Real-world gait detection using a wrist-worn inertial sensor: validation and comparison with the lower-back position. (Preprint)

Abstract

Wrist worn inertial sensors are used in digital health for evaluating mobility in real-world environments. Preceding the estimation of spatio-temporal gait parameters within continuous 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 various other sensor positions, a comparative validation of algorithms applied to the wrist position on a real-world data set across different disease populations is still 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.

The main aim of this study was to validate gait sequence 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.

Participants with Parkinson's disease, multiple sclerosis, proximal femoral fracture (hip fracture recovery), chronic obstructive pulmonary disease, congestive heart failure, and healthy elderly (n = 83 in total) were monitored for 2.5 hours in the real-world, using wearable inertial sensors on the wrist, lower-back and feet including pressure insoles and infrared distance sensors as reference. Ten algorithms for wrist-based gait detection were validated against a multi-sensor reference system and compared to gait detection performance using lower-back worn inertial sensors.

The best performing gait sequence detection algorithm for the wrist position showed a mean (per disease group) sensitivity ranging between 0.55 and 0.81 and mean (per disease group) specificity ranging between 0.95 and 0.98. The mean relative absolute error of estimated walking time ranged between 9 % and 33 % 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 and 0.91, mean specificity between 0.96 and 0.99, and a mean relative absolute error of estimated walking time between 6 % and 24 %. Performance was lower in disease groups with major gait impairments (e.g., patients recovering from hip fracture), as well as for patients using bilateral walking aids.

Selected algorithms applied to the wrist position can detect gait sequences with high performance in real-world environments. Those periods of interest in long 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.

https://doi.org/10.1186/ISRCTN12246987

RR2-10.1136/bmjopen-2021-050785