Fall risk assessment in the wild: A critical examination of wearable sensor use in free-living conditions.

BACKGROUND: Despite advances in laboratory-based supervised fall risk assessment methods (FRAs), falls still remain a major public health problem. This can be due to the alteration of behavior in laboratory due to the awareness of being observed (i.e., Hawthorne effect), the multifactorial complex etiology of falls, and our limited understanding of human behaviour in natural environments, or in the' wild'. To address these imitations, a growing body of literature has focused on free-living wearable-sensor-based FRAs. The objective of this narrative literature review is to discuss papers investigating natural data collected by wearable sensors for a duration of at least 24 h to identify fall-prone older adults. METHODS: Databases (Scopus, PubMed and Google Scholar) were searched for studies based on a rigorous search strategy. RESULTS: Twenty-four journal papers were selected, in which inertial sensors were the only wearable system employed for FRA in the wild. Gait was the most-investigated activity; but sitting, standing, lying, transitions and gait events, such as turns and missteps, were also explored. A multitude of free-living fall predictors (FLFPs), e.g., the quantity of daily steps, were extracted from activity bouts and events. FLFPs were further categorized into discrete domains (e.g., pace, complexity) defined by conceptual or data-driven models. Heterogeneity was found within the reviewed studies, which includes variance in: terminology (e.g., quantity vs macro), hyperparameters to define/estimate FLFPs, models and domains, and data processing approaches (e.g., the cut-off thresholds to define an ambulatory bout). These inconsistencies led to different results for similar FLFPs, limiting the ability to interpret and compare the evidence. CONCLUSION: Free-living FRA is a promising avenue for fall prevention. Achieving a harmonized model is necessary to systematically address the inconsistencies in the field and identify FLFPs with the highest predictive values for falls to eventually address intervention programs and fall prevention.

Advancing primary and community care for persons with spinal cord injury: Key findings from a Canadian summit.

Context: Persons with spinal cord injury (SCI) experience significant challenges when they access primary care and community services.Design: A provincial summit was held to direct research, education, and innovation for primary and community care for SCI.Setting: Toronto, Ontario, Canada.Participants: Key stakeholders (N = 95) including persons with SCI and caregivers, clinicians from primary care, rehabilitation, and specialized care, researchers, advocacy groups, and policy makers.Methods: A one-day facilitated meeting that included guest speakers, panel discussions and small group discussions was held to generate potential solutions to current issues related to SCI care and to foster collaborative relationships to advance care for SCI. Perspectives on SCI management were shared by primary care, neurosurgery, rehabilitation, and members of the SCI communityOutcome Measures: Discussions were focused on five domains: knowledge translation and dissemination, application of best practices, communication, research, and patient service accessibility.Results: Summit participants identified issues and prioritized solutions to improve primary and community care including the creation of a network of key stakeholders to enable knowledge creation and dissemination; an online repository of SCI resources, integrated health records, and a clinical network for SCI care; development and implementation of strategies to improve care transitions across sectors; implementation of effective care models and improved access to services; and utilization of empowerment frameworks to support self-management.Conclusions: This summit identified priorities for further collaborative efforts to advance SCI primary and community care and will inform the development of a provincial SCI strategy aimed at improving the system of care for SCI.

Dual-Task Elderly Gait of Prospective Fallers and Non-Fallers: A Wearable-Sensor Based Analysis.

Wearable sensors could facilitate point of care, clinically feasible assessments of dynamic stability and associated fall risk through an assessment of single-task (ST) and dual-task (DT) walking. This study investigated gait changes between ST and DT walking and between older adult prospective fallers and non-fallers. The results were compared to a study based on retrospective fall occurrence. Seventy-five individuals (75.2 ± 6.6 years; 47 non-fallers, 28 fallers; 6 month prospective fall occurrence) walked 7.62 m under ST and DT conditions while wearing pressure-sensing insoles and accelerometers at the head, pelvis, and on both shanks. DT-induced gait changes included changes in temporal measures, centre of pressure (CoP) path stance deviations and coefficient of variation, acceleration descriptive statistics, Fast Fourier Transform (FFT) first quartile, ratio of even to odd harmonics, and maximum Lyapunov exponent. Compared to non-fallers, prospective fallers had significantly lower DT anterior⁻posterior CoP path stance coefficient of variation, DT head anterior⁻posterior FFT first quartile, ST left shank medial⁻lateral FFT first quartile, and ST right shank superior maximum acceleration. DT-induced gait changes were consistent regardless of faller status or when the fall occurred (retrospective or prospective). Gait differences between fallers and non-fallers were dependent on retrospective or prospective faller identification.

Faller Classification in Older Adults Using Wearable Sensors Based on Turn and Straight-Walking Accelerometer-Based Features.

Faller classification in elderly populations can facilitate preventative care before a fall occurs. A novel wearable-sensor based faller classification method for the elderly was developed using accelerometer-based features from straight walking and turns. Seventy-six older individuals (74.15 ± 7.0 years), categorized as prospective fallers and non-fallers, completed a six-minute walk test with accelerometers attached to their lower legs and pelvis. After segmenting straight and turn sections, cross validation tests were conducted on straight and turn walking features to assess classification performance. The best "classifier model-feature selector" combination used turn data, random forest classifier, and select-5-best feature selector (73.4% accuracy, 60.5% sensitivity, 82.0% specificity, and 0.44 Matthew's Correlation Coefficient (MCC)). Using only the most frequently occurring features, a feature subset (minimum of anterior-posterior ratio of even/odd harmonics for right shank, standard deviation (SD) of anterior left shank acceleration SD, SD of mean anterior left shank acceleration, maximum of medial-lateral first quartile of Fourier transform (FQFFT) for lower back, maximum of anterior-posterior FQFFT for lower back) achieved better classification results, with 77.3% accuracy, 66.1% sensitivity, 84.7% specificity, and 0.52 MCC score. All classification performance metrics improved when turn data was used for faller classification, compared to straight walking data. Combining turn and straight walking features decreased performance metrics compared to turn features for similar classifier model-feature selector combinations.

Feature selection for elderly faller classification based on wearable sensors.

BACKGROUND: Wearable sensors can be used to derive numerous gait pattern features for elderly fall risk and faller classification; however, an appropriate feature set is required to avoid high computational costs and the inclusion of irrelevant features. The objectives of this study were to identify and evaluate smaller feature sets for faller classification from large feature sets derived from wearable accelerometer and pressure-sensing insole gait data. METHODS: A convenience sample of 100 older adults (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62 m while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, left and right shanks. Feature selection was performed using correlation-based feature selection (CFS), fast correlation based filter (FCBF), and Relief-F algorithms. Faller classification was performed using multi-layer perceptron neural network, naïve Bayesian, and support vector machine classifiers, with 75:25 single stratified holdout and repeated random sampling. RESULTS: The best performing model was a support vector machine with 78% accuracy, 26% sensitivity, 95% specificity, 0.36 F1 score, and 0.31 MCC and one posterior pelvis accelerometer input feature (left acceleration standard deviation). The second best model achieved better sensitivity (44%) and used a support vector machine with 74% accuracy, 83% specificity, 0.44 F1 score, and 0.29 MCC. This model had ten input features: maximum, mean and standard deviation posterior acceleration; maximum, mean and standard deviation anterior acceleration; mean superior acceleration; and three impulse features. The best multi-sensor model sensitivity (56%) was achieved using posterior pelvis and both shank accelerometers and a naïve Bayesian classifier. The best single-sensor model sensitivity (41%) was achieved using the posterior pelvis accelerometer and a naïve Bayesian classifier. CONCLUSIONS: Feature selection provided models with smaller feature sets and improved faller classification compared to faller classification without feature selection. CFS and FCBF provided the best feature subset (one posterior pelvis accelerometer feature) for faller classification. However, better sensitivity was achieved by the second best model based on a Relief-F feature subset with three pressure-sensing insole features and seven head accelerometer features. Feature selection should be considered as an important step in faller classification using wearable sensors.

Prospective Fall-Risk Prediction Models for Older Adults Based on Wearable Sensors.

Wearable sensors can provide quantitative, gait-based assessments that can translate to point-of-care environments. This investigation generated elderly fall-risk predictive models based on wearable-sensor-derived gait data and prospective fall occurrence, and identified the optimal sensor type, location, and combination for single and dual-task walking. 75 individuals who reported six month prospective fall occurrence (75.2 ± 6.6 years; 47 non-fallers and 28 fallers) walked 7.62 m under single-task and dual-task conditions while wearing pressure-sensinginsoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Fall-risk classificationmodels were assessed for all sensor combinations and three model types: neural network, naïve Bayesian, and support vector machine. The best performing model used a neural network, dual-task gait data, and input parameters from head, pelvis, and left shank accelerometers (accuracy = 57%, sensitivity = 43%, and specificity = 65%). The best single-sensor model used a neural network, dual-task gait data, and pelvis accelerometer parameters (accuracy = 54%, sensitivity = 35%, and specificity = 67%). Single-task and dual-task gait assessments provided similar fall-risk model performance. Fall-risk predictive models developed for point-of-care environments should use multi-sensor dual-task gait assessment with the pelvis location considered if assessment is limited to a single sensor.

Elderly fall risk prediction using static posturography.

Maintaining and controlling postural balance is important for activities of daily living, with poor postural balance being predictive of future falls. This study investigated eyes open and eyes closed standing posturography with elderly adults to identify differences and determine appropriate outcome measure cut-off scores for prospective faller, single-faller, multi-faller, and non-faller classifications. 100 older adults (75.5 ± 6.7 years) stood quietly with eyes open and then eyes closed while Wii Balance Board data were collected. Range in anterior-posterior (AP) and medial-lateral (ML) center of pressure (CoP) motion; AP and ML CoP root mean square distance from mean (RMS); and AP, ML, and vector sum magnitude (VSM) CoP velocity were calculated. Romberg Quotients (RQ) were calculated for all parameters. Participants reported six-month fall history and six-month post-assessment fall occurrence. Groups were retrospective fallers (24), prospective all fallers (42), prospective fallers (22 single, 6 multiple), and prospective non-fallers (47). Non-faller RQ AP range and RQ AP RMS differed from prospective all fallers, fallers, and single fallers. Non-faller eyes closed AP velocity, eyes closed VSM velocity, RQ AP velocity, and RQ VSM velocity differed from multi-fallers. RQ calculations were particularly relevant for elderly fall risk assessments. Cut-off scores from Clinical Cut-off Score, ROC curves, and discriminant functions were clinically viable for multi-faller classification and provided better accuracy than single-faller classification. RQ AP range with cut-off score 1.64 could be used to screen for older people who may fall once. Prospective multi-faller classification with a discriminant function (-1.481 + 0.146 x Eyes Closed AP Velocity-0.114 x Eyes Closed Vector Sum Magnitude Velocity-2.027 x RQ AP Velocity + 2.877 x RQ Vector Sum Magnitude Velocity) and cut-off score 0.541 achieved an accuracy of 84.9% and is viable as a screening tool for older people at risk of multiple falls.

Wearable-Sensor-Based Classification Models of Faller Status in Older Adults.

Wearable sensors have potential for quantitative, gait-based, point-of-care fall risk assessment that can be easily and quickly implemented in clinical-care and older-adult living environments. This investigation generated models for wearable-sensor based fall-risk classification in older adults and identified the optimal sensor type, location, combination, and modelling method; for walking with and without a cognitive load task. A convenience sample of 100 older individuals (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62 m under single-task and dual-task conditions while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Participants also completed the Activities-specific Balance Confidence scale, Community Health Activities Model Program for Seniors questionnaire, six minute walk test, and ranked their fear of falling. Fall risk classification models were assessed for all sensor combinations and three model types: multi-layer perceptron neural network, naïve Bayesian, and support vector machine. The best performing model was a multi-layer perceptron neural network with input parameters from pressure-sensing insoles and head, pelvis, and left shank accelerometers (accuracy = 84%, F1 score = 0.600, MCC score = 0.521). Head sensor-based models had the best performance of the single-sensor models for single-task gait assessment. Single-task gait assessment models outperformed models based on dual-task walking or clinical assessment data. Support vector machines and neural networks were the best modelling technique for fall risk classification. Fall risk classification models developed for point-of-care environments should be developed using support vector machines and neural networks, with a multi-sensor single-task gait assessment.

Analysis of dual-task elderly gait in fallers and non-fallers using wearable sensors.

Dual-task (DT) gait involves walking while simultaneously performing an attention-demanding task and can be used to identify impaired gait or executive function in older adults. Advancment is needed in techniques that quantify the influence of dual tasking to improve predictive and diagnostic potential. This study investigated the viability of wearable sensor measures to identify DT gait changes in older adults and distinguish between elderly fallers and non-fallers. A convenience sample of 100 older individuals (75.5±6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence) walked 7.62m under single-task (ST) and DT conditions while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Differences between ST and DT gait were identified for temporal measures, acceleration descriptive statistics, Fast Fourier Transform (FFT) quartiles, ratio of even to odd harmonics, center of pressure (CoP) stance path coefficient of variation, and deviations to expected CoP stance path. Increased posterior CoP stance path deviations, increased coefficient of variation, decreased FFT quartiles, and decreased ratio of even to odd harmonics suggested increased DT gait variability. Decreased gait velocity and decreased acceleration standard deviations (SD) at the pelvis and shanks could represent compensatory gait strategies that maintain stability. Differences in acceleration between fallers and non-fallers in head posterior SD and pelvis AP ratio of even to odd harmonics during ST, and pelvis vertical maximum Lyapunov exponent during DT gait were identified. Wearable-sensor-based DT gait assessments could be used in point-of-care environments to identify gait deficits.

Understanding responses to gait instability from plantar pressure measurement and the relationship to balance and mobility in lower-limb amputees.

BACKGROUND: Measuring responses to a more unstable walking environment at the point-of-care may reveal clinically relevant strategies, particularly for rehabilitation. This study determined if temporal measures, center of pressure-derived measures, and force impulse measures can quantify responses to surface instability and correlate with clinical balance and mobility measures. METHODS: Thirty-one unilateral amputees, 11 transfemoral and 20 transtibial, walked on level and soft ground while wearing pressure-sensing insoles. Foot-strike and foot-off center of pressure, center of pressure path, temporal, and force impulse variables were derived from F-Scan pressure-sensing insoles. FINDINGS: Significant differences (P<0.05) between level and soft ground were found for temporal and center of pressure path measures. Twenty regression models (R(2) ≤ 0.840), which related plantar-pressure-derived measures with clinical scores, consisted of nine variables. Stride time was in eight models; posterior deviations per stride in six models; mean CoP path velocity in five models; and anterior-posterior center of pressure path coefficient of variation, percent double-support time, and percent stance in four models. INTERPRETATION: Center of pressure-derived parameters, particularly temporal and center of pressure path measures, can differentiate between level and soft ground walking for transfemoral and transtibial amputees. Center of pressure-derived parameters correlated with clinical measures of mobility and balance, explaining up to 84.0% of the variability. The number of posterior deviations per stride, mean CoP path velocity stride time, anterior-posterior center of pressure path coefficient of variation, percent double-support time, and percent stance were frequently related to clinical balance and mobility measures.

Understanding dynamic stability from pelvis accelerometer data and the relationship to balance and mobility in transtibial amputees.

This study investigated whether pelvis acceleration-derived parameters can differentiate between dynamic stability states for transtibial amputees during level (LG) and uneven ground (UG) walking. Correlations between these parameters and clinical balance and mobility measures were also investigated. A convenience sample of eleven individuals with unilateral transtibial amputation walked on LG and simulated UG while pelvis acceleration data were collected at 100Hz. Descriptive statistics, Fast Fourier Transform, ratio of even to odd harmonics, and maximum Lyapunov exponent measures were derived from acceleration data. Of the 26 pelvis acceleration measures, seven had a significant difference (p≤0.05) between LG and UG walking conditions. Seven distinct, stability-relevant measures appeared in at least one of the six regression models that correlated accelerometer-derived measures to Berg Balance Scale (BBS), Community Balance and Mobility Scale (CBMS), and Prosthesis Evaluation Questionnaire (PEQ) scores, explaining up to 100% of the variability in these measures. Of these seven measures, medial-lateral acceleration range was the most frequent model variable, appearing in four models. Anterior-posterior acceleration standard deviation and stride time appeared in three models. Pelvis acceleration-derived parameters were able to differentiate between LG and UG walking for transtibial amputees. UG walking provided the most relevant data for balance and mobility assessment. These results could translate to point of patient contact assessments using a wearable system such as a smartbelt or accelerometer-equipped smartphone.

Analysis of dual-task elderly gait using wearable plantar-pressure insoles and accelerometer.

Dual-task gait allows assessment of impaired executive function and mobility control in older individuals, which are risk factors of falls. This study investigated gait changes in older individuals due to the addition of a cognitive load, using wearable pressure-sensing insole and tri-axial accelerometer measures. These wearable sensors can be applied at the point-of-care. Eleven elderly (65 years or older) individuals walked 7.62 m with and without a verbal fluency cognitive load task while wearing FScan 3000E pressure-sensing insoles in both shoes and a Gulf Coast X16-1C tri-axial accelerometer at the pelvis. Plantar-pressure derived parameters included center of force (CoF) path and temporal measures. Acceleration derived measures were descriptive statistics, Fast Fourier Transform quartile, ratio of even-to-odd harmonics, and maximum Lyapunov exponent. Stride time, stance time, and swing time all significantly increased during dual-task compared to single-task walking. Minimum, mean, and median CoF stance velocity; cadence; and vertical, anterior-posterior, and medial-lateral harmonic ratio all significantly decreased during dual-task walking. Wearable plantar pressure-sensing insole and lower back accelerometer derived-measures can identify gait differences between single-task and dual-task walking in older individuals and could be used in point-of-care environments to assess for deficits in executive function and mobility impairments.

Review of fall risk assessment in geriatric populations using inertial sensors.

BACKGROUND: Falls are a prevalent issue in the geriatric population and can result in damaging physical and psychological consequences. Fall risk assessment can provide information to enable appropriate interventions for those at risk of falling. Wearable inertial-sensor-based systems can provide quantitative measures indicative of fall risk in the geriatric population. METHODS: Forty studies that used inertial sensors to evaluate geriatric fall risk were reviewed and pertinent methodological features were extracted; including, sensor placement, derived parameters used to assess fall risk, fall risk classification method, and fall risk classification model outcomes. RESULTS: Inertial sensors were placed only on the lower back in the majority of papers (65%). One hundred and thirty distinct variables were assessed, which were categorized as position and angle (7.7%), angular velocity (11.5%), linear acceleration (20%), spatial (3.8%), temporal (23.1%), energy (3.8%), frequency (15.4%), and other (14.6%). Fallers were classified using retrospective fall history (30%), prospective fall occurrence (15%), and clinical assessment (32.5%), with 22.5% using a combination of retrospective fall occurrence and clinical assessments. Half of the studies derived models for fall risk prediction, which reached high levels of accuracy (62-100%), specificity (35-100%), and sensitivity (55-99%). CONCLUSIONS: Inertial sensors are promising sensors for fall risk assessment. Future studies should identify fallers using prospective techniques and focus on determining the most promising sensor sites, in conjunction with determination of optimally predictive variables. Further research should also attempt to link predictive variables to specific fall risk factors and investigate disease populations that are at high risk of falls.

Active video game play in children with cerebral palsy: potential for physical activity promotion and rehabilitation therapies.

OBJECTIVE: To evaluate the potential of active video game (AVG) play for physical activity promotion and rehabilitation therapies in children with cerebral palsy (CP) through a quantitative exploration of energy expenditure, muscle activation, and quality of movement. DESIGN: Single-group, experimental study. SETTING: Human movement laboratory in an urban rehabilitation hospital. PARTICIPANTS: Children (N=17; mean age ± SD, 9.43±1.51y) with CP. INTERVENTION: Participants played 4 AVGs (bowling, tennis, boxing, and a dance game). MAIN OUTCOME MEASURES: Energy expenditure via a portable cardiopulmonary testing unit; upper limb muscle activations via single differential surface electrodes; upper limb kinematics via an optical motion capture system; and self-reported enjoyment via the Physical Activity Enjoyment Scale (PACES). RESULTS: Moderate levels of physical activity were achieved during the dance (metabolic equivalent for task [MET]=3.20±1.04) and boxing (MET=3.36±1.50) games. Muscle activations did not exceed maximum voluntary exertions and were greatest for the boxing AVG and for the wrist extensor bundle. Angular velocities and accelerations were significantly larger in the dominant arm than in the hemiplegic arm during bilateral play. A high level of enjoyment was reported on the PACES (4.5±0.3 out of 5). CONCLUSIONS: AVG play via a low-cost, commercially available system can offer an enjoyable opportunity for light to moderate physical activity in children with CP. While all games may encourage motor learning to some extent, AVGs can be strategically selected to address specific therapeutic goals (eg, targeted joints, bilateral limb use). Future research is needed to address the challenge of individual variability in movement patterns/play styles. Likewise, further study exploring home use of AVGs for physical activity promotion and rehabilitation therapies, and its functional outcomes, is warranted.

A Comparison of Solo and Multiplayer Active Videogame Play in Children with Unilateral Cerebral Palsy.

OBJECTIVE: Active videogames (AVGs) have potential in terms of physical activity and therapy for children with cerebral palsy. However, the effect of social interaction on AVG play has not yet been assessed. The objective of this study is to determine if multiplayer AVG versus solo affects levels of energy expenditure and movement patterns. SUBJECTS AND METHODS: Fifteen children (9.77 [standard deviation (SD) 1.78] years old) with hemiplegic cerebral palsy (Gross Motor Function Classification System Level I) participated in solo and multiplayer Nintendo(®) "Wii™ Boxing" (Nintendo, Inc., Redmond, WA) AVG play while energy expenditure and punching frequency were monitored. RESULTS: Moderate levels of physical activity were achieved with no significant differences in energy measures during multiplayer and solo play. Dominant arm punching frequency increased during the multiplayer session from 95.75 (SD 37.93) punches/minute to 107.77 (SD 36.99) punches/minute. Conversely, hemiplegic arm punching frequency decreased from 39.05 (SD 29.57) punches/minutes to 30.73 (SD 24.74) punches/minutes during multiplayer game play. Children enjoyed multiplayer more than solo play. CONCLUSIONS: Opportunities to play AVGs with friends and family may translate to more frequent participation in this moderate physical activity. Conversely, increased hemiplegic limb use during solo play may have therapeutic advantages. As such, new strategies are recommended to promote use of the hemiplegic hand during multiplayer AVG play and to optimize commercial AVG systems for applications in virtual reality therapy.

Wearable wrist activity monitor as an indicator of functional hand use in children with cerebral palsy.

AIM: New tools that capture hand function in everyday activities and contexts are needed for assessing children with hemiplegic cerebral palsy. This study evaluates a wearable wrist monitor and tests the hypothesis that wrist extension frequency (FreqE) is an appropriate indicator of functional hand use. METHOD: Fifteen children (four females, 11 males; age range 6-12y; mean age 10y [SD 2y]) with hemiplegia (seven at level I and eight at level II on the Manual Ability Classification System) participated in the Assisting Hand Assessment (AHA) while wearing the wrist monitor. FreqEs were captured via the wrist monitor and validated using video analysis. Correlations between FreqE and AHA scores were calculated and a multivariate linear regression was conducted to explore other measures of wrist activity. RESULTS: Wrist extensions observed in video analyses were reliably detected by the wrist monitor (intraclass correlation coefficient, r=0.88; p<0.001) and were strongly correlated with the AHA scores (r=0.93; p<0.001). AHA scores were significantly correlated with FreqE (r=0.80; p=0.001) and the range of wrist extensions/flexions (r=0.70; p=0.008). The multivariate linear regression combining the FreqE and range of wrist extensions/flexions yielded a strong correlation with AHA scores (r=0.84; p=0.0043). INTERPRETATION: The wearable wrist monitor may offer a convenient, valid alternative to observer reports for functional assessments of the hemiplegic hand in everyday contexts.