living studies, accelerometers are placed by protocol on a pre-defined body location (e.g., non-dominant wrist). However, the protocol is not always followed, e.g., the sensor can be moved between wrists or reattached in a different orientation. Such protocol violations often result in PA miscalculation. We propose an approach, PLOE ("Placement, Location and Orientation Evaluation method"), to determine the sensor position using statistical features from the raw accelerometer measurements. We compare the estimated position with the study protocol and identify discrepancies. We apply PLOE to the measurements collected from 45 older adults who wore ActiGraph GT3X+ accelerometers on the left and right wrist for seven days. We found that 15.6% of participants who wore accelerometers violated the protocol for one or more days. The sensors were worn on the wrong hand during 6.9% of the days of simultaneous wearing of devices. During the periods of discrepancies, the daily PA was miscalculated by more than 20%. Our findings show that correct placement of the device has a significant effect on the PA estimates. These results demonstrate a need for the evaluation of sensor position.

Validity and Reliability of Wearable Sensors for Joint Angle Estimation: A Systematic Review

Motion capture systems are recognized as the gold standard for joint angle calculation. However, studies using these systems are restricted to laboratory settings for technical reasons, which may lead to findings that are not representative of real-life context. Recently developed commercial and home-made inertial measurement sensors (M/IMU) are potentially good alternatives to the laboratory-based systems, and recent technology improvements required a synthesis of the current evidence. The aim of this systematic review was to determine the criterion validity and reliability of M/IMU for each body joint and for tasks of different levels of complexity. Five different databases were screened (Pubmed, Cinhal, Embase, Ergonomic abstract, and Compendex). Two evaluators performed independent selection, quality assessment (consensus-based standards for the selection of health measurement instruments [COSMIN] and quality appraisal tools), and data extraction. Forty-two studies were included. Reported validity varied according to task complexity (higher validity for simple tasks) and the joint evaluated (better validity for lower limb joints). More studies on reliability are needed to make stronger conclusions, as the number of studies addressing this psychometric property was limited. M/IMU should be considered as a valid tool to assess whole body range of motion, but further studies are needed to standardize technical procedures to obtain more accurate data.

Falls Risk Classification of Older Adults Using Deep Neural Networks and Transfer Learning

Prior research in falls risk classification using inertial sensors has relied on the use of engineered features, which has resulted in a feature space containing hundreds of features that are likely redundant and possibly irrelevant. In this paper, we propose using fully convolutional neural networks (FCNNs) to classify older adults at low or high risk of falling using inertial sensor data collected from a smartphone. Due to the limited nature of older adult inertial gait datasets, we first pre-train the FCNN models using a publicly available dataset for pedestrian activity recognition. Then via transfer learning, we train the network for falls risk classification. We show that via transfer learning, our falls risk classifier obtains an area under the receiver operating characteristic curve of 93.3%, which is 10.6% higher than the equivalent model trained without the use of transfer learning. Additionally, we show that our method outperforms other standard machine learning classifiers trained on features developed in prior research.

Accuracy of Accelerometers for Measuring Physical Activity and Levels of Sedentary Behavior in Children: A Systematic Review

Objectives: This systematic review evaluated the accuracy of triaxial and omnidirectional accelerometers for measuring physical activity and sedentary behavior in children. Design: Systematic review of the literature. Methods: We comprehensively searched several databases for studies published from January 1996 through June 2018 that reported diagnostic accuracy measures in children and adolescents (age 3-18 years) and compared accelerometers with energy expenditure using indirect calorimetry. Results: We included 11 studies that enrolled 570 participants. All studies used indirect calorimetry as the reference standard. Across the studies, median sensitivity ranged from 46% to 96% and median specificity ranged from 71% to 96%. Median area under the curve ranged from 69% to 98%. Conclusions: Accuracy measures were greatest when detecting sedentary behavior and lowest when detecting light physical activity. Accuracy was higher when the accelerometer was placed on the hip compared with the wrist. The current evidence suggests that triaxial and omnidirectional accelerometers are accurate in measuring sedentary behavior and physical activity levels in children.

Reliability of Wearable-Sensor-Derived Measures of Physical Activity in Wheelchair-Dependent Spinal Cord Injured Patients

Physical activity (PA) has been shown to have a positive influence on functional recovery in patients after a spinal cord injury (SCI). Hence, it can act as a confounder in clinical intervention studies. Wearable sensors are used to quantify PA in various neurological conditions. However, there is a lack of knowledge about the inter-day reliability of PA measures. The objective of this study was to investigate the single-day reliability of various PA measures in patients with a SCI and to propose recommendations on how many days of PA measurements are required to obtain reliable results. For this, PA of 63 wheelchair-dependent patients with a SCI were measured using wearable sensors. Patients of all age ranges (49.3 ± 16.6 years) and levels of injury (from C1 to L2, ASIA A-D) were included for this study and assessed at three to four different time periods during inpatient rehabilitation (2 weeks, 1 month, 3 months, and if applicable 6 months after injury) and after in-patient rehabilitation in their home-environment (at least 6 months after injury). The metrics of interest were total activity counts, PA intensity levels, metrics of wheeling quantity and metrics of movement quality. Activity counts showed consistently high single-day reliabilities, while measures of PA intensity levels considerably varied depending on the rehabilitation progress. Single-day reliabilities of metrics of movement quantity decreased with rehabilitation progress, while metrics of movement quality increased. To achieve a mean reliability of 0.8, we found that three continuous recording days are required for out-patients, and 2 days for in-patients. Furthermore, the results show similar weekday and weekend wheeling activity for in- and out-patients. To our knowledge, this is the first study to investigate the reliability of an extended set of sensor-based measures of PA in both acute and chronic wheelchair-dependent SCI patients. The results provide recommendations for sensor-based assessments of PA in clinical SCI studies.

Computation of spatio-temporal parameters in level walking using a single inertial system in lean and obese adolescents

In recent years, the availability of low-cost equipment capable of recording kinematic data during walking has facilitated the outdoor assessment of gait parameters, thus overcoming the limitations of three-dimensional instrumented gait analysis (3D-GA). The aim of this study is twofold: firstly, to investigate whether a single sensor on the lower trunk could provide valid spatio-temporal parameters in level walking in normal-weight and obese adolescents compared to instrumented gait analysis (GA); secondly, to investigate whether the inertial sensor is capable of capturing the spatio-temporal features of obese adolescent gait. These were assessed in 10 obese and 8 non-obese adolescents using both a single inertial sensor on the lower trunk and an optoelectronic system. The parameters obtained were not statistically different in either normal-weight or obese participants between the two methods. Obese adolescents walked with longer stance and double support phase compared to normal-weight participants. The results showed that the inertial system is a valid means of evaluating spatio-temporal parameters in obese individuals.

Use of Average Vertical Velocity and Difference in Altitude for Improving Automatic Fall Detection from Trunk Based Inertial and Barometric Pressure Measurements

Despite the extensive research that has been carried out on automatic fall detection using wearable sensors, falls in the elderly cannot be detected effectively yet. Although recent fall detection algorithms that evaluate the descent, impact and post impact phases of falls, often using vertical velocity, vertical acceleration and trunk angle respectively, tend to be more accurate than the algorithms that do not consider them, they still lack the desired accuracy required to be used among frail older adults. This study aims to improve the accuracy of fall detection algorithms by incorporating average vertical velocity and difference in altitude as additional parameters to the vertical velocity, vertical acceleration and trunk angle parameters. We tested the proposed algorithms on data recorded from a comprehensive set of falling experiments with 12 young participants. Participants wore waist-mounted accelerometer, gyroscope and barometric pressure sensors and simulated the most common types of falls observed in older adults, along with near-falls and activities of daily living (ADLs). Our results showed that, while the base algorithm with the three parameters provided 91.8% specificity, the addition of difference in altitude and average vertical velocity improved the specificity to 98.0% and 99.6%, respectively.

StraightenUp+: Monitoring of Posture during Daily Activities for Older Persons Using Wearable Sensors

Monitoring the posture of older persons using portable sensors while they carry out daily activities can facilitate the process of generating indicators with which to evaluate their health and quality of life. The majority of current research into such sensors focuses primarily on their functionality and accuracy, and minimal effort is dedicated to understanding the experience of older persons who interact with the devices. This study proposes a wearable device to identify the bodily postures of older persons, while also looking into the perceptions of the users. For the purposes of this study, thirty independent and semi-independent older persons undertook eight different types of physical activity, including: walking, raising arms, lowering arms, leaning forward, sitting, sitting upright, transitioning from standing to sitting, and transitioning from sitting to standing. The data was classified offline, achieving an accuracy of 93.5%, while overall device user perception was positive. Participants rated the usability of the device, in addition to their overall user experience, highly.

The Role of Wearable Devices in Multiple Sclerosis

Multiple sclerosis (MS) is the most common neurological disorder in young adults. The prevalence of walking impairment in people with MS (pwMS) is estimated between 41% and 75%. To evaluate the walking capacity in pwMS, the patient reported outcomes (PROs) and performance-based tests (i.e., the 2-minute walk test, the 6-minute walk test, the Timed 25-Foot Walk Test, the Timed Up and Go Test, and the Six Spot Step Test) could be used. However, some studies point out that the results of both performance-based tests and objective measures (i.e., by accelerometer) could not reflect patient reports of walking performance and impact of MS on daily life. This review analyses different motion sensors embedded in smartphones and motion wearable device (MWD) that can be useful to measure free-living walking behavior, to evaluate falls, fatigue, sedentary lifestyle, exercise, and quality of sleep in everyday life of pwMS. Caveats and limitations of MWD such as variable accuracy, user adherence, power consumption and recharging, noise susceptibility, and data management are discussed as well.

Inertial sensors versus standard systems in gait analysis: a systematic review and meta-analysis

INTRODUCTION

The increasing popularity of inertial sensors in clinical practice is not supported by precise information on their reliability or guidelines for their use in rehabilitation. The authors investigated the state of the literature concerning the use of inertial sensors for gait analysis in both healthy and pathological adults comparing traditional systems. Furthermore, trying to define directions for clinicians.

EVIDENCE ACQUISITION

In accordance with the PRISMA statement, authors searched in PubMed, Web of Science and Scopus all paper published from January 1st, 2005 until December 31st, 2017. They included both healthy and pathological adults' subjects as population, wearable or inertial sensors used for gait analysis and compared with classical gait analysis performed in a Motion Lab as intervention and comparison, gait parameters as outcomes. Considering the methodological quality, authors focused on: sample; description of the study; type of gait analysis used for comparison; type of sensor; sensor placement on the body; gait task requested.

EVIDENCE SYNTHESIS

From a total of 888 articles, 16 manuscripts were selected and 7 of them were considered for meta-analysis for different gait parameters. Demographic data, tested devices, reference systems, test procedures and outcomes were analyzed.

CONCLUSIONS

Our results show a good agreement between inertial sensors and classical gait analysis for some gait parameters, supporting their use as a solution for capturing kinematic information over an extended space and time and even outside a laboratory in real-life conditions. Authors can support the use of portable inertial sensors for a practical gait analysis in clinical setting with good reliability. It will then be the experience of the clinician to direct the decision-making process.

Sharif-Human movement instrumentation system (SHARIF-HMIS): Development and validation

The interest in wearable systems among the biomedical engineering and clinical community continues to escalate as technical refinements enhance their potential use for both indoor and outdoor applications. For example, an important wearable technology known as a microelectromechanical system (MEMS) is demonstrating promising applications in the area of biomedical engineering. Accordingly, this study was designed to investigate the Sharif-Human Movement Instrumentation System (SHARIF-HMIS), consisting of inertial measurement units (IMUs), stretchable clothing, and a data logger-all of which can be used outside the controlled environment of a laboratory, thus enhancing its overall utility. This system is lightweight, portable, able to be deliver data for almost 10 h, and features a new data-fusion algorithm using the Kalman filter with an adaptive approach. In specific terms, the data from the system's gyroscope, accelerometer, and magnetometer sensors can be combined to estimate total-body orientation; additionally, the noise level of these sensors can be changed to accommodate faster motions as well as magnetic disturbances. These variations can be incorporated within the extended Kalman filter by changing the parameters of the filter adaptively. In specific terms, the system's interface was developed to acquire data from eighteen IMUs located on the body to collect kinematic data associated with human motion. Meanwhile, a validation test involving one subject performing different shoulder motions was designed to compare data captured by SHARIF-HMIS and the VICON motion-capture system. This validation test demonstrated correlation values of >0.9. Results also confirmed that the output accuracy of the new system's sensor was <0.55, 1.5 and 3.5° for roll, pitch, and yaw directions, respectively. In summary, SHARIF-HMIS successfully collected kinematic data for specific human movements, which has promising implications for a range of sporting, biomedical, and healthcare-related applications.

Children's physical activity and sedentary time compared using assessments of accelerometry counts and muscle activity level

Background

This research compared accelerometry (ACC)-derived and muscle electromyography (EMG)-based estimates of physical activity (PA) and sedentary time in typical PA tasks and during the daily lives of children.

Methods

Data was included from two exploratory studies. In Study I, 6–7-year-old children (n = 11, 64% girls) were assessed for eight PA tasks (walking, stair negotiation, climbing, crawling, swinging, balancing, trampoline jumping and a game of tag). In Study II, 7–9-year-old children (n = 14, 38% girls) were assessed for six PA tasks (walking, sitting, static squat, single leg hops, jump for height and standing long jump), and daily PA during one day with and one day without structured exercise. Quadriceps and hamstring muscle activity and inactivity using EMG shorts and acceleration by waist-mounted accelerometer were simultaneously measured and classified as sedentary, light, moderate and vigorous activity. Data from ACC was further analyzed using five different published cut-off points and varying time windows (1−60 s) for comparison with EMG.

Results

In the PA tasks ACC counts and EMG amplitude showed marked differences in swinging, trampoline jumping, crawling, static squat, single leg hops, standing long jump and jump for height, the difference being over 170% when signals were normalized to that during walking. Furthermore, in walking, swinging, trampoline jumping, stair negotiation and crawling ACC classified over 60% of the time as vigorous-intensity activity, while EMG indicated primarily light- and moderate-intensity activities. During both days with and without exercise, ACC resulted in greater proportion of light activity (p < 0.01) and smaller proportion of moderate activity compared to EMG (p < 0.05). The choice of cut-off points and epoch length in ACC analysis influenced the classification of PA level and sedentary time. In the analysis of daily activities the cut-off points by Evenson et al. (2008) with epochs of 7.5 s and 15 s yielded the smallest difference (less than 10% of recording time at each intensity) against EMG-derived PA levels.

Discussion

This research provides novel insight on muscle activity and thereby on neuromuscular loading of major locomotor muscles during normal daily activities of children. While EMG and ACC provided similar estimates of sedentary time in 13 typical PA tasks, duration of light, moderate and vigorous PA varied considerably between the methods especially during walking, stair negotiation, crawling, swinging and trampoline jumping. Evenson et al.’s (2008) cut-off points with ≤15 s epoch provided similar classification of PA than EMG during daily life. Compared to impacts recorded using ACC, EMG can provide understanding on children’s neuromuscular loading during motor tasks that is useful when studying effects of PA interventions on, and development of, motor competence and coordination.

Inertial Sensor-Based Gait and Attractor Analysis as Clinical Measurement Tool: Functionality and Sensitivity in Healthy Subjects and Patients With Symptomatic Lumbar Spinal Stenosis

Objective: To determine if the attractor for acceleration gait data is similar among healthy persons defining a reference attractor; if exercise-induced changes in the attractor in patients with symptomatic lumbar spinal stenosis (sLSS) are greater than in healthy persons; and if the exercise-induced changes in the attractor are affected by surgical treatment.

Methods: Twenty-four healthy subjects and 19 patients with sLSS completed a 6-min walk test (6MWT) on a 30-m walkway. Gait data were collected using inertial sensors (RehaGait^®;) capturing 3-dimensional foot accelerations. Attractor analysis was used to quantify changes in low-pass filtered acceleration pattern (δM) and variability (δD) and their combination as attractor-based index (δF = δM^* δD) between the first and last 30 m of walking. These parameters were compared within healthy persons and patients with sLSS (preoperatively and 10 weeks and 12 months postoperatively) and between healthy persons and patients with sLSS. The variability in the attractor pattern among healthy persons was assessed as the standard deviation of the individual attractors.

Results: The attractor pattern differed greatly among healthy persons. The variability in the attractor between subjects was about three times higher than the variability around the attractor within subject. The change in gait pattern and variability during the 6MWT did not differ significantly in patients with sLSS between baseline and follow-up but differed significantly compared to healthy persons.

Discussion: The attractor for acceleration data varied largely among healthy subjects, and hence a reference attractor could not be generated. Moreover, the change in the attractor and its variability during the 6MWT differed between patients and elderly healthy persons but not between repeated assessments. Hence, the attractor based on low-pass filtered signals as used in this study may reflect pathology specific differences in gait characteristics but does not appear to be sufficiently sensitive to serve as outcome parameter of decompression surgery in patients with sLSS.

Validation of a Lower Back "Wearable"-Based Sit-to-Stand and Stand-to-Sit Algorithm for Patients With Parkinson's Disease and Older Adults in a Home-Like Environment

Introduction: Impaired sit-to-stand and stand-to-sit movements (postural transitions, PTs) in patients with Parkinson's disease (PD) and older adults (OA) are associated with risk of falling and reduced quality of life. Inertial measurement units (IMUs, also called "wearables") are powerful tools to monitor PT kinematics. The purpose of this study was to develop and validate an algorithm, based on a single IMU positioned at the lower back, for PT detection and description in the above-mentioned groups in a home-like environment. Methods: Four PD patients (two with dyskinesia) and one OA served as algorithm training group, and 21 PD patients (16 without and 5 with dyskinesia) and 11 OA served as test group. All wore an IMU on the lower back and were videotaped while performing everyday activities for 90-180 min in a non-standardized home-like environment. Accelerometer and gyroscope signals were analyzed using discrete wavelet transformation (DWT), a six degrees-of-freedom (DOF) fusion algorithm and vertical displacement estimation. Results: From the test group, 1,001 PTs, defined by video reference, were analyzed. The accuracy of the algorithm for the detection of PTs against video observation was 82% for PD patients without dyskinesia, 47% for PD patients with dyskinesia and 85% for OA. The overall accuracy of the PT direction detection was comparable across groups and yielded 98%. Mean PT duration values were 1.96 s for PD patients and 1.74 s for OA based on the algorithm (p < 0.001) and 1.77 s for PD patients and 1.51 s for OA based on clinical observation (p < 0.001). Conclusion: Validation of the PT detection algorithm in a home-like environment shows acceptable accuracy against the video reference in PD patients without dyskinesia and controls. Current limitations are the PT detection in PD patients with dyskinesia and the use of video observation as the video reference. Potential reasons are discussed.

Changes in trunk sway and impairment during sitting and standing in children with cerebral palsy

BACKGROUND

Poor postural control constitutes a major impairment in children with cerebral palsy (CP), compromising everyday activities such as sitting- and standing-position.

PURPOSE

In this study, we measured trunk sway during sitting- and standing-position. Additionally, we assessed trunk control ability using the trunk impairment scale (TIS), trunk control measurement scale (TCMS), and sitting assessment test for children with neuromotor dysfunction (SACND), in children with CP.

METHODS

Fifteen children (10 boys and 5 girls) were recruited for this study. Trunk sway was measured using a triaxial accelerometer that recorded variation in movement acceleration during quiet sitting- and standing-position.

RESULTS

Anterior-posterior (AP) acceleration was significantly greater in the standing position than the sitting position (p= 0.001). Medio-lateral (ML) acceleration was significantly greater in the standing position than in the sitting position (p= 0.012). The TIS total score showed a moderate negative relationship with AP acceleration (r=-0.635, p= 0.011). The TCMS total score moderately and negatively correlated with AP acceleration (r=-0.582, p= 0.023). The SACND total score moderately and positively correlated with AP acceleration (r= 0.670, p= 0.006).

CONCLUSION

Measurement of trunk sway using a triaxial accelerometer revealed a moderate correlation with trunk control test data and excellent reliability. Our findings suggest that measurement of trunk sway using a triaxial accelerometer is not time-consuming, and is simple and easy. Our approach can be applied in clinical settings to gain information on trunk control in children with CP.

Gait evaluation using inertial measurement units in subjects with Parkinson's disease

We investigated whether a wearable system based on a commercial Inertial Measurement Unit (IMU) can reliably provide the main spatiotemporal gait parameters in subjects with Parkinson's disease (PD), compared to a gold-standard optoelectronic motion capture system. The gait of 22 subjects with PD (Age: 69.4 (6.1) years; UPDRS-III: 28.0 (9.2)) was recorded simultaneously with an optoelectronic system and a commercial IMU-based wearable system. Eight spatiotemporal parameters describing the step cycle (cadence, velocity, stride length, stride duration, step length, stance, swing and double support duration) were compared between the two systems. The IMU and the optical system reported comparable gait parameters, with the exception of walking velocity (optical system, 0.72 (0.27) m∙s^-1 vs. IMU: 0.86 (0.26) m∙s^-1, p < 0.05). Although most parameters detected by the two systems were not statistically different, some of them like stride length, double support and step duration showed notable root mean square and mean absolute errors. In conclusion, the algorithm embedded in the current release of the commercial IMU requires further improvements to be properly used with subjects with PD. Overall, the IMU system was sufficiently accurate in the assessment of fundamental gait spatiotemporal parameters. The fast and simplified data recording process allowed by wearables makes this technology appealing and represents a possible solution for the quantification of gait in the clinical context, especially when using a traditional 3D optoelectronic gait analysis is not possible, and when subjects are not fully cooperative.

The use of wearable devices for walking and running gait analysis outside of the lab: A systematic review

BACKGROUND

Quantitative gait analysis is essential for evaluating walking and running patterns for markers of pathology, injury, or other gait characteristics. It is expected that the portability, affordability, and applicability of wearable devices to many different populations will have contributed advancements in understanding the real-world gait patterns of walkers and runners. Therefore, the purpose of this systematic review was to identify how wearable devices are being used for gait analysis in out-of-lab settings.

METHODS

A systematic search was conducted in the following scientific databases: PubMed, Medline, CINAHL, EMBASE, and SportDiscus. Each of the included articles was assessed using a custom quality assessment. Information was extracted from each included article regarding the participants, protocol, sensor(s), and analysis.

RESULTS

A total of 61 articles were reviewed: 47 involved gait analysis during walking, 13 involved gait analysis during running, and one involved both walking and running. Most studies performed adequately on measures of reporting, and external and internal validity, but did not provide a sufficient description of power. Small, unobtrusive wearable devices have been used in retrospective studies, producing unique measures of gait quality. Walking, but not running, studies have begun to use wearable devices for gait analysis among large numbers of participants in their natural environment.

CONCLUSIONS

Despite the advantages provided by the portability and accessibility of wearable devices, more studies monitoring gait over long periods of time, among large numbers of participants, and in natural walking and running environments are needed to analyze real-world gait patterns, and would facilitate prospective, subject-specific, and subgroup investigations. The development of wearables-specific metrics for gait analysis provide insights regarding the quality of gait that cannot be determined using traditional components of in-lab gait analyses. However, guidelines for the usability of wearable devices and the validity of wearables-based measurements of gait quality need to be established.

Objective profiling of varied human motion based on normative assessment of magnetometer time series data

OBJECTIVE

To quantify varied human motion and obtain an objective assessment of relative performance across a cohort.

APPROACH

A wrist-worn magnetometer was used to record and quantify the complex motion patterns of 55 children aged 10 to 12 years old, generated during a fundamental movement skills programme. Sensor-based quantification of the physical activity used dynamic time warping of the magnetometer time series data for pairs of children. Pairwise comparison across the whole cohort produced a similarity matrix of all child to child correlations. Normative assessment scores were based on the Euclidean distance between n participants within an n  -  1 multi-variate space, created from multi-dimensional scaling of the similarity matrix. The sensor-based scores were compared to the current standardised assessment which involves binary scoring of technique, outcome and time components by trained assessors.

MAIN RESULTS

Visualisation of the relative performance using the first three axes of the multi-dimensional matrix, shows a 'performance sphere' in which children sit on concentric shells of increasing radius as performance deteriorates. Good agreement between standard and sensor scores is found, with Spearman rank correlation coefficients of the overall activity score in the range of 0.62-0.71 for different cohorts and a kappa statistic of 0.34 for categorisation of all 55 children into lower, middle, upper tertile and top 5% bands.

SIGNIFICANCE

By using multi-dimensional analysis of similarity measures between participants rather than direct parameterisation of the physiological data, complex and varied patterns of physical motion can be quantified, allowing objective and robust profiling of relative function across participant groups.

The Mouse as a Model Organism for Assessing Anesthetic Sensitivity

The mouse has been used in many medical fields as a powerful model to reveal the genetic basis of human physiology and disease. The past two decades have witnessed an enormous wealth of genetic and informatic resources dedicated to this humble organism. With the ongoing revolution in mapping neural circuitry governing behavior, the mouse is an ideal model organism poised to unravel the mysteries of general anesthetic action. This chapter will describe and provide guidelines for anesthetic phenotyping in the mouse including both motor-dependent and motor-independent assessments.

Laboratory- and community-based health outcomes in people with transtibial amputation using crossover and energy-storing prosthetic feet: A randomized crossover trial

Contemporary prosthetic feet are generally optimized for either daily or high-level activities. Prosthesis users, therefore, often require multiple prostheses to participate in activities that span a range of mobility. Crossover feet (XF) are designed to increase the range of activities that can be performed with a single prosthesis. However, little evidence exists to guide clinical prescription of XF relative to traditional energy storing feet (ESF). The objective of this study was to assess the effects of XF and ESF on health outcomes in people with transtibial amputation. A randomized crossover study was conducted to assess changes in laboratory-based (endurance, perceived exertion, walking performance) and community-based (step activity and self-reported mobility, fatigue, balance confidence, activity restrictions, and satisfaction) outcomes. Twenty-seven participants were fit with XF and ESF prostheses with standardized sockets, interfaces, and suspensions. Participants were not blinded to the intervention, and wore each prosthesis for one month while their steps were counted with an activity monitor. After each accommodation period, participants returned for data collection. Endurance and perceived exertion were measured with the Six-Minute Walk Test and Borg-CR100, respectively. Walking performance was measured using an electronic walkway. Self-reported mobility, fatigue, balance confidence, activity restrictions, and satisfaction were measured with survey instruments. Participants also reported foot preferences upon conclusion of the study. Differences between feet were assessed with a crossover analysis. While using XF, users experienced improvements in most community-based outcomes, including mobility (p = .001), fatigue (p = .001), balance confidence (p = .005), activity restrictions (p = .002), and functional satisfaction (p < .001). Participants also exhibited longer sound side steps in XF compared to ESF (p < .001). Most participants (89%) reported an overall preference for XF; others (11%) reported no preference. Results indicate that XF may be a promising alternative to ESF for people with transtibial amputation who engage in a range of mobility activities.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02440711.

Reliability and validity of a smartphone-based assessment of gait parameters across walking speed and smartphone locations: Body, bag, belt, hand, and pocket

The assessment of spatiotemporal gait parameters is a useful clinical indicator of health status. Unfortunately, most assessment tools require controlled laboratory environments which can be expensive and time consuming. As smartphones with embedded sensors are becoming ubiquitous, this technology can provide a cost-effective, easily deployable method for assessing gait. Therefore, the purpose of this study was to assess the reliability and validity of a smartphone-based accelerometer in quantifying spatiotemporal gait parameters when attached to the body or in a bag, belt, hand, and pocket. Thirty-four healthy adults were asked to walk at self-selected comfortable, slow, and fast speeds over a 10-m walkway while carrying a smartphone. Step length, step time, gait velocity, and cadence were computed from smartphone-based accelerometers and validated with GAITRite. Across all walking speeds, smartphone data had excellent reliability (ICC_2,1≥0.90) for the body and belt locations, with bag, hand, and pocket locations having good to excellent reliability (ICC_2,1≥0.69). Correlations between the smartphone-based and GAITRite-based systems were very high for the body (r=0.89, 0.98, 0.96, and 0.87 for step length, step time, gait velocity, and cadence, respectively). Similarly, Bland-Altman analysis demonstrated that the bias approached zero, particularly in the body, bag, and belt conditions under comfortable and fast speeds. Thus, smartphone-based assessments of gait are most valid when placed on the body, in a bag, or on a belt. The use of a smartphone to assess gait can provide relevant data to clinicians without encumbering the user and allow for data collection in the free-living environment.

A practical guidance for assessments of sedentary behavior at work: A PEROSH initiative

Sedentary behavior is defined as sitting or lying with low energy expenditure. Humans in industrialized societies spend an increasing amount of time in sedentary behaviors every day. This has been associated with detrimental health outcomes. Despite a growing interest in the health effects of sedentary behavior at work, associations remain unclear, plausibly due to poor and diverse methods for assessing sedentary behavior. Thus, good practice guidance for researchers and practitioners on how to assess occupational sedentary behavior are needed. The aim of this paper is to provide a practical guidance for practitioners and researchers on how to assess occupational sedentary behavior. Ambulatory systems for use in field applications (wearables) are a promising approach for sedentary behavior assessment. Many different small-size consumer wearables, with long battery life and high data storage capacity are commercially available today. However, no stand-alone commercial system is able to assess sedentary behavior in accordance with its definition. The present paper offers decision support for practitioners and researchers in selecting wearables and data collection strategies for their purpose of study on sedentary behavior. Valid and reliable assessment of occupational sedentary behavior is currently not easy. Several aspects need to be considered in the decision process on how to assess sedentary behavior. There is a need for development of a cheap and easily useable wearable for assessment of occupational sedentary behavior by researchers and practitioners.

Measuring Functional Arm Movement after Stroke Using a Single Wrist-Worn Sensor and Machine Learning

BACKGROUND AND PURPOSE

Trials of restorative therapies after stroke and clinical rehabilitation require relevant and objective efficacy end points; real-world upper extremity (UE) functional use is an attractive candidate. We present a novel, inexpensive, and feasible method for separating UE functional use from nonfunctional movement after stroke using a single wrist-worn accelerometer.

METHODS

Ten controls and 10 individuals with stroke performed a series of minimally structured activities while simultaneously being videotaped and wearing a sensor on each wrist that captured the linear acceleration and angular velocity of their UEs. Video data provided ground truth to annotate sensor data as functional or nonfunctional limb use. Using the annotated sensor data, we trained a machine learning tool, a Random Forest model. We then assessed the accuracy of that classification.

RESULTS

In intrasubject test trials, our method correctly classified sensor data with an average of 94.80% in controls and 88.38% in stroke subjects. In leave-one-out intersubject testing and training, correct classification averaged 91.53% for controls and 70.18% in stroke subjects.

CONCLUSIONS

Our method shows promise for inexpensive and objective quantification of functional UE use in hemiparesis, and for assessing the impact of UE treatments. Training a classifier on raw sensor data is feasible, and determination of whether patients functionally use their UE can thus be done remotely. For the restorative treatment trial setting, an intrasubject test/train approach would be especially accurate. This method presents a potentially precise, cost-effective, and objective measurement of UE use outside the clinical or laboratory environment.

Video analysis validation of a real-time physical activity detection algorithm based on a single waist mounted tri-axial accelerometer sensor

We have validated a real-time activity classification algorithm based on monitoring by a body worn system which is potentially suitable for low-power applications on a relatively computationally lightweight processing unit. The algorithm output was validated using annotation data generated from video recordings of 20 elderly volunteers performing both a semi-structured protocol and a free-living protocol. The algorithm correctly identified sitting 75.1% of the time, standing 68.8% of the time, lying 50.9% of the time, and walking and other upright locomotion 82.7% of the time. This is one of the most detailed validations of a body worn sensor algorithm to date and offers an insight into the challenges of developing a real-time physical activity classification algorithm for a tri-axial accelerometer based sensor worn at the waist.

Toward a low-cost gait analysis system for clinical and free-living assessment

Gait is an important clinical assessment tool since changes in gait may reflect changes in general health. Measurement of gait is a complex process which has been restricted to bespoke clinical facilities until recently. The use of inexpensive wearable technologies is an attractive alternative and offers the potential to assess gait in any environment. In this paper we present the development of a low cost analysis gait system built using entirely open source components. The system is used to capture spatio-temporal gait characteristics derived from an existing conceptual model, sensitive to ageing and neurodegenerative pathology (e.g. Parkinson's disease). We demonstrate the system is suitable for use in a clinical unit and will lead to pragmatic use in a free-living (home) environment. The system consists of a wearable (tri-axial accelerometer and gyroscope) with a Raspberry Pi module for data storage and analysis. This forms ongoing work to develop gait as a low cost diagnostic in modern healthcare.