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.

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.

A study protocol to investigate if acipimox improves muscle function and sarcopenia: an open-label, uncontrolled, before-and-after experimental medicine feasibility study in community-dwelling older adults

INTRODUCTION

Sarcopenia is the age-associated loss of muscle mass and strength. Nicotinamide adenine dinucleotide (NAD) plays a central role in both mitochondrial function and cellular ageing processes implicated in sarcopenia. NAD concentrations are low in older people with sarcopenia, and increasing skeletal muscle NAD concentrations may offer a novel therapy for this condition. Acipimox is a licensed lipid-lowering agent known to act as an NAD precursor. This open-label, uncontrolled, before-and-after proof-of-concept experimental medicine study will test whether daily supplementation with acipimox improves skeletal muscle NAD concentrations.

METHODS AND ANALYSIS

Sixteen participants aged 65 and over with probable sarcopenia will receive acipimox 250 mg and aspirin 75 mg orally daily for 4 weeks, with the frequency of acipimox administration being dependent on renal function. Muscle biopsy of the vastus lateralis and MRI scanning of the lower leg will be performed at baseline before starting acipimox and after 3 weeks of treatment. Adverse events will be recorded for the duration of the trial. The primary outcome, analysed in a per-protocol population, is the change in skeletal muscle NAD concentration between baseline and follow-up. Secondary outcomes include changes in phosphocreatine recovery rate by 31P magnetic resonance spectroscopy, changes in physical performance and daily activity (handgrip strength, 4 m walk and 7-day accelerometry), changes in skeletal muscle mitochondrial respiratory function, changes in skeletal muscle mitochondrial DNA copy number and changes in NAD concentrations in whole blood as a putative biomarker for future participant selection.

ETHICS AND DISSEMINATION

The trial is approved by the UK Medicines and Healthcare Products Regulatory Agency (EuDRACT 2021-000993-28) and UK Health Research Authority and Northeast - Tyne and Wear South Research Ethics Committee (IRAS 293565). Results will be made available to participants, their families, patients with sarcopenia, the public, regional and national clinical teams, and the international scientific community.

PROTOCOL

Acipimox feasibility study Clinical Trial Protocol V.2 2/11/21.

TRIAL REGISTRATION NUMBER

The ISRCTN trial database (ISRCTN87404878).

Digital Mobility Measures: A Window into Real-World Severity and Progression of Parkinson's Disease

BACKGROUND

Real-world monitoring using wearable sensors has enormous potential for assessing disease severity and symptoms among persons with Parkinson's disease (PD). Many distinct features can be extracted, reflecting multiple mobility domains. However, it is unclear which digital measures are related to PD severity and are sensitive to disease progression.

OBJECTIVES

The aim was to identify real-world mobility measures that reflect PD severity and show discriminant ability and sensitivity to disease progression, compared to the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) scale.

METHODS

Multicenter real-world continuous (24/7) digital mobility data from 587 persons with PD and 68 matched healthy controls were collected using an accelerometer adhered to the lower back. Machine learning feature selection and regression algorithms evaluated associations of the digital measures using the MDS-UPDRS (I-III). Binary logistic regression assessed discriminatory value using controls, and longitudinal observational data from a subgroup (n = 33) evaluated sensitivity to change over time.

RESULTS

Digital measures were only moderately correlated with the MDS-UPDRS (part II-r = 0.60 and parts I and III-r = 0.50). Most associated measures reflected activity quantity and distribution patterns. A model with 14 digital measures accurately distinguished recently diagnosed persons with PD from healthy controls (81.1%, area under the curve: 0.87); digital measures showed larger effect sizes (Cohen's d: [0.19-0.66]), for change over time than any of the MDS-UPDRS parts (Cohen's d: [0.04-0.12]).

CONCLUSIONS

Real-world mobility measures are moderately associated with clinical assessments, suggesting that they capture different aspects of motor capacity and function. Digital mobility measures are sensitive to early-stage disease and to disease progression, to a larger degree than conventional clinical assessments, demonstrating their utility, primarily for clinical trials but ultimately also for clinical care. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Effects of an Exercise Program to Reduce Falls in Older People Living in Long-Term Care: A Randomized Controlled Trial

OBJECTIVES

To investigate the effect of an exercise program on falls in intermediate and high-level long-term care (LTC) residents and to determine whether adherence, physical capacity, and cognition modified outcomes.

DESIGN

Randomized controlled trial.

SETTING AND PARTICIPANTS

Residents (n = 520, aged 84 ± 8 years) from 25 LTC facilities in New Zealand.

METHODS

Individually randomized to Staying UpRight, a physical therapist-led, balance and strength group exercise program delivered for 1 hour, twice weekly over 12 months. The control arm was dose-matched and used seated activities with no resistance. Falls were collected using routinely collected incident reports.

RESULTS

Baseline fall rates were 4.1 and 3.3 falls per person-year (ppy) for intervention and control groups. Fall rates over the trial period were 4.1 and 4.3 falls ppy respectively [P = .89, incidence rate ratio (IRR) 0.98, 95% CI 0.76, 1.27]. Over the 12-month trial period, 74% fell, with 63% of intervention and 61% of the control group falling more than once. Risk of falls (P = .56, hazard ratio 1.08, 95% CI 0.85, 1.36) and repeat falling or fallers sustaining an injury at trial completion were similar between groups. Fall rates per 100 hours walked did not differ between groups (P = .42, IRR 1.15, 95% CI 0.81, 1.63). Program delivery was suspended several times because of COVID-19, reducing average attendance to 26 hours over 12 months. Subgroup analyses of falls outcomes for those with the highest attendance (≥50% of classes), better physical capacity (Short Physical Performance Battery scores ≥8/12), or cognition (Montreal Cognitive Assessment scores ≥ 18/30) showed no significant impact of the program.

CONCLUSIONS/IMPLICATIONS

In intermediate and high-level care residents, the Staying UpRight program did not reduce fall rates or risk compared with a control activity, independent of age, sex, or care level. Inadequate exercise dose because of COVID-19-related interruptions to intervention delivery likely contributed to the null result.

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.

Pose-based tremor type and level analysis for Parkinson's disease from video

PURPOSE

Current methods for diagnosis of PD rely on clinical examination. The accuracy of diagnosis ranges between 73 and 84%, and is influenced by the experience of the clinical assessor. Hence, an automatic, effective and interpretable supporting system for PD symptom identification would support clinicians in making more robust PD diagnostic decisions.

METHODS

We propose to analyze Parkinson's tremor (PT) to support the analysis of PD, since PT is one of the most typical symptoms of PD with broad generalizability. To realize the idea, we present SPA-PTA, a deep learning-based PT classification and severity estimation system that takes consumer-grade videos of front-facing humans as input. The core of the system is a novel attention module with a lightweight pyramidal channel-squeezing-fusion architecture that effectively extracts relevant PT information and filters noise. It enhances modeling performance while improving system interpretability.

RESULTS

We validate our system via individual-based leave-one-out cross-validation on two tasks: the PT classification task and the tremor severity rating estimation task. Our system presents a 91.3% accuracy and 80.0% F1-score in classifying PT with non-PT class, while providing a 76.4% accuracy and 76.7% F1-score in more complex multiclass tremor rating classification task.

CONCLUSION

Our system offers a cost-effective PT classification and tremor severity estimation results as warning signs of PD for undiagnosed patients with PT symptoms. In addition, it provides a potential solution for supporting PD diagnosis in regions with limited clinical resources.

Walking Bout Detection for People Living in Long Residential Care: A Computationally Efficient Algorithm for a 3-Axis Accelerometer on the Lower Back

Accurate and reliable measurement of real-world walking activity is clinically relevant, particularly for people with mobility difficulties. Insights on walking can help understand mobility function, disease progression, and fall risks. People living in long-term residential care environments have heterogeneous and often pathological walking patterns, making it difficult for conventional algorithms paired with wearable sensors to detect their walking activity. We designed two walking bout detection algorithms for people living in long-term residential care. Both algorithms used thresholds on the magnitude of acceleration from a 3-axis accelerometer on the lower back to classify data as "walking" or "non-walking". One algorithm had generic thresholds, whereas the other used personalized thresholds. To validate and evaluate the algorithms, we compared the classifications of walking/non-walking from our algorithms to the real-time research assistant annotated labels and the classification output from an algorithm validated on a healthy population. Both the generic and personalized algorithms had acceptable accuracy (0.83 and 0.82, respectively). The personalized algorithm showed the highest specificity (0.84) of all tested algorithms, meaning it was the best suited to determine input data for gait characteristic extraction. The developed algorithms were almost 60% quicker than the previously developed algorithms, suggesting they are adaptable for real-time processing.

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.

Translating digital healthcare to enhance clinical management: a protocol for an observational study using a digital health technology system to monitor medication adherence and its effect on mobility in people with Parkinson's

INTRODUCTION

In people with Parkinson's (PwP) impaired mobility is associated with an increased falls risk. To improve mobility, dopaminergic medication is typically prescribed, but complex medication regimens result in suboptimal adherence. Exploring medication adherence and its impact on mobility in PwP will provide essential insights to optimise medication regimens and improve mobility. However, this is typically assessed in controlled environments, during one-off clinical assessments. Digital health technology (DHT) presents a means to overcome this, by continuously and remotely monitoring mobility and medication adherence. This study aims to use a novel DHT system (DHTS) (comprising of a smartphone, smartwatch and inertial measurement unit (IMU)) to assess self-reported medication adherence, and its impact on digital mobility outcomes (DMOs) in PwP.

METHODS AND ANALYSIS

This single-centre, UK-based study, will recruit 55 participants with Parkinson's. Participants will complete a range of clinical, and physical assessments. Participants will interact with a DHTS over 7 days, to assess self-reported medication adherence, and monitor mobility and contextual factors in the real world. Participants will complete a motor complications diary (ON-OFF-Dyskinesia) throughout the monitoring period and, at the end, a questionnaire and series of open-text questions to evaluate DHTS usability. Feasibility of the DHTS and the motor complications diary will be assessed. Validated algorithms will quantify DMOs from IMU walking activity. Time series modelling and deep learning techniques will model and predict DMO response to medication and effects of contextual factors. This study will provide essential insights into medication adherence and its effect on real-world mobility in PwP, providing insights to optimise medication regimens.

ETHICS AND DISSEMINATION

Ethical approval was granted by London-142 Westminster Research Ethics Committee (REC: 21/PR/0469), protocol V.2.4. Results will be published in peer-reviewed journals. All participants will provide written, informed consent.

TRIAL REGISTRATION NUMBER

ISRCTN13156149.

Physical Activity in Community-Dwelling Older Adults: Which Real-World Accelerometry Measures Are Robust? A Systematic Review

Measurement of real-world physical activity (PA) data using accelerometry in older adults is informative and clinically relevant, but not without challenges. This review appraises the reliability and validity of accelerometry-based PA measures of older adults collected in real-world conditions. Eight electronic databases were systematically searched, with 13 manuscripts included. Intraclass correlation coefficient (ICC) for inter-rater reliability were: walking duration (0.94 to 0.95), lying duration (0.98 to 0.99), sitting duration (0.78 to 0.99) and standing duration (0.98 to 0.99). ICCs for relative reliability ranged from 0.24 to 0.82 for step counts and 0.48 to 0.86 for active calories. Absolute reliability ranged from 5864 to 10,832 steps and for active calories from 289 to 597 kcal. ICCs for responsiveness for step count were 0.02 to 0.41, and for active calories 0.07 to 0.93. Criterion validity for step count ranged from 0.83 to 0.98. Percentage of agreement for walking ranged from 63.6% to 94.5%; for lying 35.6% to 100%, sitting 79.2% to 100%, and standing 38.6% to 96.1%. Construct validity between step count and criteria for moderate-to-vigorous PA was rs = 0.68 and 0.72. Inter-rater reliability and criterion validity for walking, lying, sitting and standing duration are established. Criterion validity of step count is also established. Clinicians and researchers may use these measures with a limited degree of confidence. Further work is required to establish these properties and to extend the repertoire of PA measures beyond "volume" counts to include more nuanced outcomes such as intensity of movement and duration of postural transitions.

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 robust walking detection algorithm using a single foot-worn inertial sensor: validation in real-life settings

Walking activity and gait parameters are considered among the most relevant mobility-related parameters. Currently, gait assessments have been mainly analyzed in laboratory or hospital settings, which only partially reflect usual performance (i.e., real world behavior). In this study, we aim to validate a robust walking detection algorithm using a single foot-worn inertial measurement unit (IMU) in real-life settings. We used a challenging dataset including 18 individuals performing free-living activities. A multi-sensor wearable system including pressure insoles, multiple IMUs, and infrared distance sensors (INDIP) was used as reference. Accurate walking detection was obtained, with sensitivity and specificity of 98 and 91% respectively. As robust walking detection is needed for ambulatory monitoring to complete the processing pipeline from raw recorded data to walking/mobility outcomes, a validated algorithm would pave the way for assessing patient performance and gait quality in real-world conditions.

Identification of Fatigue and Sleepiness in Immune and Neurodegenerative Disorders from Measures of Real-World Gait Variability

Current assessments of fatigue and sleepiness rely on patient reported outcomes (PROs), which are subjective and prone to recall bias. The current study investigated the use of gait variability in the "real world" to identify patient fatigue and daytime sleepiness. Inertial measurement units were worn on the lower backs of 159 participants (117 with six different immune and neurodegenerative disorders and 42 healthy controls) for up to 20 days, whom completed regular PROs. To address walking bouts that were short and sparse, four feature groups were considered: sequence-independent variability (SIV), sequence-dependant variability (SDV), padded SDV (PSDV), and typical gait variability (TGV) measures. These gait variability measures were extracted from step, stride, stance, and swing time, step length, and step velocity. These different approaches were compared using correlations and four machine learning classifiers to separate low/high fatigue and sleepiness.Most balanced accuracies were above 50%, the highest was 57.04% from TGV measures. The strongest correlation was 0.262 from an SDV feature against sleepiness. Overall, TGV measures had lower correlations and classification accuracies.Identifying fatigue or sleepiness from gait variability is extremely complex and requires more investigation with a larger data set, but these measures have shown performances that could contribute to a larger feature set.Clinical relevance- Gait variability has been repeatedly used to assess fatigue in the lab. The current study, however, explores gait variability for fatigue and daytime sleepiness in real-world scenarios with multiple gait-impacted disorders.

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.

The Role of Wearable Sensors to Monitor Physical Activity and Sleep Patterns in Older Adult Inpatients: A Structured Review

Low levels of physical activity (PA) and sleep disruption are commonly seen in older adult inpatients and are associated with poor health outcomes. Wearable sensors allow for objective continuous monitoring; however, there is no consensus as to how wearable sensors should be implemented. This review aimed to provide an overview of the use of wearable sensors in older adult inpatient populations, including models used, body placement and outcome measures. Five databases were searched; 89 articles met inclusion criteria. We found that studies used heterogenous methods, including a variety of sensor models, placement and outcome measures. Most studies reported the use of only one sensor, with either the wrist or thigh being the preferred location in PA studies and the wrist for sleep outcomes. The reported PA measures can be mostly characterised as the frequency and duration of PA (Volume) with fewer measures relating to intensity (rate of magnitude) and pattern of activity (distribution per day/week). Sleep and circadian rhythm measures were reported less frequently with a limited number of studies providing both physical activity and sleep/circadian rhythm outcomes concurrently. This review provides recommendations for future research in older adult inpatient populations. With protocols of best practice, wearable sensors could facilitate the monitoring of inpatient recovery and provide measures to inform participant stratification and establish common objective endpoints across clinical trials.

Validation of an Algorithm for Measurement of Sedentary Behaviour in Community-Dwelling Older Adults

Accurate measurement of sedentary behaviour in older adults is informative and relevant. Yet, activities such as sitting are not accurately distinguished from non-sedentary activities (e.g., upright activities), especially in real-world conditions. This study examines the accuracy of a novel algorithm to identify sitting, lying, and upright activities in community-dwelling older people in real-world conditions. Eighteen older adults wore a single triaxial accelerometer with an onboard triaxial gyroscope on their lower back and performed a range of scripted and non-scripted activities in their homes/retirement villages whilst being videoed. A novel algorithm was developed to identify sitting, lying, and upright activities. The algorithm's sensitivity, specificity, positive predictive value, and negative predictive value for identifying scripted sitting activities ranged from 76.9% to 94.8%. For scripted lying activities: 70.4% to 95.7%. For scripted upright activities: 75.9% to 93.1%. For non-scripted sitting activities: 92.3% to 99.5%. No non-scripted lying activities were captured. For non-scripted upright activities: 94.3% to 99.5%. The algorithm could, at worst, overestimate or underestimate sedentary behaviour bouts by ±40 s, which is within a 5% error for sedentary behaviour bouts. These results indicate good to excellent agreement for the novel algorithm, providing a valid measure of sedentary behaviour in community-dwelling older adults.

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

Introduction: Accurately assessing people's gait, especially in real-world conditions and in case of impaired mobility, is still a challenge due to intrinsic and extrinsic factors resulting in gait complexity. To improve the estimation of gait-related digital mobility outcomes (DMOs) in real-world scenarios, this study presents a wearable multi-sensor system (INDIP), integrating complementary sensing approaches (two plantar pressure insoles, three inertial units and two distance sensors). Methods: The INDIP technical validity was assessed against stereophotogrammetry during a laboratory experimental protocol comprising structured tests (including continuous curvilinear and rectilinear walking and steps) and a simulation of daily-life activities (including intermittent gait and short walking bouts). To evaluate its performance on various gait patterns, data were collected on 128 participants from seven cohorts: healthy young and older adults, patients with Parkinson's disease, multiple sclerosis, chronic obstructive pulmonary disease, congestive heart failure, and proximal femur fracture. Moreover, INDIP usability was evaluated by recording 2.5-h of real-world unsupervised activity. Results and discussion: Excellent absolute agreement (ICC >0.95) and very limited mean absolute errors were observed for all cohorts and digital mobility outcomes (cadence ≤0.61 steps/min, stride length ≤0.02 m, walking speed ≤0.02 m/s) in the structured tests. Larger, but limited, errors were observed during the daily-life simulation (cadence 2.72-4.87 steps/min, stride length 0.04-0.06 m, walking speed 0.03-0.05 m/s). Neither major technical nor usability issues were declared during the 2.5-h acquisitions. Therefore, the INDIP system can be considered a valid and feasible solution to collect reference data for analyzing gait in real-world conditions.

Feasibility and usability of a digital health technology system to monitor mobility and assess medication adherence in mild-to-moderate Parkinson's disease

Introduction

Parkinson's disease (PD) is a neurodegenerative disorder which requires complex medication regimens to mitigate motor symptoms. The use of digital health technology systems (DHTSs) to collect mobility and medication data provides an opportunity to objectively quantify the effect of medication on motor performance during day-to-day activities. This insight could inform clinical decision-making, personalise care, and aid self-management. This study investigates the feasibility and usability of a multi-component DHTS to remotely assess self-reported medication adherence and monitor mobility in people with Parkinson's (PwP).

Methods

Thirty participants with PD [Hoehn and Yahr stage I (n = 1) and II (n = 29)] were recruited for this cross-sectional study. Participants were required to wear, and where appropriate, interact with a DHTS (smartwatch, inertial measurement unit, and smartphone) for seven consecutive days to assess medication adherence and monitor digital mobility outcomes and contextual factors. Participants reported their daily motor complications [motor fluctuations and dyskinesias (i.e., involuntary movements)] in a diary. Following the monitoring period, participants completed a questionnaire to gauge the usability of the DHTS. Feasibility was assessed through the percentage of data collected, and usability through analysis of qualitative questionnaire feedback.

Results

Adherence to each device exceeded 70% and ranged from 73 to 97%. Overall, the DHTS was well tolerated with 17/30 participants giving a score &gt; 75% [average score for these participants = 89%, from 0 (worst) to 100 (best)] for its usability. Usability of the DHTS was significantly associated with age (ρ = −0.560, BCa 95% CI [−0.791, −0.207]). This study identified means to improve usability of the DHTS by addressing technical and design issues of the smartwatch. Feasibility, usability and acceptability were identified as key themes from PwP qualitative feedback on the DHTS.

Conclusion

This study highlighted the feasibility and usability of our integrated DHTS to remotely assess medication adherence and monitor mobility in people with mild-to-moderate Parkinson's disease. Further work is necessary to determine whether this DHTS can be implemented for clinical decision-making to optimise management of PwP.

Mobility recorded by wearable devices and gold standards: the Mobilise-D procedure for data standardization

Wearable devices are used in movement analysis and physical activity research to extract clinically relevant information about an individual's mobility. Still, heterogeneity in protocols, sensor characteristics, data formats, and gold standards represent a barrier for data sharing, reproducibility, and external validation. In this study, we aim at providing an example of how movement data (from the real-world and the laboratory) recorded from different wearables and gold standard technologies can be organized, integrated, and stored. We leveraged on our experience from a large multi-centric study (Mobilise-D) to provide guidelines that can prove useful to access, understand, and re-use the data that will be made available from the study. These guidelines highlight the encountered challenges and the adopted solutions with the final aim of supporting standardization and integration of data in other studies and, in turn, to increase and facilitate comparison of data recorded in the scientific community. We also provide samples of standardized data, so that both the structure of the data and the procedure can be easily understood and reproduced.

Associations Between Local Area Deprivation and Physical Activity Participation in People with Cognitive Impairment in the North East of England

BACKGROUND

Promoting physical activity, such as habitual walking behaviors, in people with cognitive impairment may support their ability to remain independent with a good quality of life for longer. However, people with cognitive impairment participate in less physical activity compared to cognitively unimpaired older adults. The local area in which people live may significantly impact abilities to participate in physical activity. For example, people who live in more deprived areas may have less safe and walkable routes.

OBJECTIVE

To examine this further, this study aimed to explore associations between local area deprivation and physical activity in people with cognitive impairment and cognitively unimpaired older adults (controls).

METHODS

87 participants with cognitive impairment (mild cognitive impairment or dementia) and 27 older adult controls from the North East of England were included in this analysis. Participants wore a tri-axial wearable accelerometer (AX3, Axivity) on their lower backs continuously for seven days. The primary physical activity outcome was daily step count. Individuals' neighborhoods were linked to UK government area deprivation statistics. Hierarchical Bayesian models assessed the association between local area deprivation and daily step count in people with cognitive impairment and controls.

RESULTS

Key findings indicated that there was no association between local area deprivation and daily step count in people with cognitive impairment, but higher deprivation was associated with lower daily steps for controls.

CONCLUSION

These findings suggest that cognitive impairment may be associated with lower participation in physical activity which supersedes the influence of local area deprivation observed in normal aging.

Can Digital Mobility Assessment Enhance the Clinical Assessment of Disease Severity in Parkinson's Disease?

BACKGROUND

Real-world walking speed (RWS) measured using wearable devices has the potential to complement the Movement Disorder Society-Unified Parkinson's Disease Rating Scale (MDS-UPDRS III) for motor assessment in Parkinson's disease (PD).

OBJECTIVE

Explore cross-sectional and longitudinal differences in RWS between PD and older adults (OAs), and whether RWS was related to motor disease severity cross-sectionally, and if MDS-UPDRS III was related to RWS, longitudinally.

METHODS

88 PD and 111 OA participants from ICICLE-GAIT (UK) were included. RWS was evaluated using an accelerometer at four time points. RWS was aggregated within walking bout (WB) duration thresholds. Between-group-comparisons in RWS between PD and OAs were conducted cross-sectionally, and longitudinally with mixed effects models (MEMs). Cross-sectional association between RWS and MDS-UPDRS III was explored using linear regression, and longitudinal association explored with MEMs.

RESULTS

RWS was significantly lower in PD (1.04 m/s) in comparison to OAs (1.10 m/s) cross-sectionally. RWS significantly decreased over time for both cohorts and decline was more rapid in PD by 0.02 m/s per year. Significant negative relationship between RWS and the MDS-UPDRS III only existed at a specific WB threshold (30 to 60 s, β= - 3.94 points, p = 0.047). MDS-UPDRS III increased significantly by 1.84 points per year, which was not related to change in RWS.

CONCLUSION

Digital mobility assessment of gait may add unique information to quantify disease progression remotely, but further validation in research and clinical settings is needed.

Design and validation of a multi-task, multi-context protocol for real-world gait simulation

BACKGROUND

Measuring mobility in daily life entails dealing with confounding factors arising from multiple sources, including pathological characteristics, patient specific walking strategies, environment/context, and purpose of the task. The primary aim of this study is to propose and validate a protocol for simulating real-world gait accounting for all these factors within a single set of observations, while ensuring minimisation of participant burden and safety.

METHODS

The protocol included eight motor tasks at varying speed, incline/steps, surface, path shape, cognitive demand, and included postures that may abruptly alter the participants' strategy of walking. It was deployed in a convenience sample of 108 participants recruited from six cohorts that included older healthy adults (HA) and participants with potentially altered mobility due to Parkinson's disease (PD), multiple sclerosis (MS), proximal femoral fracture (PFF), chronic obstructive pulmonary disease (COPD) or congestive heart failure (CHF). A novelty introduced in the protocol was the tiered approach to increase difficulty both within the same task (e.g., by allowing use of aids or armrests) and across tasks.

RESULTS

The protocol proved to be safe and feasible (all participants could complete it and no adverse events were recorded) and the addition of the more complex tasks allowed a much greater spread in walking speeds to be achieved compared to standard straight walking trials. Furthermore, it allowed a representation of a variety of daily life relevant mobility aspects and can therefore be used for the validation of monitoring devices used in real life.

CONCLUSIONS

The protocol allowed for measuring gait in a variety of pathological conditions suggests that it can also be used to detect changes in gait due to, for example, the onset or progression of a disease, or due to therapy.

TRIAL REGISTRATION

ISRCTN-12246987.

Using digital technology to quantify habitual physical activity in community-dwellers with cognitive impairment: A systematic review (Preprint)

BACKGROUND

Participating in habitual physical activity (HPA) can support people with dementia and mild cognitive impairment (MCI) to maintain functional independence. Digital technology can continuously measure HPA objectively, capturing nuanced measures relating to its volume, intensity, pattern, and variability.

OBJECTIVE

To understand HPA participation in people with cognitive impairment, this systematic review aims to (1) identify digital methods and protocols; (2) identify metrics used to assess HPA; (3) describe differences in HPA between people with dementia, MCI, and controls; and (4) make recommendations for measuring and reporting HPA in people with cognitive impairment.

METHODS

Key search terms were input into 6 databases: Scopus, Web of Science, Psych Articles, PsychInfo, MEDLINE, and Embase. Articles were included if they included community dwellers with dementia or MCI, reported HPA metrics derived from digital technology, were published in English, and were peer reviewed. Articles were excluded if they considered populations without dementia or MCI diagnoses, were based in aged care settings, did not concern digitally derived HPA metrics, or were only concerned with physical activity interventions. Key outcomes extracted included the methods and metrics used to assess HPA and differences in HPA outcomes across the cognitive spectrum. Data were synthesized narratively. An adapted version of the National Institute of Health Quality Assessment Tool for Observational Cohort and Cross-sectional Studies was used to assess the quality of articles. Due to significant heterogeneity, a meta-analysis was not feasible.

RESULTS

A total of 3394 titles were identified, with 33 articles included following the systematic review. The quality assessment suggested that studies were moderate-to-good quality. Accelerometers worn on the wrist or lower back were the most prevalent methods, while metrics relating to volume (eg, daily steps) were most common for measuring HPA. People with dementia had lower volumes, intensities, and variability with different daytime patterns of HPA than controls. Findings in people with MCI varied, but they demonstrated different patterns of HPA compared to controls.

CONCLUSIONS

This review highlights limitations in the current literature, including lack of standardization in methods, protocols, and metrics; limited information on validity and acceptability of methods; lack of longitudinal research; and limited associations between HPA metrics and clinically meaningful outcomes. Limitations of this review include the exclusion of functional physical activity metrics (eg, sitting/standing) and non-English articles. Recommendations from this review include suggestions for measuring and reporting HPA in people with cognitive impairment and for future research including validation of methods, development of a core set of clinically meaningful HPA outcomes, and further investigation of socioecological factors that may influence HPA participation.

TRIAL REGISTRATION

PROSPERO CRD42020216744; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=216744  .

Auditory rhythmical cueing to improve gait in community-dwelling stroke survivors (ACTIVATE): a pilot randomised controlled trial

Background

Gait impairment limiting mobility and restricting activities is common after stroke. Auditory rhythmical cueing (ARC) uses a metronome beat delivered during exercise to train stepping and early work reports gait improvements. This study aimed to establish the feasibility of a full scale multicentre randomised controlled trial to evaluate an ARC gait and balance training programme for use by stroke survivors in the home and outdoors.

Methods

A parallel-group observer-blind pilot randomised controlled trial was conducted. Adults within 2 years of stroke with a gait-related mobility impairment were recruited from four NHS stroke services and randomised to an ARC gait and balance training programme (intervention) or the training programme without ARC (control). Both programmes consisted of 3x30 min sessions per week for 6 weeks undertaken at home/nearby outdoor community. One session per week was supervised and the remainder self-managed. Gait and balance performance assessments were undertaken at baseline, 6 and 10 weeks. Key trial outcomes included recruitment and retention rates, programme adherence, assessment data completeness and safety.

Results

Between November 2018 and February 2020, 59 participants were randomised (intervention n=30, control n=29), mean recruitment rate 4/month. At baseline, 6 weeks and 10 weeks, research assessments were conducted for 59/59 (100%), 47/59 (80%) and 42/59 (71%) participants, respectively. Missing assessments were largely due to discontinuation of data collection from mid-March 2020 because of the UK COVID-19 pandemic lockdown. The proportion of participants with complete data for each individual performance assessment ranged from 100% at baseline to 68% at 10 weeks. In the intervention group, 433/540 (80%) total programme exercise sessions were undertaken, in the control group, 390/522 (75%). Falls were reported by five participants in the intervention group, six in the control group. Three serious adverse events occurred, all unrelated to the study.

Conclusion

We believe that a definitive multicentre RCT to evaluate the ARC gait and balance training programme is feasible. Recruitment, programme adherence and safety were all acceptable. Although we consider that the retention rate and assessment data completeness were not sufficient for a future trial, this was largely due to the UK COVID-19 pandemic lockdown.

Trial registration

ISRCTN, ISRCTN10874601, Registered on 05/03/2018,

Supplementary Information

The online version contains supplementary material available at 10.1186/s40814-022-01193-y.

Acipimox in Mitochondrial Myopathy (AIMM): study protocol for a randomised, double-blinded, placebo-controlled, adaptive design trial of the efficacy of acipimox in adult patients with mitochondrial myopathy

BACKGROUND

Mitochondrial disease is a heterogenous group of rare, complex neurometabolic disorders. Despite their individual rarity, collectively mitochondrial diseases represent the most common cause of inherited metabolic disorders in the UK; they affect 1 in every 4300 individuals, up to 15,000 adults (and a similar number of children) in the UK. Mitochondrial disease manifests multisystem and isolated organ involvement, commonly affecting those tissues with high energy demands, such as skeletal muscle. Myopathy manifesting as fatigue, muscle weakness and exercise intolerance is common and debilitating in patients with mitochondrial disease. Currently, there are no effective licensed treatments and consequently, there is an urgent clinical need to find an effective drug therapy.

AIM

To investigate the efficacy of 12-week treatment with acipimox on the adenosine triphosphate (ATP) content of skeletal muscle in patients with mitochondrial disease and myopathy.

METHODS

AIMM is a single-centre, double blind, placebo-controlled, adaptive designed trial, evaluating the efficacy of 12 weeks' administration of acipimox on skeletal muscle ATP content in patients with mitochondrial myopathy. Eligible patients will receive the trial investigational medicinal product (IMP), either acipimox or matched placebo. Participants will also be prescribed low dose aspirin as a non-investigational medical product (nIMP) in order to protect the blinding of the treatment assignment. Eighty to 120 participants will be recruited as required, with an interim analysis for sample size re-estimation and futility assessment being undertaken once the primary outcome for 50 participants has been obtained. Randomisation will be on a 1:1 basis, stratified by Fatigue Impact Scale (FIS) (dichotomised as < 40, ≥ 40). Participants will take part in the trial for up to 20 weeks, from screening visits through to follow-up at 16 weeks post randomisation. The primary outcome of change in ATP content in skeletal muscle and secondary outcomes relating to quality of life, perceived fatigue, disease burden, limb function, balance and walking, skeletal muscle analysis and symptom-limited cardiopulmonary fitness (optional) will be assessed between baseline and 12 weeks.

DISCUSSION

The AIMM trial will investigate the effect of acipimox on modulating muscle ATP content and whether it can be repurposed as a new treatment for mitochondrial disease with myopathy.

TRIAL REGISTRATION

EudraCT2018-002721-29 . Registered on 24 December 2018, ISRCTN 12895613. Registered on 03 January 2019, https://www.isrctn.com/search?q=aimm.

Free-living monitoring of ambulatory activity after treatments for lower extremity musculoskeletal cancers using an accelerometer-based wearable - a new paradigm to outcome assessment in musculoskeletal oncology?

PURPOSE

Ambulatory activity (walking) is affected after sarcoma surgery yet is not routinely assessed. Small inexpensive accelerometers could bridge the gap. Study objectives investigated, whether in patients with lower extremity musculoskeletal tumours: (A) it was feasible to conduct ambulatory activity assessments in patient's homes using an accelerometer-based wearable (AX3, Axivity). (B) AX3 assessments produced clinically useful data, distinguished tumour sub-groups and related to existing measures.

METHODS

In a prospective cross-sectional pilot, 34 patients with musculoskeletal tumours in the femur/thigh (19), pelvis/hip (3), tibia/leg (9), or ankle/foot (3) participated. Twenty-seven had limb-sparing surgery and seven amputation. Patients were assessed using a thigh-worn monitor. Summary measures of volume (total steps/day, total ambulatory bouts/day, mean bout length), pattern (alpha), and variability (S₂) of ambulatory activity were derived.

RESULTS

AX3 was well-tolerated and feasible to use. Outcomes compared to literature but did not distinguish tumour sub-groups. Alpha negatively correlated with disability (walking outside (r=-418, p = 0.042*), social life (r=-0.512, p = 0.010*)). Disability negatively predicted alpha (unstandardised co-efficient= -0.001, R²=0.186, p = 0.039*).

CONCLUSIONS

A wearable can assess novel attributes of walking; volume, pattern, and variability after sarcoma surgery. Such outcomes provide valuable information about people's physical performance in their homes, which can guide rehabilitation. Implications for rehabilitationRoutine capture of ambulatory activity by sarcoma services in peoples' homes can provide important information about individuals "actual" physical activity levels and limitations after sarcoma surgery to inform personalised rehabilitation and care needs, including timely referral for support.Routine remote ambulatory monitoring about out of hospital activity can support personalised care for patients, including identifying high risk patients who need rapid intervention and care closer to home.Use of routine remote ambulatory monitoring could enhance delivery of evidence-based care closer to peoples' homes without disrupting their daily routine and therefore reducing patient and carer burden.Collection of data close to home using questionnaires and objective community assessment could be more cost effective and comprehensive than in-hospital assessment and could reduce the need for hospital attendance, which is of importance to vulnerable patients, particularly during the Covid-19 pandemic.

An Algorithm for Accurate Marker-Based Gait Event Detection in Healthy and Pathological Populations During Complex Motor Tasks

There is growing interest in the quantification of gait as part of complex motor tasks. This requires gait events (GEs) to be detected under conditions different from straight walking. This study aimed to propose and validate a new marker-based GE detection method, which is also suitable for curvilinear walking and step negotiation. The method was first tested against existing algorithms using data from healthy young adults (YA, n = 20) and then assessed in data from 10 individuals from the following five cohorts: older adults, chronic obstructive pulmonary disease, multiple sclerosis, Parkinson’s disease, and proximal femur fracture. The propagation of the errors associated with GE detection on the calculation of stride length, duration, speed, and stance/swing durations was investigated. All participants performed a variety of motor tasks including curvilinear walking and step negotiation, while reference GEs were identified using a validated methodology exploiting pressure insole signals. Sensitivity, positive predictive values (PPV), F1-score, bias, precision, and accuracy were calculated. Absolute agreement [intraclass correlation coefficient (ICC2,1)] between marker-based and pressure insole stride parameters was also tested. In the YA cohort, the proposed method outperformed the existing ones, with sensitivity, PPV, and F1 scores ≥ 99% for both GEs and conditions, with a virtually null bias (&lt;10 ms). Overall, temporal inaccuracies minimally impacted stride duration, length, and speed (median absolute errors ≤1%). Similar algorithm performances were obtained for all the other five cohorts in GE detection and propagation to the stride parameters, where an excellent absolute agreement with the pressure insoles was also found (ICC2,1=0.817− 0.999). In conclusion, the proposed method accurately detects GE from marker data under different walking conditions and for a variety of gait impairments.

Investigating the Impact of Environment and Data Aggregation by Walking Bout Duration on Parkinson's Disease Classification Using Machine Learning

Parkinson's disease (PD) is a common neurodegenerative disease. PD misdiagnosis can occur in early stages. Gait impairment in PD is typical and is linked with an increased fall risk and poorer quality of life. Applying machine learning (ML) models to real-world gait has the potential to be more sensitive to classify PD compared to laboratory data. Real-world gait yields multiple walking bouts (WBs), and selecting the optimal method to aggregate the data (e.g., different WB durations) is essential as this may influence classification performance. The objective of this study was to investigate the impact of environment (laboratory vs. real world) and data aggregation on ML performance for optimizing sensitivity of PD classification. Gait assessment was performed on 47 people with PD (age: 68 ± 9 years) and 52 controls [Healthy controls (HCs), age: 70 ± 7 years]. In the laboratory, participants walked at their normal pace for 2 min, while in the real world, participants were assessed over 7 days. In both environments, 14 gait characteristics were evaluated from one tri-axial accelerometer attached to the lower back. The ability of individual gait characteristics to differentiate PD from HC was evaluated using the Area Under the Curve (AUC). ML models (i.e., support vector machine, random forest, and ensemble models) applied to real-world gait showed better classification performance compared to laboratory data. Real-world gait characteristics aggregated over longer WBs (WB 30-60 s, WB > 60 s, WB > 120 s) resulted in superior discriminative performance (PD vs. HC) compared to laboratory gait characteristics (0.51 ≤ AUC ≤ 0.77). Real-world gait speed showed the highest AUC of 0.77. Overall, random forest trained on 14 gait characteristics aggregated over WBs > 60 s gave better performance (F1 score = 77.20 ± 5.51%) as compared to laboratory results (F1 Score = 68.75 ± 12.80%). Findings from this study suggest that the choice of environment and data aggregation are important to achieve maximum discrimination performance and have direct impact on ML performance for PD classification. This study highlights the importance of a harmonized approach to data analysis in order to drive future implementation and clinical use.

Clinical Trial Registration

[09/H0906/82].

Optimising function and well-being in older adults: protocol for an integrated research programme in Aotearoa/New Zealand

BACKGROUND

Maintaining independence is of key importance to older people. Ways to enable health strategies, strengthen and support whanāu (family) at the community level are needed. The Ageing Well through Eating, Sleeping, Socialising and Mobility (AWESSOM) programme in Aotearoa/New Zealand (NZ) delivers five integrated studies across different ethnicities and ages to optimise well-being and to reverse the trajectory of functional decline and dependence associated with ageing.

METHODS

Well-being, independence and the trajectory of dependence are constructs viewed differently according to ethnicity, age, and socio-cultural circumstance. For each AWESSoM study these constructs are defined and guide study development through collaboration with a wide range of stakeholders, and with reference to current evidence. The Compression of Functional Decline model (CFD) underpins aspects of the programme. Interventions vary to optimise engagement and include a co-developed whānau (family) centred initiative (Ngā Pou o Rongo), the use of a novel LifeCurve™App to support behavioural change, development of health and social initiatives to support Pacific elders, and the use of a comprehensive oral health and cognitive stimulation programme for cohorts in aged residential care. Running parallel to these interventions is analysis of large data sets from primary care providers and national health databases to understand complex multi-morbidities and identify those at risk of adverse outcomes. Themes or target areas of sleep, physical activity, oral health, and social connectedness complement social capital and community integration in a balanced programme involving older people across the ability spectrum.

DISCUSSION

AWESSoM delivers a programme of bespoke yet integrated studies. Outcomes and process analysis from this research will inform about novel approaches to implement relevant, socio-cultural interventions to optimise well-being and health, and to reverse the trajectory of decline experienced with age.

TRIAL REGISTRATION

The At-risk cohort study was registered by the Australian New Zealand Clinical Trials registry on 08/12/2021 (Registration number ACTRN 12621001679875 ).

Acceptability and deliverability of an auditory rhythmical cueing (ARC) training programme for use at home and outdoors to improve gait and physical activity post-stroke

BACKGROUND

Although laboratory studies demonstrate that training programmes using auditory rhythmical cueing (ARC) may improve gait post-stroke, few studies have evaluated this intervention in the home and outdoors where deployment may be more appropriate. This manuscript reports stakeholder refinement of an ARC gait and balance training programme for use at home and outdoors, and a study which assessed acceptability and deliverability of this programme.

METHODS

Programme design and content were refined during stakeholder workshops involving physiotherapists and stroke survivors. A two-group acceptability and deliverability study was then undertaken. Twelve patients post-stroke with a gait related mobility impairment received either the ARC gait and balance training programme or the gait and balance training programme without ARC. Programme provider written notes, participant exercise and fall diaries, adverse event monitoring and feedback questionnaires captured data about deliverability, safety and acceptability of the programmes.

RESULTS

The training programme consisted of 18 sessions (six supervised, 12 self-managed) of exercises and ARC delivered by a low-cost commercially available metronome. All 12 participants completed the six supervised sessions and 10/12 completed the 12 self-managed sessions. Provider and participant session written records and feedback questionnaires confirmed programme deliverability and acceptability.

CONCLUSION

An ARC gait and balance training programme refined by key stakeholders was feasible to deliver and acceptable to participants and providers.

TRIAL REGISTRATION

ISCTRN 12/03/2018.

Digital mobility outcomes to assess habitual physical activity in people with cognitive impairment: A systematic review

BACKGROUND

Maintaining habitual physical activity (HPA) is essential for people with dementia and mild cognitive impairment (MCI) to remain functionally independent. Therefore, physical activity interventions may complement care services and promote wellbeing and independence in this population. The advent of digital technology, such as wearable technology and ambient sensors, has enhanced our ability to objectively and reliably measure HPA in a cognitively-impaired population. Digital technology can continuously and remotely capture a range of digital mobility outcomes important to independence, such as volume (i.e. amount of HPA), intensity (i.e. rate/magnitude of HPA), pattern (i.e. distribution of HPA over time) and variability (i.e. how regular or dynamic HPA is) of HPA. In order to inform clinical interventions and public health strategies for dementia, appropriate HPA outcomes must be quantified. The key aim of this review is to identify the digital tools and HPA outcomes used in community-dwellers with dementia and mild cognitive impairment, and describe the volumes, intensities, pattern and variability of physical activity in this population.

METHOD

2975 article titles were systematically reviewed. Following title search, 266 abstracts were selected for abstract review. Seventy-five articles are currently undergoing full text review.

RESULT

This review will report (1). digital technology used to assess HPA (e.g. accelerometers, infra-red sensors), (2). the range of digital outcomes reported (e.g. steps per day, average ambulatory bout length), (3). key findings relating to the quantification of volume, intensity, pattern and variability of HPA in people with dementia and MCI, drawing comparisons to healthy older adults were applicable.

CONCLUSION

Findings from this review will be informative to future selection of digital mobility tools and outcomes to quantify HPA in people with dementia and MCI. The literature will be synthesized to identify the current state of research and identify gaps for future investigation. Recommendations will be made for the development of protocols to continuously and remotely assess HPA in people with cognitive impairment, and for identifying the most appropriate digital mobility outcomes to serve as clinical or interventional endpoints to monitor change in HPA in this population.

Walking parameters of older adults from a lower back inertial measurement unit, a 6-year longitudinal observational study

Gait changes during aging and differs between sexes. Inertial measurement units (IMUs) enable accurate quantitative evaluations of gait in ambulatory environments and in large populations. This study aims to provide IMU-based gait parameters' values derived from a large longitudinal cohort study in older adults. We measured gait parameters, such as velocity, step length, time, variability, and asymmetry, from straight, self-paced 20-m walks in older adults (four visits: 715/1102/1017/957 participants) every second year over 6 years using an IMU at the lower back. Moreover, we calculated the associations of gait parameters with sex and age. Women showed lower gait speed, step length, step time, stride time, swing time, and stance time, compared to men. Longitudinal analyses suggest that these parameters are at least partly deteriorating within the assessment period of 2 years, especially in men and at an older age. Variability and asymmetry parameters show a less clear sex- and age-associated pattern. Altogether, our large longitudinal dataset provides the first sex-specific information on which parameters are particularly promising for the detection of age-related gait changes that can be extracted from an IMU on the lower back. This information may be helpful for future observational and treatment studies investigating sex and age-related effects on gait, as well as for studies investigating age-related diseases.

Technical validation of real-world monitoring of gait: a multicentric observational study

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).

Predicting the Progression of Parkinson's Disease MDS-UPDRS-III Motor Severity Score from Gait Data using Deep Learning

Parkinson's disease (PD) is a common neurodegenerative disease presenting with both motor and non-motor symptoms. Among PD motor symptoms, gait impairments are common and evolve over time. PD motor symptoms severity can be evaluated using clinical scales such as the Movement Disorder Society Unified Parkinson's Rating Scale part III (MDS-UPDRS-III), which depend on the patient's status at the time of assessment and are limited by subjectivity. Objective quantification of motor symptoms (i.e. gait) with wearable technology paired with Deep Learning (DL) techniques could help assess motor severity. The aims of this study were to: (i) apply DL techniques to wearable-based gait data to estimate MDS-UPDRS-III scores; (ii) test the DL approach on longitudinal dataset to predict the progression of MDS-UPDRSIII scores. PD gait was measured in the laboratory, during a 2 minute continuous walk, with a sensor positioned on the lower back. A DL Convolutional Neural Network (CNN) was trained on 70 PD subjects (mean disease duration: 3.5 years), validated on 58 subjects (mean disease duration: 5 years) and tested on 46 subjects (mean disease duration: 6.5 years). Model performance was evaluated on longitudinal data by quantifying the association (Pearson correlation (r)), absolute agreement (Intraclass correlation (ICC)) and mean absolute error between the predicted and true MDS-UPDRS-III. Results showed that MDS-UPDRS-III scores predicted with the proposed model, strongly correlated (r=0.82) and had a good agreement (ICC(2,1)=0.76) with true values; the mean absolute error for the predicted MDS-UPDRS-III scores was 6.29 points. The results from this study are encouraging and show that a DL-CNN model trained on baseline wearable-based gait data could be used to assess PD motor severity after 3 years.Clinical Relevance-Gait assessed with wearable technology paired with DL-CNN can estimate PD motor symptom severity and progression to support clinical decision making.

Consensus based framework for digital mobility monitoring

Digital mobility assessment using wearable sensor systems has the potential to capture walking performance in a patient's natural environment. It enables monitoring of health status and disease progression and evaluation of interventions in real-world situations. In contrast to laboratory settings, real-world walking occurs in non-conventional environments and under unconstrained and uncontrolled conditions. Despite the general understanding, there is a lack of agreed definitions about what constitutes real-world walking, impeding the comparison and interpretation of the acquired data across systems and studies. The goal of this study was to obtain expert-based consensus on specific aspects of real-world walking and to provide respective definitions in a common terminological framework. An adapted Delphi method was used to obtain agreed definitions related to real-world walking. In an online survey, 162 participants from a panel of academic, clinical and industrial experts with experience in the field of gait analysis were asked for agreement on previously specified definitions. Descriptive statistics was used to evaluate whether consent (> 75% agreement as defined a priori) was reached. Of 162 experts invited to participate, 51 completed all rounds (31.5% response rate). We obtained consensus on all definitions ("Walking" > 90%, "Purposeful" > 75%, "Real-world" > 90%, "Walking bout" > 80%, "Walking speed" > 75%, "Turning" > 90% agreement) after two rounds. The identification of a consented set of real-world walking definitions has important implications for the development of assessment and analysis protocols, as well as for the reporting and comparison of digital mobility outcomes across studies and systems. The definitions will serve as a common framework for implementing digital and mobile technologies for gait assessment and are an important link for the transition from supervised to unsupervised gait assessment.

Exenatide once weekly over 2 years as a potential disease-modifying treatment for Parkinson's disease: protocol for a multicentre, randomised, double blind, parallel group, placebo controlled, phase 3 trial: The 'Exenatide-PD3' study

INTRODUCTION

Parkinson's disease (PD) is a common neurodegenerative disorder with substantial morbidity. No disease-modifying treatments currently exist. The glucagon like peptide-1 receptor agonist exenatide has been associated in single-centre studies with reduced motor deterioration over 1 year. The aim of this multicentre UK trial is to confirm whether these previous positive results are maintained in a larger number of participants over 2 years and if effects accumulate with prolonged drug exposure.

METHODS AND ANALYSIS

This is a phase 3, multicentre, double-blind, randomised, placebo-controlled trial of exenatide at a dose of 2 mg weekly in 200 participants with mild to moderate PD. Treatment duration is 96 weeks. Randomisation is 1:1, drug to placebo. Assessments are performed at baseline, week 12, 24, 36, 48, 60, 72, 84 and 96 weeks.The primary outcome is the comparison of Movement Disorders Society Unified Parkinson's Disease Rating Scale part 3 motor subscore in the practically defined OFF medication state at 96 weeks between participants according to treatment allocation. Secondary outcomes will compare the change between groups among other motor, non-motor and cognitive scores. The primary outcome will be reported using descriptive statistics and comparisons between treatment groups using a mixed model, adjusting for baseline scores. Secondary outcomes will be summarised between treatment groups using summary statistics and appropriate statistical tests to assess for significant differences.

ETHICS AND DISSEMINATION

This trial has been approved by the South Central-Berkshire Research Ethics Committee and the Health Research Authority. Results will be disseminated in peer-reviewed journals, presented at scientific meetings and to patients in lay-summary format.

TRIAL REGISTRATION NUMBERS

NCT04232969, ISRCTN14552789.

Detecting Sensitive Mobility Features for Parkinson's Disease Stages Via Machine Learning

BACKGROUND

It is not clear how specific gait measures reflect disease severity across the disease spectrum in Parkinson's disease (PD).

OBJECTIVE

To identify the gait and mobility measures that are most sensitive and reflective of PD motor stages and determine the optimal sensor location in each disease stage.

METHODS

Cross-sectional wearable-sensor records were collected in 332 patients with PD (Hoehn and Yahr scale I-III) and 100 age-matched healthy controls. Sensors were adhered to the participant's lower back, bilateral ankles, and wrists. Study participants walked in a ~15-meter corridor for 1 minute under two walking conditions: (1) preferred, usual walking speed and (2) walking while engaging in a cognitive task (dual-task). A subgroup (n = 303, 67% PD) also performed the Timed Up and Go test. Multiple machine-learning feature selection and classification algorithms were applied to discriminate between controls and PD and between the different PD severity stages.

RESULTS

High discriminatory values were found between motor disease stages with mean sensitivity in the range 72%-83%, specificity 69%-80%, and area under the curve (AUC) 0.76-0.90. Measures from upper-limb sensors best discriminated controls from early PD, turning measures obtained from the trunk sensor were prominent in mid-stage PD, and stride timing and regularity were discriminative in more advanced stages.

CONCLUSIONS

Applying machine-learning to multiple, wearable-derived features reveals that different measures of gait and mobility are associated with and discriminate distinct stages of PD. These disparate feature sets can augment the objective monitoring of disease progression and may be useful for cohort selection and power analyses in clinical trials of PD. © 2021 International Parkinson and Movement Disorder Society.

Continuous Real-World Gait Monitoring in Idiopathic REM Sleep Behavior Disorder

BACKGROUND

Patients with REM sleep behavior disorder (RBD) have a high risk of developing PD, and thus can be used to study prodromal biomarkers. RBD has been associated with changes in gait; quantifying these changes using wearable technology is promising; however, most data are obtained in clinical settings precluding pragmatic application.

OBJECTIVE

We aimed to investigate if wearable-based, real-world gait monitoring can detect early gait changes and discriminate individuals with RBD from controls, and explore relationships between real-world gait and clinical characteristics.

METHODS

63 individuals with RBD (66±10 years) and 34 controls recruited in the Oxford Parkinson's Disease Centre Discovery Study were assessed. Data were collected using a wearable device positioned on the lower back for 7 days. Real-world gait was quantified in terms of its Macrostructure (volume, pattern and variability (S2)) and Microstructure (14 characteristics). The value of Macro and Micro gait in discriminating RBD from controls was explored using ANCOVA and ROC analysis, and correlation analysis was performed between gait and clinical characteristics.

RESULTS

Significant differences were found in discrete Micro characteristics in RBD with reduced gait velocity, variability and rhythm (p≤0.023). These characteristics significantly discriminated RBD (AUC≥0.620), with swing time as the single strongest discriminator (AUC=0.652). Longer walking bouts discriminated best between the groups for Macro and Micro outcomes (p≤0.036).

CONCLUSIONS

Our results suggest that real-world gait monitoring may have utility as "risk" clinical marker in RBD participants. Real-world gait assessment is low-cost and could serve as a pragmatic screening tool to identify gait impairment in RBD.

Balance Impairments as Differential Markers of Dementia Disease Subtype

Background

Accurately differentiating dementia subtypes, such as Alzheimer’s disease (AD) and Lewy body disease [including dementia with Lewy bodies (DLB) and Parkinson’s disease dementia (PDD)] is important to ensure appropriate management and treatment of the disease. Similarities in clinical presentation create difficulties for differential diagnosis. Simple supportive markers, such as balance assessments, may be useful to the diagnostic toolkit. This study aimed to identify differences in balance impairments between different dementia disease subtypes and normal aging using a single triaxial accelerometer.

Methods

Ninety-seven participants were recruited, forming four groups: cognitive impairment due to Alzheimer’s disease (AD group; n = 31), dementia with Lewy bodies (DLB group; n = 26), Parkinson’s disease dementia (PDD group; n = 13), and normal aging controls (n = 27). Participants were asked to stand still for 2 minutes in a standardized position with their eyes open while wearing a single triaxial accelerometer on their lower back. Seven balance characteristics were derived, including jerk (combined, mediolateral, and anterior–posterior), root mean square (RMS; combined, mediolateral, and anterior–posterior), and ellipsis. Mann–Whitney U tests identified the balance differences between groups. Receiver operating characteristics and area under the curve (AUC) determined the overall accuracy of the selected balance characteristics.

Results

The PDD group demonstrated higher RMS [combined (p = 0.001), mediolateral (p = 0.005), and anterior–posterior (p = 0.001)] and ellipsis scores (p < 0.002) than the AD group (AUC = 0.71–0.82). The PDD group also demonstrated significantly impaired balance across all characteristics (p ≤ 0.001) compared to the controls (AUC = 0.79–0.83). Balance differences were not significant between PDD and DLB (AUC = 0.69–0.74), DLB and AD (AUC = 0.50–0.65), DLB and controls (AUC = 0.62–0.68), or AD and controls (AUC = 0.55–0.67) following Bonferroni correction.

Discussion

Although feasible and quick to conduct, key findings suggest that an accelerometer-based balance during quiet standing does not differentiate dementia disease subtypes accurately. Assessments that challenge balance more, such as gait or standing with eyes closed, may prove more effective to support differential diagnosis.

Falls Risk in Relation to Activity Exposure in High-Risk Older Adults

Background

Physical activity is linked to many positive health outcomes, stimulating the development of exercise programs. However, many falls occur while walking and so promoting activity might paradoxically increase fall rates, causing injuries, and worse quality of life. The relationship between activity exposure and fall rates remains unclear. We investigated the relationship between walking activity (exposure to risk) and fall rates before and after an exercise program (V-TIME).

Methods

One hundred and nine older fallers, 38 fallers with mild cognitive impairment (MCI), and 128 fallers with Parkinson’s disease (PD) were randomly assigned to one of two active interventions: treadmill training only or treadmill training combined with a virtual reality component. Participants were tested before and after the interventions. Free-living walking activity was characterized by volume, pattern, and variability of ambulatory bouts using an accelerometer positioned on the lower back for 1 week. To evaluate that relationship between fall risk and activity, a normalized index was determined expressing fall rates relative to activity exposure (FRA index), with higher scores indicating a higher risk of falls per steps taken.

Results

At baseline, the FRA index was higher for fallers with PD compared to those with MCI and older fallers. Walking activity did not change after the intervention for the groups but the FRA index decreased significantly for all groups (p ≤ .035).

Conclusions

This work showed that V-TIME interventions reduced falls risk without concurrent change in walking activity. We recommend using the FRA index in future fall prevention studies to better understand the nature of intervention programs.

The Impact of Environment on Gait Assessment: Considerations from Real-World Gait Analysis in Dementia Subtypes

Laboratory-based gait assessments are indicative of clinical outcomes (e.g., disease identification). Real-world gait may be more sensitive to clinical outcomes, as impairments may be exaggerated in complex environments. This study aims to investigate how different environments (e.g., lab, real world) impact gait. Different walking bout lengths in the real world will be considered proxy measures of context. Data collected in different dementia disease subtypes will be analysed as disease-specific gait impairments are reported between these groups. Thirty-two people with cognitive impairment due to Alzheimer’s disease (AD), 28 due to dementia with Lewy bodies (DLB) and 25 controls were recruited. Participants wore a tri-axial accelerometer for six 10 m walks in lab settings, and continuously for seven days in the real world. Fourteen gait characteristics across five domains were measured (i.e., pace, variability, rhythm, asymmetry, postural control). In the lab, the DLB group showed greater step length variability (p = 0.008) compared to AD. Both subtypes demonstrated significant gait impairments (p < 0.01) compared to controls. In the real world, only very short walking bouts (<10 s) demonstrated different gait impairments between subtypes. The context where walking occurs impacts signatures of gait impairment in dementia subtypes. To develop real-world gait assessment as a clinical tool, algorithms and metrics must accommodate for changes in context.

Body-Worn Sensors for Remote Monitoring of Parkinson's Disease Motor Symptoms: Vision, State of the Art, and Challenges Ahead

The increasing prevalence of neurodegenerative conditions such as Parkinson's disease (PD) and related mobility issues places a serious burden on healthcare systems. The COVID-19 pandemic has reinforced the urgent need for better tools to manage chronic conditions remotely, as regular access to clinics may be problematic. Digital health technology in the form of remote monitoring with body-worn sensors offers significant opportunities for transforming research and revolutionizing the clinical management of PD. Significant efforts are being invested in the development and validation of digital outcomes to support diagnosis and track motor and mobility impairments "off-line". Imagine being able to remotely assess your patient, understand how well they are functioning, evaluate the impact of any recent medication/intervention, and identify the need for urgent follow-up before overt, irreparable change takes place? This could offer new pragmatic solutions for personalized care and clinical research. So the question remains: how close are we to achieving this? Here, we describe the state-of-the-art based on representative papers published between 2017 and 2020. We focus on remote (i.e., real-world, daily-living) monitoring of PD using body-worn sensors (e.g., accelerometers, inertial measurement units) for assessing motor symptoms and their complications. Despite the tremendous potential, existing challenges exist (e.g., validity, regulatory) that are preventing the widespread clinical adoption of body-worn sensors as a digital outcome. We propose a roadmap with clear recommendations for addressing these challenges and future directions to bring us closer to the implementation and widespread adoption of this important way of improving the clinical care, evaluation, and monitoring of PD.

Gait analysis as a clinical tool for dementia: current perspectives and future challenges

Gait, the way that we walk, requires complex cognitive functions. Gait may be a useful early marker for dementia diagnosis, as gait impairments precede and reflect cognitive decline. Early diagnosis of dementia enables individuals and their families to make informed decisions about their care plans, and allows researchers to understand preclinical and prodromal disease stages, providing novel targets for drug therapies. As such, a range of biomarkers are being developed to improve early and accurate diagnosis, including gait analysis. This editorial will outline how gait analysis can support the clinical diagnosis of dementia, including evidence of unique signatures of gait which can aid the identification of cognitive impairment and discrete dementia disease subtypes, the potential use of wearable technology to assess gait in the clinic and the real world, and key recommendations for the future implementation of gait into the diagnostic toolkit for dementia.

Gait Analysis with Wearables Can Accurately Classify Fallers from Non-Fallers: A Step toward Better Management of Neurological Disorders

Falls are the leading cause of mortality, morbidity and poor quality of life in older adults with or without neurological conditions. Applying machine learning (ML) models to gait analysis outcomes offers the opportunity to identify individuals at risk of future falls. The aim of this study was to determine the effect of different data pre-processing methods on the performance of ML models to classify neurological patients who have fallen from those who have not for future fall risk assessment. Gait was assessed using wearables in clinic while walking 20 m at a self-selected comfortable pace in 349 (159 fallers, 190 non-fallers) neurological patients. Six different ML models were trained on data pre-processed with three techniques such as standardisation, principal component analysis (PCA) and path signature method. Fallers walked more slowly, with shorter strides and longer stride duration compared to non-fallers. Overall, model accuracy ranged between 48% and 98% with 43-99% sensitivity and 48-98% specificity. A random forest (RF) classifier trained on data pre-processed with the path signature method gave optimal classification accuracy of 98% with 99% sensitivity and 98% specificity. Data pre-processing directly influences the accuracy of ML models for the accurate classification of fallers. Using gait analysis with trained ML models can act as a tool for the proactive assessment of fall risk and support clinical decision-making.