Feature selection of stabilometric parameters based on principal component analysis

Abstract

This study addresses the challenge of identifying the features of the Centre of pressure (COP) trajectory that are most sensitive to postural performance, with the aim of avoiding redundancy and allowing a straightforward interpretation of the results. Postural sway in 50 young, healthy subjects was measured by a force platform. Thirty-seven stabilometric parameters were computed from the one-dimensional and two-dimensional COP time series. After normalisation to the relevant biomechanical factors, by means of multiple regression models, a feature selection process was performed based on principal component analysis. Results suggest that COP two-dimensional time series can be primarily characterised by four parameters, describing the size of the COP path over the support surface; the principal sway direction; and the shape and bandwidth of the power spectral density plot. COP one-dimensional time series (antero-posterior (AP) and medio-lateral (ML)) can be characterised by six parameters describing COP dispersion along the AP direction; mean velocity along the ML and AP directions; the contrast between ML and AP regulatory activity; and two parameters describing the spectral characteristics of the COP along the AP direction. On the basis of the results obtained, some guidelines are suggested for the choice of stabilometric parameters to use, with the aim of promoting standardisation in quantitative posturography.

Influence of prolonged wearing of unstable shoes on upright standing postural control

“…The results obtained confirm our hypothesis that prolonged wearing of unstable shoes increases postural control performance, demonstrated by a decrease of the most representative CoP displacement parameters (Collins & De Luca, 1993;Maurer & Peterka, 2005;Pavol, 2005;Rocchi, et al, 2004), and decreased postural control system error, demonstrated by the adaptation of the RM and TR components (Zatsiorsky & Duarte, 2000), more marked in the unstable shoe condition. However, our results failed in demonstrating a decreased co-activation command and increased reciprocal activation command as a training effect.…”

“…A 95% confidence ellipse for each trial was estimated to enclose approximately 95% of the CoP motion points in the 2D domain. These parameters were selected as they were demonstrated to be sensitive to postural performance and efficiency (Rocchi et al, 2004).…”

The contribution of postural balance analysis in older adult fallers: A narrative review

“…Particular attention was given to weight, height, base of support area, feet-opening angle and maximum foot width during between-subject comparisons. In 2004 (Rocchi et al 2004) to promote standardization in quantitative posturography, the same authors suggested that if no normalization is undertaken, it is essential to constrain the foot position in such a way as to reduce inter-subject variability of base of support measurements. Furthermore, they underlined the need to align properly the reference frame of the subject with the reference frame of the platform.…”

Objective and subjective measures reflect different aspects of balance in multiple sclerosis

“…Thus, the constructs differ between these measures. The center of pressure variables used in this study reflect both the balance control processes necessary to maintain stance and movement of the entire body's center of mass [14]. Previous studies have shown that even when standing with eyes open, PwMS exhibit a larger center of pressure sway area [4,30], greater sway velocity [3,30], and greater RMS of sway than nondisabled controls [31][32].…”

“…For the present study, we used the composite score from the Sensory Organization Test (SOT) as generated by commercially available posturography devices and we extracted the raw center of pressure signal from each trial of the SOT and calculated root mean square (RMS), range, total sway area, and mean velocity for the resultant sway path. Analyses of these center of pressure variables have been shown to most effectively characterize different aspects of postural sway [14][15]. For example, sway area reflects the effectiveness of, or the stability achieved by, the postural control system and mean velocity reflects the amount of regulatory activity associated with this level of stability [15][16].…”