New insights into the plantar pressure correlates of walking speed using pedobarographic statistical parametric mapping (pSPM)

Abstract

This study investigates the relation between walking speed and the distribution of peak plantar pressure and compares a traditional ten-region subsampling (10RS) technique with a new technique: pedobarographic statistical parametric mapping (pSPM). Adapted from cerebral fMRI methodology, pSPM is a digital image processing technique that registers foot pressure images such that homologous structures optimally overlap, thereby enabling statistical tests to be conducted at the pixel level. Following previous experimental protocols, we collected pedobarographic records from 10 subjects walking at three different speeds: slow, normal, and fast. Walking speed was recorded and correlated with the peak pressures extracted from the 10 regions, and subsequently with the peak pixel data extracted after pSPM preprocessing. Both methods revealed significant positive correlation between peak plantar pressure and walking speed over the rearfoot and distal forefoot after Bonferroni correction for multiple comparisons. The 10RS analysis found positive correlation in the midfoot and medial proximal forefoot, but the pixel data exhibited significant negative correlation throughout these regions (p<5×10⁻⁵). Comparing the statistical maps from the two approaches shows that subsampling may conflate pressure differences evident in pixel-level data, obscuring or even reversing statistical trends. The negative correlation observed in the midfoot implies reduced longitudinal arch collapse with higher walking speeds. We infer that this results from pre- or early-stance phase muscle activity and speculate that preferred walking speed reflects, in part, a balance between the energy required to tighten the longitudinal arch and the apparent propulsive benefits of the stiffened arch.

Introduction

The human foot is a complex structure that constitutes the primary mechanical interface between our bodies and the environment. As walking speed increases, the foot must transmit increasing propulsive impulsive to the ground, the mechanics of which are not fully understood (Zatsiorsky et al., 1994; Alexander, 2004; Erdemir et al., 2004; Erdemir and Piazza, 2004). Previous studies have demonstrated that peak pressures are positively correlated with walking speed across the plantar surface of the foot (Rosenbaum et al., 1994; Zhu et al., 1995; Drerup et al., 2001; Burnfield et al., 2004; Segal et al., 2004; Taylor et al., 2004; Warren et al., 2004; Yang et al., 2005). The only exception is that, in some of these studies, a peak pressure decrease was observed in the lateral midfoot as a function of walking speed, but this trend either failed to reach significance (Drerup et al., 2001; Taylor et al., 2004) or was not explicitly discussed (Rosenbaum et al., 1994; Segal et al., 2004).

We believe that a decrease in midfoot peak pressure is non-trivial because it implies decreased longitudinal arch collapse modulated by pre-stance or early stance muscular activity. If the arch is not loaded in this manner, the higher vertical ground reaction forces associated with faster walking speeds (Keller et al., 1996) would cause the arch to collapse to a greater extent. Decreased longitudinal arch collapse would thus imply that there is some propulsive benefit, direct or indirect, to active arch collapse prevention. To our knowledge this issue has not been explicitly addressed in the biomechanics literature.

All previous studies of the plantar pressure correlates of walking speed have employed traditional subsampling methodology. ‘Subsampling’ refers to spatial data reduction; the foot is discretized into on the order of 10 regions (Rosenbaum and Becker, 1997), and one metric is extracted per region (usually the maximal pressure). While effectively reducing the large data set to a manageable size, the main problem with subsampling is that it ignores most of the data. An adult foot can contact over 500 sensors when using currently available commercial hardware, so subsampling can entail an approximately 50-fold decrease in spatial information. Disposing of so much data could be problematic if there is substantial intra-region variation.

Here we employ the established cerebral fMRI methodology: ‘Statistical parametric mapping’ (SPM) (Friston et al., 1995) to analyze pedobarographic images collected for a range of walking speeds. The technique first registers plantar pressure images such that homologous structures optimally overlap, and then conducts pixel-level statistical tests using a mass univariate approach. The result is a continuous statistical map that can be viewed in the context of the original foot pressure images.

The purposes of the current study were: (1) to use SPM to clarify the midfoot pressure correlates of walking speed, and (2) to corroborate the results with those obtained using a traditional ten-region subsampling (10RS) technique.