Vertical ground reaction force marker for Parkinson’s disease

Abstract

Parkinson’s disease (PD) patients regularly exhibit abnormal gait patterns. Automated differentiation of abnormal gait from normal gait can serve as a potential tool for early diagnosis as well as monitoring the effect of PD treatment. The aim of current study is to differentiate PD patients from healthy controls, on the basis of features derived from plantar vertical ground reaction force (VGRF) data during walking at normal pace. The current work presents a comprehensive study highlighting the efficacy of different machine learning classifiers towards devising an accurate prediction system. Selection of meaningful feature based on sequential forward feature selection, the swing time, stride time variability, and center of pressure features facilitated successful classification of control and PD gaits. Support Vector Machine (SVM), K-nearest neighbor (KNN), random forest, and decision trees classifiers were used to build the prediction model. We found that SVM with cubic kernel outperformed other classifiers with an accuracy of 93.6%, the sensitivity of 93.1%, and specificity of 94.1%. In comparison to other studies, utilizing same dataset, our designed prediction system improved the classification performance by approximately 10%. The results of the current study underscore the ability of the VGRF data obtained non-invasively from wearable devices, in combination with a SVM classifier trained on meticulously selected features, as a tool for diagnosis of PD and monitoring effectiveness of therapy post pathology.

Comparison of Walking Protocols and Gait Assessment Systems for Machine Learning-Based Classification of Parkinson’s Disease

“…In order to maximize information for disease classification, analysis of multiple characteristics can be enhanced using machine learning (ML) [6]. The most widely used ML models for PD classification are the support vector machine (SVM) and random forest (RF) [13][14][15][16][17][18][19]. Classification accuracy however is inconsistent across studies which may be largely due to methodological differences (e.g., testing protocols, gait assessment systems and normalization of participants' data) [13,14,17].…”

Feedback-Based Gait Identification Using Deep Neural Network Classification

“…The major three types of disorders are shown in the Figure 1 [18,19] • Parkinson gait: The persons with Parkinson's disease (PD) is called as Parkinson gait often called as abnormal gait [2], the classic stooped occurrence while walking, neck drop between trunk and limbs while walking, with flexion of the hips and knees while walking, and a huge gap between rounding of the shoulders while walking [9]. • Neuropathic Gait: The abnormality of neuropathic deformity seen with foot drop, swinging the leg when step forwarding, this is also due to the weakness of the person with leg stiff and foot drop due to flexion of the hip [10].…”

“…Ahmed et.al [6,7] proposed for abnormal gait detection technique the joining the human body parts by suing Fourier transformation method. Faezeh et.al [8] proposed a different approach for a model-based approach for analysing the leg and arm movements and shoulders in human gait recognition, this problem is not solve the neuropathic gait [9,18]. A model is constructed using active contour models (ACM) this model is incorporated with a feedback-based approach [10,18].…”

“…The lean angle and ramp angle are two angles to useful to find the abnormal gait detection [13]. Extract the features of video sequence has been considered to check training features with query features [9]. The lean and ramp angle calculates the abnormal walking position of human [10], DNN based classification algorithms applied in lean angle and ramp angle dataset [11].…”

“…The lean and ramp angle is most required to observe the walking position and identify the abnormality of a human [5,6,7,8], it depends on the "actual position of walking" the observation towards the foot, and also depends on the strength of the person stability to walk [8]. The difference of angle between the two legs with a heel wedge under the liner, the people with excessive range of motion while walking with a boot of lower ramp angle is standing more upright [9]. Based on the human walking style, and pattern of leg movements derived from the kinematics, we observed the video sequence, abnormal person, it identifies the abnormal person by using gait cycles.…”