Prediction of Disorientation by Accelerometric and Gait Features in Young and Older Adults Navigating in a Virtually Enriched Environment

Abstract

Objective: To determine whether gait and accelerometric features can predict disorientation events in young and older adults.

Methods: Cognitively healthy younger (18-40 years, n = 25) and older (60-85 years, n = 28) participants navigated on a treadmill through a virtual representation of the city of Rostock featured within the Gait Real-Time Analysis Interactive Lab (GRAIL) system. We conducted Bayesian Poisson regression to determine the association of navigation performance with domain-specific cognitive functions. We determined associations of gait and accelerometric features with disorientation events in real-time data using Bayesian generalized mixed effect models. The accuracy of gait and accelerometric features to predict disorientation events was determined using cross-validated support vector machines (SVM) and Hidden Markov models (HMM).

Results: Bayesian analysis revealed strong evidence for the effect of gait and accelerometric features on disorientation. The evidence supported a relationship between executive functions but not visuospatial abilities and perspective taking with navigation performance. Despite these effects, the cross-validated percentage of correctly assigned instances of disorientation was only 72% in the SVM and 63% in the HMM analysis using gait and accelerometric features as predictors.

Conclusion: Disorientation is reflected in spatiotemporal gait features and the accelerometric signal as a potentially more easily accessible surrogate for gait features. At the same time, such measurements probably need to be enriched with other parameters to be sufficiently accurate for individual prediction of disorientation events.

Keywords: actimetry; aging; executive function; gait; navigation; virtual reality; visuo-spatial abilities.

FIGURE 1

Aggregated disorientation events, accelerometry, and walking speed by age group by condition. Disorientation events (upper row), ankle worn accelerometric signal (middle row), and walking speed mean (lower row) according to age group and condition [control (C) vs. experimental (E)]. Bars show mean and 95% credibility intervals.

FIGURE 2

Real-time data, ankle worn accelerometry. Bayesian mixed-effect logistic regression of disorientation events on ankle worn accelerometric signal (main effect, upper left and interaction effect with condition, upper right), condition (experimental or control, middle left), age group (middle right), and gender (lower row). The graphs feature mean effects and 95% credibility intervals.

FIGURE 3

Real-time data, walking speed. Bayesian mixed-effect logistic regression of disorientation events on mean walking speed (main effect, upper left and interaction effect with condition, upper right), condition (experimental or control, middle left), age group (middle right), and gender (lower row). The graphs feature mean effects and 95% credibility intervals.

FIGURE 4

Distribution of orientation status across features. Three-dimensional representation of the distribution of orientation status (oriented – black beads, disoriented – red beads) across ankle and chest-worn accelerometric signal and walking speed mean.

FIGURE 5

Hidden Markov model generated states and observed orientation states. (A) Time series of states within 5,000 s. The upper row plots the orientation states generated from the Hidden Markov model during the first 500 time segments (= 5,000 s, pooled across participants) with 1 = oriented, 2 = disoriented; the lower row plots the observed orientation states from the same time segments. (B) Association between number of disorientation events and accuracy of HMM generated states. This graph plots the accuracy of the HMM generated states relative to the observed states per participant (y-axis) vs. the number of disorientation events per participant (x-axis).