Measurement of Human Walking Movements by Using a Mobile Health App: Motion Sensor Data Analysis

Mobile Health App for Adolescents: Motion Sensor Data and Deep Learning Technique to Examine the Relationship between Obesity and Walking Patterns

With the prevalence of obesity in adolescents, and its long-term influence on their overall health, there is a large body of research exploring better ways to reduce the rate of obesity. A traditional way of maintaining an adequate body mass index (BMI), calculated by measuring the weight and height of an individual, is no longer enough, and we are in need of a better health care tool. Therefore, the current research proposes an easier method that offers instant and real-time feedback to the users from the data collected from the motion sensors of a smartphone. The study utilized the mHealth application to identify participants presenting the walking movements of the high BMI group. Using the feedforward deep learning models and convolutional neural network models, the study was able to distinguish the walking movements between nonobese and obese groups, at a rate of 90.5%. The research highlights the potential use of smartphones and suggests the mHealth application as a way to monitor individual health.

Gait and Axial Spondyloarthritis: Comparative Gait Analysis Study Using Foot-Worn Inertial Sensors

Background

Axial spondyloarthritis (axSpA) can lead to spinal mobility restrictions associated with restricted lower limb ranges of motion, thoracic kyphosis, spinopelvic ankylosis, or decrease in muscle strength. It is well known that these factors can have consequences on spatiotemporal gait parameters during walking. However, no study has assessed spatiotemporal gait parameters in patients with axSpA. Divergent results have been obtained in the studies assessing spatiotemporal gait parameters in ankylosing spondylitis, a subgroup of axSpA, which could be partly explained by self-reported pain intensity scores at time of assessment. Inertial measurement units (IMUs) are increasingly popular and may facilitate gait assessment in clinical practice.

Objective

This study compared spatiotemporal gait parameters assessed with foot-worn IMUs in patients with axSpA and matched healthy individuals without and with pain intensity score as a covariate.

Methods

A total of 30 patients with axSpA and 30 age- and sex-matched healthy controls performed a 10-m walk test at comfortable speed. Various spatiotemporal gait parameters were computed from foot-worn inertial sensors including gait speed in ms^–1 (mean walking velocity), cadence in steps/minute (number of steps in a minute), stride length in m (distance between 2 consecutive footprints of the same foot on the ground), swing time in percentage (portion of the cycle during which the foot is in the air), stance time in percentage (portion of the cycle during which part of the foot touches the ground), and double support time in percentage (portion of the cycle where both feet touch the ground).

Results

Age, height, and weight were not significantly different between groups. Self-reported pain intensity was significantly higher in patients with axSpA than healthy controls (P<.001). Independent sample t tests indicated that patients with axSpA presented lower gait speed (P<.001) and cadence (P=.004), shorter stride length (P<.001) and swing time (P<.001), and longer double support time (P<.001) and stance time (P<.001) than healthy controls. When using pain intensity as a covariate, spatiotemporal gait parameters were still significant with patients with axSpA exhibiting lower gait speed (P<.001), shorter stride length (P=.001) and swing time (P<.001), and longer double support time (P<.001) and stance time (P<.001) than matched healthy controls. Interestingly, there were no longer statistically significant between-group differences observed for the cadence (P=.17).

Conclusions

Gait was significantly altered in patients with axSpA with reduced speed, cadence, stride length, and swing time and increased double support and stance time. Taken together, these changes in spatiotemporal gait parameters could be interpreted as the adoption of a so-called cautious gait pattern in patients with axSpA. Among factors that may influence gait in patients with axSpA, patient self-reported pain intensity could play a role. Finally, IMUs allowed computation of spatiotemporal gait parameters and are usable to assess gait in patients with axSpA in clinical routine.

Trial Registration

ClinicalTrials.gov NCT03761212; https://clinicaltrials.gov/ct2/show/NCT03761212

International Registered Report Identifier (IRRID)

RR2-10.1007/s00296-019-04396-4

Fusing Ambient and Mobile Sensor Features Into a Behaviorome for Predicting Clinical Health Scores

Advances in machine learning and low-cost, ubiquitous sensors offer a practical method for understanding the predictive relationship between behavior and health. In this study, we analyze this relationship by building a behaviorome, or set of digital behavior markers, from a fusion of data collected from ambient and wearable sensors. We then use the behaviorome to predict clinical scores for a sample of n = 21 participants based on continuous data collected from smart homes and smartwatches and automatically labeled with corresponding activity and location types. To further investigate the relationship between domains, including participant demographics, self-report and external observation-based health scores, and behavior markers, we propose a joint inference technique that improves predictive performance for these types of high-dimensional spaces. For our participant sample, we observe correlations ranging from small to large for the clinical scores. We also observe an improvement in predictive performance when multiple sensor modalities are used and when joint inference is employed.