Understanding the effects of pre-processing on extracted signal features from gait accelerometry signals

Abstract

Gait accelerometry is an important approach for gait assessment. Previous contributions have adopted various pre-processing approaches for gait accelerometry signals, but none have thoroughly investigated the effects of such pre-processing operations on the obtained results. Therefore, this paper investigated the influence of pre-processing operations on signal features extracted from gait accelerometry signals. These signals were collected from 35 participants aged over 65 years-old: 14 of them were healthy controls (HC), 10 had Parkinson’s disease (PD) and 11 had peripheral neuropathy (PN). The participants walked on a treadmill at preferred speed. Signal features in time, frequency and time-frequency domains were computed for both raw and pre-processed signals. The pre-processing stage consisted of applying tilt correction and de-noising operations to acquired signals. We first examined the effects of these operations separately, followed by the investigation of their joint effects. Several important observations were made based on the obtained results. First, the denoising operation alone had almost no effects in comparison to the trends observed in the raw data. Second, the tilt correction affected the reported results to a certain degree, which could lead to a better discrimination between groups. Third, the combination of the two pre-processing operations yielded similar trends as the tilt correction alone. These results indicated that while gait accelerometry is a valuable approach for the gait assessment, one has to carefully adopt any pre-processing steps as they alter the observed findings.

Quantification of upper body movements during gait in older adults and in those with Parkinson’s disease: impact of acceleration realignment methodologies

“…Similar to this study, it was shown that tilt correction can impact discrimination amongst patient groups [13]. This agreement both confirms the need to realign raw acceleration signals and additionally shows that different realignment methods can have clear implications for interpretation of results when assessing upper body variables’ ability to detect pathological movements.…”

“…The effect of the realignment technique on the sensitivity of upper body variables to discriminate pathology has previously been investigated, comparing realignment method M1 and M2, at sensor location (P), during treadmill walking and considering different variables than this investigation (HR being the only variable in common) [13]. Similar to this study, it was shown that tilt correction can impact discrimination amongst patient groups [13].…”

“…This realignment might impact gait variables and their ability to discriminate between patient groups, as shown by a previous study focusing on the pelvis movements [13]. Other upper body variables and segments, not previously investigated, might be similarly affected.…”

A Review on Accelerometry-Based Gait Analysis and Emerging Clinical Applications

“…The trunk mounted accelerometers have been used to investigate the gait patterns of chronic obstructive pulmonary disease (COPD) patients versus healthy subjects [45], create reference data for normal subjects [54], compare gaits in patients with fibromyalgia with those in controls using Locometrix system [47], assess gait parameters in children [57], investigate Gait variability and regularity of people with transtibial amputation [179], compare the CoM movement within PD patients [71], compare gait impairment of patients with neurological condition (including PD and ataxic patients) with those of healthy subjects [169], compare gait parameters in elderly people suffering from mild cognitive impairment (MCI) and Alzheimer's disease (AD) patients using Locometrix system [59], discriminate hemiplegic gait from gait in the comparison group [170], assess spatiotemporal parameters in amputee gait using Dynaport [64], investigate the difference in gait patterns for dementia patients using Dynaport [172], evaluate gait events for Hemiplegic patients [66], distinguish the step events in normal and pathological populations [175], differentiate between fit and frail elderlies [43], describe the characteristics of stroke patient gait [178], differentiate between two groups of young and elderly [184], differentiate spatio-temporal gait parameters between young and old subjects [55], differentiate between PD patients and healthy subjects [185], differentiate PD and peripheral neuropathy (PN) patients from healthy subjects [196], [199] and validate the estimated stride event versus those by motion capture system [108], investigate the effects of age and gender on gait parameters [3], investigate the effects of age, gender and height on gait parameters [198], estimate gait asymmetry in patients with hemiparetic stroke [188], investigate the relationship between spatio-temporal gait parameters with increasing age [186], monitor gait of the orthopaedic patients with symptomatic gonarthrosis aimed for total knee arthroplasty [50], and investigate the ability to differentiate between functional knee limitations and its suitability for clinical ...…”

Detecting free-living steps and walking bouts: validating an algorithm for macro gait analysis

“…Step identification: Further correction of the acceleration data for misalignment, unaccounted for when removing gravity (subtracting the mean acceleration) was performed by transforming data to a horizontal-vertical coordinate system [43,44], aligning with recommended gait data processing guidelines [45]. Once corrected, data for each bout is subjected to a continuous wavelet transform ('CWT'; a convolution of the acceleration data and analysing function) technique to identify initial contact (IC), within a predefined timed period from a previous step (0.25-2.25s [46]), and final contact (FC) events within the gait cycle [47].…”