Short inertial sensor-based gait tests reflect perceived state fatigue in multiple sclerosis

AbstractThe emergence of digital technologies such as smartphones in healthcare applications have demonstrated the possibility of developing rich, continuous, and objective measures of multiple sclerosis (MS) disability that can be administered remotely and out-of-clinic. Deep Convolutional Neural Networks (DCNN) may capture a richer representation of healthy and MS-related ambulatory characteristics from the raw smartphone-based inertial sensor data than standard feature-based methodologies. To overcome the typical limitations associated with remotely generated health data, such as low subject numbers, sparsity, and heterogeneous data, a transfer learning (TL) model from similar large open-source datasets was proposed. Our TL framework leveraged the ambulatory information learned on human activity recognition (HAR) tasks collected from wearable smartphone sensor data. It was demonstrated that fine-tuning TL DCNN HAR models towards MS disease recognition tasks outperformed previous Support Vector Machine (SVM) feature-based methods, as well as DCNN models trained end-to-end, by upwards of 8–15%. A lack of transparency of “black-box” deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications. Ensuing work therefore aimed to visualise DCNN decisions attributed by relevance heatmaps using Layer-Wise Relevance Propagation (LRP). Through the LRP framework, the patterns captured from smartphone-based inertial sensor data that were reflective of those who are healthy versus people with MS (PwMS) could begin to be established and understood. Interpretations suggested that cadence-based measures, gait speed, and ambulation-related signal perturbations were distinct characteristics that distinguished MS disability from healthy participants. Robust and interpretable outcomes, generated from high-frequency out-of-clinic assessments, could greatly augment the current in-clinic assessment picture for PwMS, to inform better disease management techniques, and enable the development of better therapeutic interventions.

Download Full-text

Thigh-Derived Inertial Sensor Metrics to Assess the Sit-to-Stand and Stand-to-Sit Transitions in the Timed Up and Go (TUG) Task for Quantifying Mobility Impairment in Multiple Sclerosis

Frontiers in Neurology ◽

10.3389/fneur.2018.00684 ◽

2018 ◽

Vol 9 ◽

Cited By ~ 13

Author(s):

Harry J. Witchel ◽

Cäcilia Oberndorfer ◽

Robert Needham ◽

Aoife Healy ◽

Carina E. I. Westling ◽

...

Keyword(s):

Multiple Sclerosis ◽

Inertial Sensor ◽

Mobility Impairment ◽

Timed Up And Go ◽

Sit To Stand

Download Full-text

Assessment of Postural Sway in Individuals with Multiple Sclerosis Using a Novel Wearable Inertial Sensor

Digital Biomarkers ◽

10.1159/000485958 ◽

2018 ◽

Vol 2 (1) ◽

pp. 1-10 ◽

Cited By ~ 19

Author(s):

Ruopeng Sun ◽

Yaejin Moon ◽

Ryan S. McGinnis ◽

Kirsten Seagers ◽

Robert W. Motl ◽

...

Keyword(s):

Multiple Sclerosis ◽

Postural Sway ◽

Inertial Sensor

Download Full-text

Gait Characteristics Harvested during a Smartphone-Based Self-Administered 2-Minute Walk Test in People with Multiple Sclerosis: Test-Retest Reliability and Minimum Detectable Change

Sensors ◽

10.3390/s20205906 ◽

2020 ◽

Vol 20 (20) ◽

pp. 5906

Author(s):

Alan K. Bourke ◽

Alf Scotland ◽

Florian Lipsmeier ◽

Christian Gossens ◽

Michael Lindemann

Keyword(s):

Multiple Sclerosis ◽

Inertial Sensor ◽

Walk Test ◽

Detectable Change ◽

Longitudinal Assessment ◽

Retest Reliability ◽

Minimum Detectable Change ◽

Gait Characteristics ◽

Test Retest Reliability ◽

Minute Walk

The measurement of gait characteristics during a self-administered 2-minute walk test (2MWT), in persons with multiple sclerosis (PwMS), using a single body-worn device, has the potential to provide high-density longitudinal information on disease progression, beyond what is currently measured in the clinician-administered 2MWT. The purpose of this study is to determine the test-retest reliability, standard error of measurement (SEM) and minimum detectable change (MDC) of features calculated on gait characteristics, harvested during a self-administered 2MWT in a home environment, in 51 PwMS and 11 healthy control (HC) subjects over 24 weeks, using a single waist-worn inertial sensor-based smartphone. Excellent, or good to excellent test-retest reliability were observed in 58 of the 92 temporal, spatial and spatiotemporal gait features in PwMS. However, these were less reliable for HCs. Low SEM% and MDC% values were observed for most of the distribution measures for all gait characteristics for PwMS and HCs. This study demonstrates the inter-session test-retest reliability and provides an indication of clinically important change estimates, for interpreting the outcomes of gait characteristics measured using a body-worn smartphone, during a self-administered 2MWT. This system thus provides a reliable measure of gait characteristics in PwMS, supporting its application for the longitudinal assessment of gait deficits in this population.

Download Full-text

What Gait Features Influence the Amount and Intensity of Physical Activity in People with Multiple Sclerosis?

10.21203/rs.2.22011/v1 ◽

2020 ◽

Author(s):

Massimiliano Pau ◽

Micaela Porta ◽

Giuseppina Pilloni ◽

Giancarlo Coghe ◽

Eleonora Cocco

Keyword(s):

Physical Activity ◽

Multiple Sclerosis ◽

Gait Speed ◽

Stride Length ◽

Inertial Sensor ◽

Rank Correlation ◽

Double Support ◽

Temporal Parameters ◽

Gait Parameters ◽

Spatio Temporal

Abstract Background: Although the mutual relationship between ambulation and Physical Activity (PA) in people with Multiple Sclerosis (pwMS) has been described in several studies, there is still a lack of detailed information about the way in which specific aspects of the gait cycle are associated with amount and intensity of PA. This study aimed to verify the existence of possible relationships among PA parameters and the spatio-temporal parameters of gait when both are instrumentally assessed.Methods: Thirty-one pwMS (17F, 14M, mean age 52.5, mean Expanded Disability Status Scale score 3.1) were requested to wear a tri-axial accelerometer 24h/day for 7 consecutive days and underwent an instrumental gait analysis, performed using an inertial sensor located on the low back, immediately before the PA assessment period. Main spatio-temporal parameters of gait (i.e. gait speed, stride length, cadence and duration of stance, swing and double support phase) were extracted by processing trunk accelerations. PA was quantified using average number of daily steps and percentage of time spent at different PA intensity, the latter calculated using cut-point sets previously validated for MS. The existence of possible relationships between PA and gait parameters was assessed using Spearman’s rank correlation coefficient rho.Results: Gait speed and stride length were the parameters with the highest number of significant correlations with PA features. In particular, they were found moderately to largely correlated with number of daily steps (rho 0.62, p<0.001), percentage of sedentary activity (rho = -0.44, p<0.001) and percentage of moderate-to-vigorous activity (rho = 0.48, p<0.001). Small to moderate significant correlations were observed between PA intensity and duration of stance, swing and double support phases.Conclusions: The data obtained suggest that the most relevant determinants associated with higher and more intense levels of physical activity in free-living conditions are gait speed and stride length.The simultaneous quantitative assessment of gait parameters and PA levels might represent a useful support for physical therapists in tailoring optimized rehabilitative and training interventions.

Download Full-text