Open Access Open Access  Restricted Access Subscription or Fee Access

Gait Motor Signal Processing for Parkinson's Disease Detection Based on Artificial Intelligence

Mohammad Karimi Moridani, Nona Gholami Niaye Shahrestani

Abstract



Early diagnosis of neurodegenerative diseases is crucial to prevent the progression of these diseases. Also, in some nervous system disorders, the early diagnosis of the disease could change the course of the treatment. Considering that gait disorder is one of the important symptoms of Parkinson’s disease (PD) in this paper using the linear and nonlinear analysis of gait motor signal in two groups of healthy and PD patients, the two groups will be diagnosed and differentiated.
The data used in this study included 16 healthy people and 15 people with PD, which was collected by physiognomy database. They did not have any history of neurological disease and did not use motor vehicles such as cane or wheelchairs. After removing noise and extracting linear and nonlinear features, the feature selection was done by statistical analysis of the t-test on the independent samples. Finally using the selected features and multilayer perceptron artificial neural network and radial base function the classification of normal and patient subjects was performed.
To compare the proposed algorithm, sensitivity, specificity, and accuracy criteria were used in this paper. The results of the proposed method showed that the percentage of sensitivity, specificity, and accuracy were 95.1% ± 4.8, 93.3 ± 3.5 and 92.6% ± 1.3 using multi-layer perceptron classifier and 92.3% ± 2.9%, 89.4 ± 3.7% and 88.2 ± 3.3% using the radial base function. Therefore, the use of the network can help identify people at risk of PD.
Using the gait motor signal of people by intelligent algorithms can help to identify people who are at the early stages of the PD and also prevent the rapid progression of this disease.

Keywords


Artificial Intelligence, Gait Motor Signal, Linear and Nonlinear Analysis, Parkinson’s disease

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.