Spatiotemporal Ground Reaction Force Analysis using Convolutional Neural Networks to Analyze Parkinsonian Gait

TL;DR

This paper presents a convolutional neural network approach to analyze spatiotemporal ground reaction forces for early Parkinson's disease diagnosis, achieving 97% accuracy in distinguishing gait patterns.

Contribution

It introduces a novel CNN-based method for analyzing GRF data to identify and assess Parkinsonian gait severity.

Findings

Achieved 97% accuracy in classifying Parkinsonian gait.

Successfully distinguished between healthy and Parkinsonian gait patterns.

Demonstrated effectiveness of CNN in gait analysis for PD diagnosis.

Abstract

Parkinson's disease (PD) is a non-curable disease that commonly found among elders that greatly reduce their quality of life. PD primarily affects the gait pattern and slowly changes the walking gait from the normality to disability. The early diagnosing of PD is important for treatments and gait pattern analysis is used as a technique to diagnose PD. The present paper has identified the raw spatiotemporal ground reaction force (GRF) as a key parameter to identify the changes in human gait patterns associated with PD. The changes in GRF are identified using a convolutional neural network through pre-processing, conversion, recognition, and performance evaluation. The proposed algorithm is capable of identifying the severity of the PD and distinguishing the parkinsonian gait from the healthy gait. The technique has shown a 97% of accuracy in automatic decision-making process.