BackgroundWrist-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. ObjectiveThe 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. MethodsParticipants 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. ResultsThe 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. ConclusionsAlgorithms 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 RegistrationISRCTN Registry 12246987; https://www.isrctn.com/ISRCTN12246987 International Registered Report Identifier (IRRID)RR2-10.1136/bmjopen-2021-050785
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.
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.
Abstract Background: Estimation of walking speed from wearable devices requires combining a set of algorithms in a single analytical pipeline. The aim of this study was to validate a pipeline for walking speed estimation and assess its performance across different factors (complexity, speed, and walking bout duration) to make recommendations on the use and validity of wearable devices for real-world mobility analysis. Methods: 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 for 2.5 hours in the real-world, using a wearable device worn on the lower back. Two pipelines for estimating WS were validated across 1298 detected walking bouts, against 1365 walking bouts detected by a multi-sensor reference system. Results: In the laboratory, the mean absolute error (MAE) and mean absolute relative error (MARE) for estimation of walking speed ranged from − 0.06 to 0.04 m/s and 2.1–14.4% respectively, with ICCs ranged between good (0.79) and excellent (0.91). The real-world MAE ranged from − 0.04 to 0.11, and MARE from 1.3–22.7%, where ICCs showed moderate (0.57) to good (0.88) agreement. Errors were lower for cohorts with no major gait impairments, for less complex gait tasks and when considering longer walking bouts. Conclusions: We demonstrated that the analytical pipelines estimated walking speed with good accuracy. Accuracy was dependent upon confounding factors, highlighting the importance of undertaking a robust technical validation of wearable device-derived walking speed before clinical application. Trial registration ISRCTN – 12246987.
Walking/gait speed is a key measure for daily mobility characterization. To date, various studies have attempted to design algorithms to estimate walking speed using an inertial sensor worn on the lower back, which is considered as a proper location for activity monitoring in daily life. However, these algorithms were rarely compared and validated on the same datasets, including people with different preferred walking speed. This study implemented several original, improved, and new algorithms for estimating cadence, step length and eventually speed. We designed comprehensive cross-validation to compare the algorithms for walking slow, normal, fast, and using walking aids. We used two datasets, including reference data for algorithm validation from an instrumented mat (40 subjects) and shanks-worn inertial sensors (88 subjects), with normal and impaired walking patterns. The results showed up to 50% performance improvements. Training of algorithms on data from people with different preferred speeds led to better performance. For the slow walkers, an average RMSE of 2.5 steps/min, 0.04 m, and 0.10 m/s were respectively achieved for cadence, step length, and speed estimation. For normal walkers, the errors were 3.5 steps/min, 0.08 m, and 0.12 m/s. An average RMSE of 1.3 steps/min, 0.05 m, and 0.10 m/s were also observed on fast walkers. For people using walking aids, the error significantly increased up to an RMSE of 14 steps/min, 0.18 m, and 0.27 m/s. The results demonstrated the robustness of the proposed combined speed estimation approach for different speed ranges. It achieved an RMSE of 0.10, 0.18, 0.15, and 0.32 m/s for slow, normal, fast, and using walking aids, respectively.
- In this study an extensive technical review was performed to identify original algorithms for walking speed (WS) estimation using single IMU. Based on the review a conceptual framework was proposed highliting different stages for accurate assesment of WS from separate cadence and step length estimation. Original algorithms and their improved versions were implemented and tested on gait dataset including large range of WS. Time-domain algorithms allowed a better step demarcation while had more error that frequency-domain for cadence estimation. Machine learning provided better results than model based approach but may suffer from overtraining. The results showed high heterogeneity between algorithms and a significant decline in performance for low WS values. Considering the higher risk of disability in slow walkers, there is a need in clinic to improve WS performance. An interesting approach would be weighted average of WS estimated with various algorithms in order to take the best from each algorithms and potentially improve robustness. WS estimation real-world acceleration and angular GF calibration further of stages possibilities for and original algorithms the tested large gait dataset. The results illustrates high heterogeneity and a significant decline in performance for estimating low WS values.
INTRODUCTION:Existing mobility endpoints based on functional performance, physical assessments and patient self-reporting are often affected by lack of sensitivity, limiting their utility in clinical practice. Wearable devices including inertial measurement units (IMUs) can overcome these limitations by quantifying digital mobility outcomes (DMOs) both during supervised structured assessments and in real-world conditions. The validity of IMU-based methods in the real-world, however, is still limited in patient populations. Rigorous validation procedures should cover the device metrological verification, the validation of the algorithms for the DMOs computation specifically for the population of interest and in daily life situations, and the users' perspective on the device.METHODS AND ANALYSIS:This protocol was designed to establish the technical validity and patient acceptability of the approach used to quantify digital mobility in the real world by Mobilise-D, a consortium funded by the European Union (EU) as part of the Innovative Medicine Initiative, aiming at fostering regulatory approval and clinical adoption of DMOs.After defining the procedures for the metrological verification of an IMU-based device, the experimental procedures for the validation of algorithms used to calculate the DMOs are presented. These include laboratory and real-world assessment in 120 participants from five groups: healthy older adults; chronic obstructive pulmonary disease, Parkinson's disease, multiple sclerosis, proximal femoral fracture and congestive heart failure. DMOs extracted from the monitoring device will be compared with those from different reference systems, chosen according to the contexts of observation. Questionnaires and interviews will evaluate the users' perspective on the deployed technology and relevance of the mobility assessment.ETHICS AND DISSEMINATION:The study has been granted ethics approval by the centre's committees (London-Bloomsbury Research Ethics committee; Helsinki Committee, Tel Aviv Sourasky Medical Centre; Medical Faculties of The University of Tübingen and of the University of Kiel). Data and algorithms will be made publicly available.TRIAL REGISTRATION NUMBER:ISRCTN (12246987).
Walking speed (WS) is recognized as an important dimension of functional health and a candidate endpoint for clinical trials. To be adopted as a powerful outcome measure in clinical assessment, WS should be estimated pervasively and accurately in the real-life context. Although current state of the art points to possible solutions, e.g., by using pairing of wearable sensors with dedicated algorithms, the accuracy and robustness of existing algorithms in challenging situations should be carefully considered. This study highlights the main methodological issues for WS estimation using single inertial sensor fixed on trunk (chest/low back) and data recorded in a sample of stroke patients with impaired mobility.