Real-World Gait Detection Using a Wrist-Worn Inertial Sensor: Validation Study

Abstract

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

Objective: The aim of this study was to validate gait sequence (GS) 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.

Methods: Participants with Parkinson disease, multiple sclerosis, proximal femoral fracture (hip fracture recovery), chronic obstructive pulmonary disease, and congestive heart failure and healthy older adults (N=83) were monitored for 2.5 hours in the real-world using inertial sensors on the wrist, lower back, and feet including pressure insoles and infrared distance sensors as reference. In total, 10 algorithms for wrist-based gait detection were validated against a multisensor reference system and compared to gait detection performance using lower back-worn inertial sensors.

Results: The best-performing GS detection algorithm for the wrist showed a mean (per disease group) sensitivity ranging between 0.55 (SD 0.29) and 0.81 (SD 0.09) and a mean (per disease group) specificity ranging between 0.95 (SD 0.06) and 0.98 (SD 0.02). The mean relative absolute error of estimated walking time ranged between 8.9% (SD 7.1%) and 32.7% (SD 19.2%) 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 (SD 0.12) and 0.91 (SD 0.04), mean specificity between 0.96 (SD 0.03) and 0.99 (SD 0.01), and a mean relative absolute error of estimated walking time between 6.3% (SD 5.4%) and 23.5% (SD 13%). Performance was lower in disease groups with major gait impairments (eg, patients recovering from hip fracture) and for patients using bilateral walking aids.

Conclusions: Algorithms applied to the wrist position can detect GSs with high performance in real-world environments. Those periods of interest in 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.

Trial registration: ISRCTN Registry 12246987; https://www.isrctn.com/ISRCTN12246987.

International registered report identifier (irrid): RR2-10.1136/bmjopen-2021-050785.

Keywords: Mobilise-D; accelerometer; digital health; digital mobility outcomes; inertial measurement unit; validation; walking; wearable sensor.

Figure 1

Performance of assessed algorithms based on a disease group level (n=6). Individual data points are highlighted for each disease group as an overlay. The names of lower back algorithms are given as defined previously [11] and referred to in Table 1. Boxes indicate lower and upper quartiles; the whiskers correspond to 1.5 IQR. Colors indicate the algorithm version: orange indicates the default algorithm version without optimized parameters, and blue indicates the optimized algorithm (parameter tuning based on the optimization data set). In the “wrist” subplot, shapes indicate the disease group to visualize algorithm performance for each group. CHF: congestive heart failure; COPD: chronic obstructive pulmonary disease; GSD: gait sequence detection; HA: healthy older adults; MS: multiple sclerosis; PD: Parkinson disease; PFF: proximal femoral fracture (hip fracture recovery).

Figure 2

Sensitivity (left) and specificity (right) for the best-performing wrist algorithms (performance index higher than 0.7 for most disease groups except proximal femoral fracture) based on a participant level (N=83). Colors indicate the algorithm version: orange indicates the default algorithm version without optimized parameters, and blue indicates the optimized algorithm with parameter tuning based on the optimization data set. GSD: gait sequence detection.

Figure 3

Relative errors of the estimated number of GSs (left) and of the estimated gait duration (right) per 2.5-hour recording based on a participant level (N=83). The dashed red line represents an error of 0 (optimal result). Negative relative errors indicate that fewer GS were detected or the total GS duration was lower than estimated by the reference system. The figure includes the best-performing algorithms (performance index higher than 0.7 for most disease groups except proximal femoral fracture). Colors indicate the algorithm version: orange indicates the default algorithm version without optimized parameters, and blue indicates the optimized algorithm with parameter tuning based on the optimization data set. GS: gait sequence; GSD: gait sequence detection.

Figure 4

Effect of walking aids on sensitivity for the algorithm Brand (2022) [17]. Each data point represents 1 participant (N=83), the color indicates the type of walking aid. CHF: congestive heart failure; COPD: chronic obstructive pulmonary disease; HA: healthy older adults; MS: multiple sclerosis; PD: Parkinson disease; PFF: proximal femoral fracture (hip fracture recovery).