The Novel Quantitative Technique for Assessment of Gait Symmetry Using Advanced Statistical Learning Algorithm

Abstract

The accurate identification of gait asymmetry is very beneficial to the assessment of at-risk gait in the clinical applications. This paper investigated the application of classification method based on statistical learning algorithm to quantify gait symmetry based on the assumption that the degree of intrinsic change in dynamical system of gait is associated with the different statistical distributions between gait variables from left-right side of lower limbs; that is, the discrimination of small difference of similarity between lower limbs is considered the reorganization of their different probability distribution. The kinetic gait data of 60 participants were recorded using a strain gauge force platform during normal walking. The classification method is designed based on advanced statistical learning algorithm such as support vector machine algorithm for binary classification and is adopted to quantitatively evaluate gait symmetry. The experiment results showed that the proposed method could capture more intrinsic dynamic information hidden in gait variables and recognize the right-left gait patterns with superior generalization performance. Moreover, our proposed techniques could identify the small significant difference between lower limbs when compared to the traditional symmetry index method for gait. The proposed algorithm would become an effective tool for early identification of the elderly gait asymmetry in the clinical diagnosis.

Observational Gait Assessment Scales in Patients with Walking Disorders: Systematic Review

“…The authors highlight the scale HGAF [31], which studied symmetry from the spatial and temporal point of view, with the evaluation of the symmetry of step length and step period. Its evaluation is considered relevant as a symmetrical gait is necessary for the development of a biomechanically correct gait pattern [41].…”

Latest Research Trends in Gait Analysis Using Wearable Sensors and Machine Learning: A Systematic Review

“…Wu et al [86]: This paper aims the accurate identification of the gait. Each participant performs a 10 m walk carrying a force plate at the foot for data acquisition.…”

“…Medical Fitness Security Wu et al [86] Chen et al [89] Zebin et al [92] Ordóñez et al [96] Neverova et al [101] Zhen et al [104] Chen et al [105] Camps et al [108] Gharani et al [109] McGinnis et al [111] Zhao et al [116] Murad et al [119] Dehzangi et al [128] Steffan et al [130] Almaslukh et al [131] Cheng et al [133] Zdravevski et al [136] Abdulhay et al [137] Gadaleta et al [139] Xia et al [142] Asuncion et al [144] Huang et al [146] Aicha et al [147] Rescio et al [150] Hsieh et al [151] Putra et al [153] Ghazali et al [154] Rastegari et al [155] Gurchiek et al [159] Zhang et al [162] Abujrida et al [165] Kim et al [167] Wang et al [168]…”

“…Papers Percentage Authentication [139], [144], [146], [96], [116], [128], [101] 15 % BAC Estimation [109] 2% Disease Diagnosis [137], [155], [159], [165], [111], [146], [86], [133] 18%…”

“…Fall Detection [104], [153] 5% Fall Prevention [147], [150], [151], [130] 9% Fitness Monitoring [162], [136] 5% FoG Detection [142], [108], [167] 7% Gait Classification [162], [116] 5% Gait Improvement [86], [168], [136] 7% HAR [92], [96], [119], [150], [131], [89], [105], [133] 18% Injury Avoidance [159], [ As mentioned in Section III, these applications are subdivided into specific groups such as HAR, disease diagnosis, gait classification, and injury avoidance. TABLE 6 lists the publications according to their applicability and percentage of papers.…”