Differentiation of gait using principal component analysis and application for Parkinson’s disease monitoring

Abstract

Parkinson’s disease (PD) is the second most common neurodegenerative disease. The diagnosis of PD can be difficult, especially in its early stage since there are no existing specific biomarkers. Most biomechanical data characterizing human movement is shown as time series or temporal waveforms representing different joint measures. Principal component analysis (PCA) can be used as a tool to identify differences in gait between healthy persons and those diagnosed with PD. The purpose of this study is to compare hip and knee kinematics during walking in PD group and control (CO) group using PCA, and to identify the specific PCA variables that can be used for differentiating Parkinsonian gait from normal gait. The subjects were divided into two groups: PD group n = 15, control group n = 12. Each subject performed a gait task and kinematics of limbs was measured using nine degrees of freedom inertial measurement unit (IMU). PCA was performed on the angular velocity of right and left side hip and knee joints in the sagittal plane of the gait cycle. Different numbers of principal components (PC) are needed to describe important information from hip (PC – 3) and knee (PC – 4) joints in sagittal plane. Statistically significant differences were found between PD and CO groups: right hip PC3 (p=0.0026); left hip PC3 (p=0.0262); right knee PC3 (p=0.0286). The PCA applied in this paper identified differences in gait features between PD and CO groups. Identification of these differences between PD and CO groups could clarify PD progress.