Detection of postural sway abnormalities by wireless inertial sensors in minimally disabled patients with multiple sclerosis: a case-control study

Abstract

Background: Common clinical neurological exams can be insensitive to balance and mobility impairment at the early stages of multiple sclerosis (MS) and may not correspond with patient reports. Instrumented measurement of standing postural sway with inertial motion sensors may provide sensitive measures of balance impairment and better correspond with patient reports.

Methods: While wearing wireless inertial sensors, 20 subjects with MS - Expanded Disability Status Scale of less than 3.0 and a Timed 25 Foot Walk of 5 sec or less - and 20 age- and sex-matched control subjects stood with eyes open and eyes closed on a foam surface. Forty-six outcome measures of postural sway were derived. A stepwise logistic regression model determined which measures of instrumented sway provide independent predictors of group status. Subjects with MS also completed the Activities-Specific Balance Confidence (ABC) scale and the 12-Item MS Walking Scale (MSWS-12) as measures of subject-reported balance and mobility impairment.

Results: The regression model identified medio-lateral sway path length and medio-lateral range of sway acceleration amplitude, each in the eyes-open condition, as the only two significant independent predictors to differentiate subjects with MS from those without MS (model chi-squared = 34.55, p < 0.0001): accuracy = 87.5 %, positive likelihood ratio = 6 (2.09-17.21), negative likelihood ratio = 0.12 (0.03-0.44). Range of sway acceleration amplitude significantly correlated with both ABC (Spearman's r = -0.567, p = 0.009) and MSWS-12 scores (Spearman's r = -0.590, p = 0.006).

Conclusions: Postural sway abnormalities in subjects with MS who are minimally disabled were detected using wireless inertial sensors and may signify a superior sensitivity to identify balance impairment prior to developing clinically evident disability or impaired gait speed. Further study is needed to confirm the clinical significance and predictive value of these objectively identified balance impairments.

Fig. 1

Scatter plots demonstrating the strength of Spearman’s correlations of subject-reported measures (ABC scale and MSWS-12) versus instrumented sway measures found to differentiate between people with and without MS (medial-lateral (ML) range of acceleration amplitude and sway path length in the eyes-open (EO) condition) as well as clinical measures of impairment and disability (Brief-BESTest, EDSS, and T25FW)