A multi-sensor wearable system for the assessment of diseased gait in real-world conditions

Real-World Gait Detection Using a Wrist-Worn Inertial Sensor: Validation Study

BACKGROUND

Wrist-worn inertial sensors are used in digital health for evaluating mobility in real-world environments. Preceding the estimation of spatiotemporal gait parameters within long-term recordings, gait detection is an important step to identify regions of interest where gait occurs, which requires robust algorithms due to the complexity of arm movements. While algorithms exist for other sensor positions, a comparative validation of algorithms applied to the wrist position on real-world data sets across different disease populations is missing. Furthermore, gait detection performance differences between the wrist and lower back position have not yet been explored but could yield valuable information regarding sensor position choice in clinical studies.

OBJECTIVE

The aim of this study was to validate gait sequence (GS) detection algorithms developed for the wrist position against reference data acquired in a real-world context. In addition, this study aimed to compare the performance of algorithms applied to the wrist position to those applied to lower back-worn inertial sensors.

METHODS

Participants with Parkinson disease, multiple sclerosis, proximal femoral fracture (hip fracture recovery), chronic obstructive pulmonary disease, and congestive heart failure and healthy older adults (N=83) were monitored for 2.5 hours in the real-world using inertial sensors on the wrist, lower back, and feet including pressure insoles and infrared distance sensors as reference. In total, 10 algorithms for wrist-based gait detection were validated against a multisensor reference system and compared to gait detection performance using lower back-worn inertial sensors.

RESULTS

The best-performing GS detection algorithm for the wrist showed a mean (per disease group) sensitivity ranging between 0.55 (SD 0.29) and 0.81 (SD 0.09) and a mean (per disease group) specificity ranging between 0.95 (SD 0.06) and 0.98 (SD 0.02). The mean relative absolute error of estimated walking time ranged between 8.9% (SD 7.1%) and 32.7% (SD 19.2%) per disease group for this algorithm as compared to the reference system. Gait detection performance from the best algorithm applied to the wrist inertial sensors was lower than for the best algorithms applied to the lower back, which yielded mean sensitivity between 0.71 (SD 0.12) and 0.91 (SD 0.04), mean specificity between 0.96 (SD 0.03) and 0.99 (SD 0.01), and a mean relative absolute error of estimated walking time between 6.3% (SD 5.4%) and 23.5% (SD 13%). Performance was lower in disease groups with major gait impairments (eg, patients recovering from hip fracture) and for patients using bilateral walking aids.

CONCLUSIONS

Algorithms applied to the wrist position can detect GSs with high performance in real-world environments. Those periods of interest in real-world recordings can facilitate gait parameter extraction and allow the quantification of gait duration distribution in everyday life. Our findings allow taking informed decisions on alternative positions for gait recording in clinical studies and public health.

TRIAL REGISTRATION

ISRCTN Registry 12246987; https://www.isrctn.com/ISRCTN12246987.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.1136/bmjopen-2021-050785.

Accuracy, concurrent validity, and test-retest reliability of pressure-based insoles for gait measurement in chronic stroke patients

Introduction

Wearables are potentially valuable tools for understanding mobility behavior in individuals with neurological disorders and how it changes depending on health status, such as after rehabilitation. However, the accurate detection of gait events, which are crucial for the evaluation of gait performance and quality, is challenging due to highly individual-specific patterns that also vary greatly in movement and speed, especially after stroke. Therefore, the purpose of this study was to assess the accuracy, concurrent validity, and test-retest reliability of a commercially available insole system in the detection of gait events and the calculation of stance duration in individuals with chronic stroke.

Methods

Pressure insole data were collected from 17 individuals with chronic stroke during two measurement blocks, each comprising three 10-min walking tests conducted in a clinical setting. The gait assessments were recorded with a video camera that served as a ground truth, and pressure insoles as an experimental system. We compared the number of gait events and stance durations between systems.

Results and discussion

Over all 3,820 gait events, 90.86% were correctly identified by the insole system. Recall values ranged from 0.994 to 1, with a precision of 1 for all measurements. The F1 score ranged from 0.997 to 1. Excellent absolute agreement (Intraclass correlation coefficient, ICC = 0.874) was observed for the calculation of the stance duration, with a slightly longer stance duration recorded by the insole system (difference of -0.01 s). Bland-Altmann analysis indicated limits of agreement of 0.33 s that were robust to changes in walking speed. This consistency makes the system well-suited for individuals post-stroke. The test-retest reliability between measurement timepoints T1 and T2 was excellent (ICC = 0.928). The mean difference in stance duration between T1 and T2 was 0.03 s. We conclude that the insole system is valid for use in a clinical setting to quantitatively assess continuous walking in individuals with stroke.

Automated Gait Detection in Older Adults during Daily-Living using Self-Supervised Learning of Wrist-Worn Accelerometer Data: Development and Validation of ElderNet

Progressive gait impairment is common in aging adults. Remote phenotyping of gait during daily living has the potential to quantify gait alterations and evaluate the effects of interventions that may prevent disability in the aging population. Here, we developed ElderNet, a self-supervised learning model for gait detection from wrist-worn accelerometer data. Validation involved two diverse cohorts, including over 1,000 participants without gait labels, as well as 83 participants with labeled data: older adults with Parkinson's disease, proximal femoral fracture, chronic obstructive pulmonary disease, congestive heart failure, and healthy adults. ElderNet presented high accuracy (96.43 ± 2.27), specificity (98.87 ± 2.15), recall (82.32 ± 11.37), precision (86.69 ± 17.61), and F1 score (82.92 ± 13.39). The suggested method yielded superior performance compared to two state-of-the-art gait detection algorithms, with improved accuracy and F1 score (p < 0.05). In an initial evaluation of construct validity, ElderNet identified differences in estimated daily walking durations across cohorts with different clinical characteristics, such as mobility disability (p < 0.001) and parkinsonism (p < 0.001). The proposed self-supervised gait detection method has the potential to serve as a valuable tool for remote phenotyping of gait function during daily living in aging adults.

Real-world walking cadence in people with COPD

Introduction

The clinical validity of real-world walking cadence in people with COPD is unsettled. Our objective was to assess the levels, variability and association with clinically relevant COPD characteristics and outcomes of real-world walking cadence.

Methods

We assessed walking cadence (steps per minute during walking bouts longer than 10 s) from 7 days' accelerometer data in 593 individuals with COPD from five European countries, and clinical and functional characteristics from validated questionnaires and standardised tests. Severe exacerbations during a 12-month follow-up were recorded from patient reports and medical registries.

Results

Participants were mostly male (80%) and had mean±sd age of 68±8 years, post-bronchodilator forced expiratory volume in 1 s (FEV1) of 57±19% predicted and walked 6880±3926 steps·day-1. Mean walking cadence was 88±9 steps·min-1, followed a normal distribution and was highly stable within-person (intraclass correlation coefficient 0.92, 95% CI 0.90-0.93). After adjusting for age, sex, height and number of walking bouts in fractional polynomial or linear regressions, walking cadence was positively associated with FEV1, 6-min walk distance, physical activity (steps·day-1, time in moderate-to-vigorous physical activity, vector magnitude units, walking time, intensity during locomotion), physical activity experience and health-related quality of life and negatively associated with breathlessness and depression (all p<0.05). These associations remained after further adjustment for daily steps. In negative binomial regression adjusted for multiple confounders, walking cadence related to lower number of severe exacerbations during follow-up (incidence rate ratio 0.94 per step·min-1, 95% CI 0.91-0.99, p=0.009).

Conclusions

Higher real-world walking cadence is associated with better COPD status and lower severe exacerbations risk, which makes it attractive as a future prognostic marker and clinical outcome.

Identifying Subtle Motor Deficits Before Parkinson's Disease is Diagnosed: What to Look for?

Motor deficits typical of Parkinson's disease (PD), such as gait and balance disturbances, tremor, reduced arm swing and finger movement, and voice and breathing changes, are believed to manifest several years prior to clinical diagnosis. Here we describe the evidence for the presence and progression of motor deficits in this pre-diagnostic phase in order to provide suggestions for the design of future observational studies for an effective, quantitatively oriented investigation. On the one hand, these future studies must detect these motor deficits in as large (potentially, population-based) cohorts as possible with high sensitivity and specificity. On the other hand, they must describe the progression of these motor deficits in the pre-diagnostic phase as accurately as possible, to support the testing of the effect of pharmacological and non-pharmacological interventions. Digital technologies and artificial intelligence can substantially accelerate this process.

Mobilise-D insights to estimate real-world walking speed in multiple conditions with a wearable device

This study aimed to validate a wearable device's walking speed estimation pipeline, considering complexity, speed, and walking bout duration. The goal was to provide recommendations on the use of wearable devices for real-world mobility analysis. Participants with Parkinson's Disease, Multiple Sclerosis, Proximal Femoral Fracture, Chronic Obstructive Pulmonary Disease, Congestive Heart Failure, and healthy older adults (n = 97) were monitored in the laboratory and the real-world (2.5 h), using a lower back wearable device. Two walking speed estimation pipelines were validated across 4408/1298 (2.5 h/laboratory) detected walking bouts, compared to 4620/1365 bouts detected by a multi-sensor reference system. In the laboratory, the mean absolute error (MAE) and mean relative error (MRE) for walking speed estimation ranged from 0.06 to 0.12 m/s and - 2.1 to 14.4%, with ICCs (Intraclass correlation coefficients) between good (0.79) and excellent (0.91). Real-world MAE ranged from 0.09 to 0.13, MARE from 1.3 to 22.7%, with ICCs indicating moderate (0.57) to good (0.88) agreement. Lower errors were observed for cohorts without major gait impairments, less complex tasks, and longer walking bouts. The analytical pipelines demonstrated moderate to good accuracy in estimating walking speed. Accuracy depended on confounding factors, emphasizing the need for robust technical validation before clinical application.Trial registration: ISRCTN - 12246987.

Toward Personalized Orthopedic Care: Validation of a Smart Knee Brace

Introduction

Wearable technology offers a promising solution to advance current rehabilitation strategies for post-operative orthopedic care. The aim of this study was to determine the level of agreement and concurrent validity of a smart knee brace compared to the gold standard measurement system GAITRite® for assessing lower limb gait parameters.

Methods

Thirty-four healthy participants were fitted with the smart knee brace (Digital Knee®) on their dominant limb. Gait parameters (stride length, stride time, and gait velocity) were measured simultaneously using the Digital Knee® and the GAITRite® electronic walkway. Two walks were performed at a comfortable speed and two at a fast-walking speed.

Results

At a comfortable walking speed, stride time was moderately valid (ICC2,1 = 0.66 s), and stride length and gait velocity demonstrated poor validity (ICC2,1 = 0.29; ICC2,1 = 0.41). All gait parameters demonstrated poor validity at a fast-walking speed (ICC2,1 = -0.16 to -0.01). Bias ranged from -0.08 to 0.28, with more clinically acceptable percentage errors at a comfortable walking speed (14.1-30%) versus at a fast-walking speed (26.4-42.6%). Gait velocity and stride length had substantially higher biases in the fast-walking speed compared to the comfortable walking speed (0.28 ± 0.39 m s-1 vs. 0.02 ± 0.21 m s-1; 0.15 ± 0.23 m vs. -0.04 ± 0.17 m). Limits of agreement were considered narrower for stride time compared to stride length and gait velocity.

Conclusion

The Digital Knee® is a promising approach to improving post-operative rehabilitation outcomes in patients with osteoarthritis. The Digital Knee® demonstrated good agreement and moderate concurrent validity for measuring gait metrics at a comfortable walking speed. These findings highlight the opportunity of the wearable sensor as an intervention for post-operative orthopedic care. This was a laboratory-based study; thus, further research is required to validate the wearable sensor in real-world contexts and in patients with knee pathologies. Further, refinement of the algorithm for measuring gait metrics at slow- and fast-walking speed with the Digital Knee® is warranted.

Validation of algorithms for calculating spatiotemporal gait parameters during continuous turning using lumbar and foot mounted inertial measurement units

Spatiotemporal gait parameters such as step time and walking speed can be used to quantify gait performance and determine physical function. Inertial measurement units (IMUs) allow for the measurement of spatiotemporal gait parameters in unconstrained environments but must be validated against a gold standard. While many IMU systems and algorithms have been validated during treadmill walking and overground walking in a straight line, fewer studies have validated algorithms during more complex walking conditions such as continuous turning in different directions. This study explored the concurrent validity in a population of healthy adults (range 26-52 years) of three different algorithms using lumbar and foot mounted IMUs to calculate spatiotemporal gait parameters: two methods utilizing an inverted pendulum model, and one method based on strapdown integration. IMU data was compared to a Vicon twelve-camera optoelectronic system, using data collected from 9 participants performing straight walking and continuous walking trials at different speeds, resulting in 162 walking trials in total. Intraclass correlation coefficients (ICCA,1) for absolute agreement were calculated between the algorithm outputs and Vicon output. Temporal parameters were comparable in all methods and ranged from moderate to excellent, except double support time which was poor. Strapdown integration performed better for estimating spatial parameters than pendulum models during straight walking, but worse during turning. Selecting the most appropriate model should take into consideration both speed and walking condition.

Ecological validity of a deep learning algorithm to detect gait events from real-life walking bouts in mobility-limiting diseases

Introduction

The clinical assessment of mobility, and walking specifically, is still mainly based on functional tests that lack ecological validity. Thanks to inertial measurement units (IMUs), gait analysis is shifting to unsupervised monitoring in naturalistic and unconstrained settings. However, the extraction of clinically relevant gait parameters from IMU data often depends on heuristics-based algorithms that rely on empirically determined thresholds. These were mainly validated on small cohorts in supervised settings.

Methods

Here, a deep learning (DL) algorithm was developed and validated for gait event detection in a heterogeneous population of different mobility-limiting disease cohorts and a cohort of healthy adults. Participants wore pressure insoles and IMUs on both feet for 2.5 h in their habitual environment. The raw accelerometer and gyroscope data from both feet were used as input to a deep convolutional neural network, while reference timings for gait events were based on the combined IMU and pressure insoles data.

Results and discussion

The results showed a high-detection performance for initial contacts (ICs) (recall: 98%, precision: 96%) and final contacts (FCs) (recall: 99%, precision: 94%) and a maximum median time error of -0.02 s for ICs and 0.03 s for FCs. Subsequently derived temporal gait parameters were in good agreement with a pressure insoles-based reference with a maximum mean difference of 0.07, -0.07, and <0.01 s for stance, swing, and stride time, respectively. Thus, the DL algorithm is considered successful in detecting gait events in ecologically valid environments across different mobility-limiting diseases.

Laboratory and free-living gait performance in adults with COPD and healthy controls

Background

Gait characteristics are important risk factors for falls, hospitalisations and mortality in older adults, but the impact of COPD on gait performance remains unclear. We aimed to identify differences in gait characteristics between adults with COPD and healthy age-matched controls during 1) laboratory tests that included complex movements and obstacles, 2) simulated daily-life activities (supervised) and 3) free-living daily-life activities (unsupervised).

Methods

This case-control study used a multi-sensor wearable system (INDIP) to obtain seven gait characteristics for each walking bout performed by adults with mild-to-severe COPD (n=17; forced expiratory volume in 1 s 57±19% predicted) and controls (n=20) during laboratory tests, and during simulated and free-living daily-life activities. Gait characteristics were compared between adults with COPD and healthy controls for all walking bouts combined, and for shorter (≤30 s) and longer (>30 s) walking bouts separately.

Results

Slower walking speed (-11 cm·s-1, 95% CI: -20 to -3) and lower cadence (-6.6 steps·min-1, 95% CI: -12.3 to -0.9) were recorded in adults with COPD compared to healthy controls during longer (>30 s) free-living walking bouts, but not during shorter (≤30 s) walking bouts in either laboratory or free-living settings. Double support duration and gait variability measures were generally comparable between the two groups.

Conclusion

Gait impairment of adults with mild-to-severe COPD mainly manifests during relatively long walking bouts (>30 s) in free-living conditions. Future research should determine the underlying mechanism(s) of this impairment to facilitate the development of interventions that can improve free-living gait performance in adults with COPD.

A Single-Sensor Approach to Quantify Gait in Patients with Hereditary Spastic Paraplegia

Hereditary spastic paraplegia (HSP) is characterised by progressive lower-limb spasticity and weakness resulting in ambulation difficulties. During clinical practice, walking is observed and/or assessed by timed 10-metre walk tests; time, feasibility, and methodological reliability are barriers to detailed characterisation of patients' walking abilities when instrumenting this test. Wearable sensors have the potential to overcome such drawbacks once a validated approach is available for patients with HSP. Therefore, while limiting patients' and assessors' burdens, this study aims to validate the adoption of a single lower-back wearable inertial sensor approach for step detection in HSP patients; this is the first essential algorithmic step in quantifying most gait temporal metrics. After filtering the 3D acceleration signal based on its smoothness and enhancing the step-related peaks, initial contacts (ICs) were identified as positive zero-crossings of the processed signal. The proposed approach was validated on thirteen individuals with HSP while they performed three 10-metre tests and wore pressure insoles used as a gold standard. Overall, the single-sensor approach detected 794 ICs (87% correctly identified) with high accuracy (median absolute errors (mae): 0.05 s) and excellent reliability (ICC = 1.00). Although about 12% of the ICs were missed and the use of walking aids introduced extra ICs, a minor impact was observed on the step time quantifications (mae 0.03 s (5.1%), ICC = 0.89); the use of walking aids caused no significant differences in the average step time quantifications. Therefore, the proposed single-sensor approach provides a reliable methodology for step identification in HSP, augmenting the gait information that can be accurately and objectively extracted from patients with HSP during their clinical assessment.

A Light-Weight Artificial Neural Network for Recognition of Activities of Daily Living

Human activity recognition (HAR) is essential for the development of robots to assist humans in daily activities. HAR is required to be accurate, fast and suitable for low-cost wearable devices to ensure portable and safe assistance. Current computational methods can achieve accurate recognition results but tend to be computationally expensive, making them unsuitable for the development of wearable robots in terms of speed and processing power. This paper proposes a light-weight architecture for recognition of activities using five inertial measurement units and four goniometers attached to the lower limb. First, a systematic extraction of time-domain features from wearable sensor data is performed. Second, a small high-speed artificial neural network and line search method for cost function optimization are used for activity recognition. The proposed method is systematically validated using a large dataset composed of wearable sensor data from seven activities (sitting, standing, walking, stair ascent/descent, ramp ascent/descent) associated with eight healthy subjects. The accuracy and speed results are compared against methods commonly used for activity recognition including deep neural networks, convolutional neural networks, long short-term memory and convolutional-long short-term memory hybrid networks. The experiments demonstrate that the light-weight architecture can achieve a high recognition accuracy of 98.60%, 93.10% and 84.77% for seen data from seen subjects, unseen data from seen subjects and unseen data from unseen subjects, respectively, and an inference time of 85 μs. The results show that the proposed approach can perform accurate and fast activity recognition with a reduced computational complexity suitable for the development of portable assistive devices.

Assessing real-world gait with digital technology? Validation, insights and recommendations from the Mobilise-D consortium

BACKGROUND

Although digital mobility outcomes (DMOs) can be readily calculated from real-world data collected with wearable devices and ad-hoc algorithms, technical validation is still required. The aim of this paper is to comparatively assess and validate DMOs estimated using real-world gait data from six different cohorts, focusing on gait sequence detection, foot initial contact detection (ICD), cadence (CAD) and stride length (SL) estimates.

METHODS

Twenty healthy older adults, 20 people with Parkinson's disease, 20 with multiple sclerosis, 19 with proximal femoral fracture, 17 with chronic obstructive pulmonary disease and 12 with congestive heart failure were monitored for 2.5 h in the real-world, using a single wearable device worn on the lower back. A reference system combining inertial modules with distance sensors and pressure insoles was used for comparison of DMOs from the single wearable device. We assessed and validated three algorithms for gait sequence detection, four for ICD, three for CAD and four for SL by concurrently comparing their performances (e.g., accuracy, specificity, sensitivity, absolute and relative errors). Additionally, the effects of walking bout (WB) speed and duration on algorithm performance were investigated.

RESULTS

We identified two cohort-specific top performing algorithms for gait sequence detection and CAD, and a single best for ICD and SL. Best gait sequence detection algorithms showed good performances (sensitivity > 0.73, positive predictive values > 0.75, specificity > 0.95, accuracy > 0.94). ICD and CAD algorithms presented excellent results, with sensitivity > 0.79, positive predictive values > 0.89 and relative errors < 11% for ICD and < 8.5% for CAD. The best identified SL algorithm showed lower performances than other DMOs (absolute error < 0.21 m). Lower performances across all DMOs were found for the cohort with most severe gait impairments (proximal femoral fracture). Algorithms' performances were lower for short walking bouts; slower gait speeds (< 0.5 m/s) resulted in reduced performance of the CAD and SL algorithms.

CONCLUSIONS

Overall, the identified algorithms enabled a robust estimation of key DMOs. Our findings showed that the choice of algorithm for estimation of gait sequence detection and CAD should be cohort-specific (e.g., slow walkers and with gait impairments). Short walking bout length and slow walking speed worsened algorithms' performances. Trial registration ISRCTN - 12246987.