Abstract
Wearable sensors can provide detailed information on human movement but the clinical impact of this information remains limited. We propose a machine learning approach, using wearable sensor data, to identify subject-specific changes in gait patterns related to improvements in clinical outcomes. Eight patients with knee osteoarthritis (OA) completed two gait trials before and one following an exercise intervention. Wearable sensor data (e.g., 3-dimensional (3D) linear accelerations) were collected from a sensor located near the lower back, lateral thigh and lateral shank during level treadmill walking at a preferred speed. Wearable sensor data from the 2 pre-intervention gait trials were used to define each individual’s typical movement pattern using a one-class support vector machine (OCSVM). The percentage of strides defined as outliers, based on the pre-intervention gait data and the OCSVM, were used to define the overall change in an individual’s movement pattern. The correlation between the change in movement patterns following the intervention (i.e., percentage of outliers) and improvement in self-reported clinical outcomes (e.g., pain and function) was assessed using a Spearman rank correlation. The number of outliers observed post-intervention exhibited a large association (ρ = 0.78) with improvements in self-reported clinical outcomes. These findings demonstrate a proof-of-concept and a novel methodological approach for integrating machine learning and wearable sensor data. This approach provides an objective and evidence-informed way to understand clinically important changes in human movement patterns in response to exercise therapy.
Highlights
As wearable sensors become more and more ubiquitous in today’s world, so does their use in human movement analysis
The number of outliers observed post-intervention exhibited a large association (ρ = 0.78) with improvements in self-reported clinical outcomes. These findings demonstrate a proof-of-concept and a novel methodological approach for integrating machine learning and wearable sensor data
The average percentage of gait cycles defined as outliers in the 20% cross-validated baseline data and regularization parameters (ν) selected the single-subject boundary thresholds wereregularization found to range post-intervention gait trial data were 0.5for and 17.7 (17.1)%, respectively
Summary
As wearable sensors become more and more ubiquitous in today’s world, so does their use in human movement analysis Given their size, affordability and ease of use, wearable inertial sensors can provide a clinically accessible alternative to more expensive conventional three-dimensional (3D). A fundamental problem in collecting data from multiple sensors over long periods of time is that datasets quickly become exceedingly large, complex, and, most importantly, clinically uninterpretable. To counter this problem, many clinical investigations have examined simple wearable sensor outputs such as gait speed, step times and other discrete variables [3,4,5]. There remains a vast amount of data being created by today’s wearable sensors that goes unanalyzed and may itself hold the key to answering important clinical
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
