Development of a Gait Feature–Based Model for Classifying Cognitive Disorders Using a Single Wearable Inertial Sensor

Abstract

Background and Objectives:Gait changes are potential markers of cognitive disorders (CD). We developed a model for classifying older adults with CD from those with normal cognition using gait speed and variability captured from a wearable inertia sensor and compared its diagnostic performance for CD with that of the model using the Mini-Mental State Examination (MMSE).Methods:We enrolled community-dwelling older adults with normal gait from the Korean Longitudinal Study on Cognitive Aging and Dementia and measured their gait features using a wearable inertia sensor placed at the center of body mass while they walked on a 14-m long walkway thrice at comfortable paces. We randomly split our entire dataset into the development (80%) and validation (20%) datasets. We developed a model for classifying CD using logistic regression analysis from the development dataset and validated it in the validation dataset. In both datasets, we compared the diagnostic performance of the model with that using the MMSE. We estimated optimal cutoff score of our model using receiver operator characteristics analysis.Results:In total, 595 participants were enrolled, 101 of them had CD. Our model included both gait speed and temporal gait variability and exhibited good diagnostic performance for classifying CD from normal cognition in both the development (area under the receiver operator characteristic curve [AUC] = 0.788, 95% confidence interval [CI] = 0.748–0.823, p < 0.001) and validation datasets (AUC = 0.811, 95% CI = 0.729–0.877, p < 0.001). Our model showed comparable diagnostic performance for CD to that of the model using the MMSE in both the development (difference in AUC = 0.026, standard error [SE] = 0.043, z statistic = 0.610, p = 0.542) and validation datasets (difference in AUC = 0.070, SE = 0.073, z statistic = 0.956, p = 0.330). The optimal cutoff score of the gait-based model was > -1.56.Discussion:Our gait-based model using a wearable inertia sensor may be a promising diagnostic marker of CD in older adults.Classification of Evidence:This study provides Class III evidence that gait analysis can accurately distinguish cognitive disorders from healthy controls in older adults.

Evaluation of a multimodal diagnostic algorithm for prediction of cognitive impairment in elderly patients with dizziness

“…The prediction models from this study performed comparably and even superior to other previously reported algorithms in the risk prediction of cognitive impairment, although differences in patient collectives limit a direct comparison. A gait feature-based model for detecting cognitive dysfunction in the elderly utilizing a single wearable inertia sensor yielded an AUC of 0.73–0.88 [ 37 ]. A standardized evaluation of multiple cognition prediction algorithms based on imaging data showed that the best AUC achieved was about 0.79 [ 38 ].…”

Spatiotemporal gait parameter fluctuations in older adults affected by mild cognitive impairment: comparisons among three cognitive dual-task tests

“…Up to date, multiple lines of studies have confirmed that walking is a learned behavior rather than an automatic process that requires the coordination of cognitive function [ 11 , 12 ]. Gait performance is associated with individual capacities of executive function and working memory, especially in the dual-task tests [ 13 – 15 ].…”

Measuring Gait to Monitor Cognitive Function in Older Adults

“…The unique approach by Park et al 5 to use a wearable IMU sensor to quantify gait performance is particularly intriguing because it enables low-cost measurement of parameters beyond gait speed. While speed can be relatively easily captured with a stopwatch, other walking parameters such as variability, cadence, and asymmetry require more sensitive equipment.…”

“…Third, remote gait assessments enabled by IMU sensors will likely increase the accessibility of gait assessment for older adults who live far away from clinical or research facilities and for those individuals who have difficulty organizing or using transportation to these facilities. It will thus be exciting to learn whether the results published by Park et al 5 hold when using IMU data acquired from partially or fully unsupervised gait assessments conducted from older adults in the comfort of their home setting.…”