How Much Data Is Enough? A Reliable Methodology to Examine Long-Term Wearable Data Acquisition in Gait and Postural Sway

Wearable sensors facilitate the evaluation of gait and balance impairment in the free-living environment, often with observation periods spanning weeks, months, and even years. Data supporting the minimal duration of sensor wear, which is necessary to capture representative variability in impairment measures, are needed to balance patient burden, data quality, and study cost. Prior investigations have examined the duration required for resolving a variety of movement variables (e.g., gait speed, sit-to-stand tests), but these studies use differing methodologies and have only examined a small subset of potential measures of gait and balance impairment. Notably, postural sway measures have not yet been considered in these analyses. Here, we propose a three-level framework for examining this problem. Difference testing and intra-class correlations (ICC) are used to examine the agreement in features computed from potential wear durations (levels one and two). The association between features and established patient reported outcomes at each wear duration is also considered (level three) for determining the necessary wear duration. Utilizing wearable accelerometer data continuously collected from 22 persons with multiple sclerosis (PwMS) for 6 weeks, this framework suggests that 2 to 3 days of monitoring may be sufficient to capture most of the variability in gait and sway; however, longer periods (e.g., 3 to 6 days) may be needed to establish strong correlations to patient-reported clinical measures. Regression analysis indicates that the required wear duration depends on both the observation frequency and variability of the measure being considered. This approach provides a framework for evaluating wear duration as one aspect of the comprehensive assessment, which is necessary to ensure that wearable sensor-based methods for capturing gait and balance impairment in the free-living environment are fit for purpose.

[1]  R. Mcginnis,et al.  Advancing Digital Medicine with Wearables in the Wild , 2022, Sensors.

[2]  Brett M. Meyer,et al.  The Sit-to-Stand Transition as a Biomarker for Impairment: Comparison of Instrumented 30-Second Chair Stand Test and Daily Life Transitions in Multiple Sclerosis , 2022, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  Brett M. Meyer,et al.  Evaluation of unsupervised 30-second chair stand test performance assessed by wearable sensors to predict fall status in multiple sclerosis. , 2022, Gait & posture.

[4]  K. B. Beyer,et al.  Feasibility of a continuous, multi-sensor remote health monitoring approach in persons living with neurodegenerative disease , 2021, Journal of Neurology.

[5]  D. Cui,et al.  Recent developments in sensors for wearable device applications , 2021, Analytical and Bioanalytical Chemistry.

[6]  Nicky Baker,et al.  Inertial Sensor Reliability and Validity for Static and Dynamic Balance in Healthy Adults: A Systematic Review , 2021, Sensors.

[7]  Clint R. Bellenger,et al.  Wrist-Based Photoplethysmography Assessment of Heart Rate and Heart Rate Variability: Validation of WHOOP , 2021, Sensors.

[8]  Lukas Adamowicz,et al.  Wearables and Deep Learning Classify Fall Risk From Gait in Multiple Sclerosis , 2020, IEEE Journal of Biomedical and Health Informatics.

[9]  Charmaine Demanuele,et al.  Assessment of Sit-to-Stand Transfers during Daily Life Using an Accelerometer on the Lower Back , 2020, Sensors.

[10]  J. DeLuca,et al.  Tired of not knowing what that fatigue score means? Normative data of the Modified Fatigue Impact Scale (MFIS). , 2020, Multiple sclerosis and related disorders.

[11]  Koene R. A. Van Dijk,et al.  Age and environment-related differences in gait in healthy adults using wearables , 2020, npj Digital Medicine.

[12]  Ryan S McGinnis,et al.  Metrics extracted from a single wearable sensor during sit-stand transitions relate to mobility impairment and fall risk in people with multiple sclerosis. , 2020, Gait & posture.

[13]  Reed D. Gurchiek,et al.  Gait event detection using a thigh-worn accelerometer. , 2020, Gait & posture.

[14]  Ariel V. Dowling,et al.  Verification, analytical validation, and clinical validation (V3): the foundation of determining fit-for-purpose for Biometric Monitoring Technologies (BioMeTs) , 2020, npj Digital Medicine.

[15]  Reed D. Gurchiek,et al.  Open-Source Remote Gait Analysis: A Post-Surgery Patient Monitoring Application , 2019, Scientific Reports.

[16]  A. Pavic,et al.  Wearable inertial sensors to measure gait and posture characteristic differences in older adult fallers and non-fallers: A scoping review. , 2019, Gait & posture.

[17]  Amir Muaremi,et al.  Continuous Digital Monitoring of Walking Speed in Frail Elderly Patients: Noninterventional Validation Study and Longitudinal Clinical Trial , 2019, JMIR mHealth and uHealth.

[18]  Stefano Pastorelli,et al.  Wearable Inertial Sensors to Assess Standing Balance: A Systematic Review , 2019, Sensors.

[19]  Ryan S. McGinnis,et al.  Next Steps in Wearable Technology and Community Ambulation in Multiple Sclerosis , 2019, Current Neurology and Neuroscience Reports.

[20]  Ryan S McGinnis,et al.  Sprint Assessment Using Machine Learning and a Wearable Accelerometer. , 2019, Journal of applied biomechanics.

[21]  Ellen W. McGinnis,et al.  Rapid detection of internalizing diagnosis in young children enabled by wearable sensors and machine learning , 2019, PloS one.

[22]  Jacob J. Sosnoff,et al.  Fall Risk Prediction in Multiple Sclerosis Using Postural Sway Measures: A Machine Learning Approach , 2018, Scientific Reports.

[23]  John A. Wright,et al.  A novel adhesive biosensor system for detecting respiration, cardiac, and limb movement signals during sleep: validation with polysomnography , 2018, Nature and science of sleep.

[24]  Clint Hansen,et al.  Wearables for gait and balance assessment in the neurological ward - study design and first results of a prospective cross-sectional feasibility study with 384 inpatients , 2018, BMC Neurology.

[25]  Yike Guo,et al.  Remote Monitoring in the Home Validates Clinical Gait Measures for Multiple Sclerosis , 2018, Front. Neurol..

[26]  Jill M van der Meulen,et al.  Free-living and laboratory gait characteristics in patients with multiple sclerosis , 2018, PloS one.

[27]  Shyamal Patel,et al.  Assessment of Postural Sway in Individuals with Multiple Sclerosis Using a Novel Wearable Inertial Sensor , 2018, Digital Biomarkers.

[28]  Jordan J. Craig,et al.  The relationship between trunk and foot acceleration variability during walking shows minor changes in persons with multiple sclerosis , 2017, Clinical biomechanics.

[29]  J. V. van Dieën,et al.  Predicting falls among patients with multiple sclerosis: Comparison of patient-reported outcomes and performance-based measures of lower extremity functions. , 2017, Multiple sclerosis and related disorders.

[30]  Shyamal Patel,et al.  A machine learning approach for gait speed estimation using skin-mounted wearable sensors: From healthy controls to individuals with multiple sclerosis , 2017, PloS one.

[31]  Susan L. Kasser,et al.  Symptom variability, affect and physical activity in ambulatory persons with multiple sclerosis: Understanding patterns and time-bound relationships. , 2017, Disability and health journal.

[32]  G. Allali,et al.  Gait variability in multiple sclerosis: a better falls predictor than EDSS in patients with low disability , 2016, Journal of Neural Transmission.

[33]  Yuwen Chen,et al.  LSTM Networks for Mobile Human Activity Recognition , 2016 .

[34]  Ken Kleinman,et al.  Calculating Power by Bootstrap, with an Application to Cluster-Randomized Trials , 2014, EGEMS.

[35]  Jaap H van Dieën,et al.  Assessing physical activity in older adults: required days of trunk accelerometer measurements for reliable estimation. , 2015, Journal of aging and physical activity.

[36]  Minsoo Kang,et al.  The minimum number of days required to establish reliable physical activity estimates in children aged 2–15 years , 2014, Physiological measurement.

[37]  Robert W Motl,et al.  Validation of patient determined disease steps (PDDS) scale scores in persons with multiple sclerosis , 2013, BMC Neurology.

[38]  Fay B. Horak,et al.  Accelerometry Reveals Differences in Gait Variability Between Patients with Multiple Sclerosis and Healthy Controls , 2012, Annals of Biomedical Engineering.

[39]  Lorenzo Chiari,et al.  ISway: a sensitive, valid and reliable measure of postural control , 2012, Journal of NeuroEngineering and Rehabilitation.

[40]  A. Forsberg,et al.  Activities-Specific Balance Confidence in People with Multiple Sclerosis , 2012, Multiple sclerosis international.

[41]  Scott J Strath,et al.  How many days of monitoring predict physical activity and sedentary behaviour in older adults? , 2011, The international journal of behavioral nutrition and physical activity.

[42]  X. Montalban,et al.  Does the Modified Fatigue Impact Scale offer a more comprehensive assessment of fatigue in MS? , 2005, Multiple sclerosis.

[43]  A J Thompson,et al.  Measuring the impact of MS on walking ability , 2003, Neurology.

[44]  David R Bassett,et al.  Sources of variance in daily physical activity levels as measured by an accelerometer. , 2002, Medicine and science in sports and exercise.

[45]  B. Ainsworth,et al.  Intra-individual variation and estimates of usual physical activity. , 1999, Annals of epidemiology.

[46]  L. E. Powell,et al.  The Activities-specific Balance Confidence (ABC) Scale. , 1995, The journals of gerontology. Series A, Biological sciences and medical sciences.

[47]  H J Montoye,et al.  Variability of some objective measures of physical activity. , 1992, Medicine and science in sports and exercise.

[48]  J. Kurtzke Rating neurologic impairment in multiple sclerosis , 1983, Neurology.