A Novel Approach to Parkinson's Disease Progression Evaluation Using Convolutional Neural Networks

A Novel Approach to Parkinson's Disease Progression Evaluation Using Convolutional Neural Networks

Mhamed Zineddine
Copyright: © 2023 |Pages: 26
DOI: 10.4018/IJSI.315655
Article PDF Download
Open access articles are freely available for download

Abstract

Parkinson's disease (PD) is a devastating disorder with serious impacts on the health and quality of life for a wide group of patients. While the early diagnosis of PD is a critical step in managing its symptoms, measuring its progression would be the cornerstone for the development of treatment protocols suitable for each patient. This paper proposes a novel approach to digital PPMI measures and its combination with spirals drawings to increase the accuracy rate of a neural network to the maximum possible. The results show a well performing CNN model with an accuracy of 1(100%). Thus, the end-users of the proposed approach could be more confident when evaluating the progression of PD. The trained, validated, and tested model was able to classify the PD's progression as High, Medium, or Low, with high sureness.
Article Preview
Top

1. Introduction

Individuals in their 60s are increasingly affected by neurological conditions. Parkinson's disease (PD) is the second most common neurological syndrome in the central nervous system (Benba et al. 2016a). There is a consensus among neurologists and researchers that Parkinson’s is caused by aberrations in dopamine signaling in the brain; that is, the dopaminergic neurons fail to release enough signaling substance (dopamine) due to the demise of a significant percentage of them. Bradykinesia (slowness of movement), dysphonia (voice impairment), rigidity, tremor, and poor balance are common symptoms of PD that raise alerts regarding the loss of dopaminergic neurons in the substantia nigra of the brain (Diaz et al. 2022, Louis et.al 2015, Duffy, 2013), that is, the etiology of PD (Kouli et al., 2018). Multiple techniques have been used to detect PD at early stages. For instance, the accuracy of Magnetic Resonance Imaging (MRI) of the brain has increased; thus, MRI has been a part of PD diagnosis (Heim, et al. 2017, Fioravanti, et al. 2015). Physicians have visually and quantitatively interpreted MR images based on changes in brain structure and different types of tissues to identify PD (Tolosa et al.2021, Pyatigorskaya et al., 2018, Heim, 2017, Sterling et al. 2016, Fioravanti, 2015). Moreover, acoustic analysis of patients could help detect voice impairments, which is one of the signs of early PD (Fernández-García et al. 2021, Al-Fatlawi et al., 2016).

Certainly, each PD patient experiences dissimilar progression, cadence, occurrence, evolution and severity of symptoms (Raket et al., 2022), therefore, monitoring these manifestations is of great medical value in order to identify patients with a higher risk of rapid disease progression at early or at advanced stages of the disorder. The benefit of gauging the disease progression is to reassess the level of attention and monitoring required for these patients to cope with the aggressive evolution of their PD symptomatology. Consequently, this helps to ensure an acceptable level of quality of life, which requires careful adjustment of the PD’s management plans.

Complete Article List

Search this Journal:
Reset
Volume 12: 1 Issue (2024)
Volume 11: 1 Issue (2023)
Volume 10: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 9: 4 Issues (2021)
Volume 8: 4 Issues (2020)
Volume 7: 4 Issues (2019)
Volume 6: 4 Issues (2018)
Volume 5: 4 Issues (2017)
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing