scholarly journals Screening of Parkinson’s Disease Using Geometric Features Extracted from Spiral Drawings

2021 ◽  
Vol 11 (10) ◽  
pp. 1297
Author(s):  
Jay Chandra ◽  
Siva Muthupalaniappan ◽  
Zisheng Shang ◽  
Richard Deng ◽  
Raymond Lin ◽  
...  

Conventional means of Parkinson’s Disease (PD) screening rely on qualitative tests typically administered by trained neurologists. Tablet technologies that enable data collection during handwriting and drawing tasks may provide low-cost, portable, and instantaneous quantitative methods for high-throughput PD screening. However, past efforts to use data from tablet-based drawing processes to distinguish between PD and control populations have demonstrated only moderate classification ability. Focusing on digitized drawings of Archimedean spirals, the present study utilized data from the open-access ParkinsonHW dataset to improve existing PD drawing diagnostic pipelines. Random forest classifiers were constructed using previously documented features and highly-predictive, newly-proposed features that leverage the many unique mathematical characteristics of the Archimedean spiral. This approach yielded an AUC of 0.999 on the particular dataset we tested on, and more importantly identified interpretable features with good promise for generalization across diverse patient cohorts. It demonstrated the potency of mathematical relationships inherent to the drawing shape and the usefulness of sparse feature sets and simple models, which further enhance interpretability, in the face of limited sample size. The results of this study also inform suggestions for future drawing task design and data analytics (feature extraction, shape selection, task diversity, drawing templates, and data sharing).

2016 ◽  
Vol 365 ◽  
pp. 175-180 ◽  
Author(s):  
Erica Cassani ◽  
Roberto Cilia ◽  
Janeth Laguna ◽  
Michela Barichella ◽  
Manuela Contin ◽  
...  

Author(s):  
Domenico Buongiorno ◽  
Gianpaolo Francesco Trotta ◽  
Ilaria Bortone ◽  
Nicola Di Gioia ◽  
Felice Avitto ◽  
...  

2021 ◽  
Vol 12 ◽  
Author(s):  
Cheng-Fu Su ◽  
Li Jiang ◽  
Xiao-Wen Zhang ◽  
Ashok Iyaswamy ◽  
Min Li

Parkinson’s disease (PD) is a common neurodegenerative disease featured by progressive degeneration of nigrostriatal dopaminergic neurons (DA) accompanied with motor function impairment. Accumulating evidence has demonstrated that natural compounds from herbs have potent anti-PD efficacy in PD models. Among those compounds, resveratrol, a polyphenol found in many common plants and fruits, is more effective against PD. Resveratrol has displayed a potent neuroprotective efficacy in several PD animal models. However, there is still no systematic analysis of the quality of methodological design of these studies, nor of their results. In this review, we retrieved and analyzed 18 studies describing the therapeutic effect of resveratrol on PD animal models. There are 5 main kinds of PD rodent models involved in the 18 articles, including chemical-induced (MPTP, rotenone, 6-OHDA, paraquat, and maneb) and transgenic PD models. The neuroprotective mechanisms of resveratrol were mainly concentrated on the antioxidation, anti-inflammation, ameliorating mitochondrial dysfunction, and motor function. We discussed the disadvantages of different PD animal models, and we used meta-analysis approach to evaluate the results of the selected studies and used SYRCLE’s risk of bias tool to evaluate the methodological quality. Our analytical approach minimized the bias of different studies. We have also summarized the pharmacological mechanisms of resveratrol on PD models as reported by the researchers. The results of this study support the notion that resveratrol has significant neuroprotective effects on different PD models quantified using qualitative and quantitative methods. The collective information in our review can guide researchers to further plan their future experiments without any hassle regarding preclinical and clinical studies. In addition, this collective assessment of animal studies can provide a qualitative analysis of different PD animal models, either to guide further testing of these models or to avoid unnecessary duplication in their future research.


Biomolecules ◽  
2019 ◽  
Vol 9 (4) ◽  
pp. 142 ◽  
Author(s):  
Fabio Bello ◽  
Mario Giannella ◽  
Gianfabio Giorgioni ◽  
Alessandro Piergentili ◽  
Wilma Quaglia

Levodopa (LD) is the most effective drug in the treatment of Parkinson’s disease (PD). However, although it represents the “gold standard” of PD therapy, LD can cause side effects, including gastrointestinal and cardiovascular symptoms as well as transient elevated liver enzyme levels. Moreover, LD therapy leads to LD-induced dyskinesia (LID), a disabling motor complication that represents a major challenge for the clinical neurologist. Due to the many limitations associated with LD therapeutic use, other dopaminergic and non-dopaminergic drugs are being developed to optimize the treatment response. This review focuses on recent investigations about non-dopaminergic central nervous system (CNS) receptor ligands that have been identified to have therapeutic potential for the treatment of motor and non-motor symptoms of PD. In a different way, such agents may contribute to extending LD response and/or ameliorate LD-induced side effects.


2020 ◽  
Vol 80 ◽  
pp. 138-141 ◽  
Author(s):  
Letizia Straniero ◽  
Valeria Rimoldi ◽  
Giada Melistaccio ◽  
Alessio Di Fonzo ◽  
Gianni Pezzoli ◽  
...  

2008 ◽  
Vol 2 (3) ◽  
pp. 201-205 ◽  
Author(s):  
Marina Ceres Silva Pena ◽  
Emmanuelle Silva Tavares Sobreira ◽  
Carolina Pinto Souza ◽  
Guiomar Nascimento Oliveira ◽  
Vitor Tumas ◽  
...  

Abstract Parkinson's disease (PD) is a neurological disorder characterized by motor disturbances, neuropsychological symptoms and cognitive changes, including cases of dementia. The most frequently described cognitive changes in these patients involve executive and visuospatial functions, which are very important for the execution of daily life activities. Objective: To compare different tests used to examine visuospatial functions in patients with PD. Methods: Thirty-five patients (21 women) with PD symptoms (medicated and "on") and mean schooling of 5.5±4.2 years were examined using the following tests: Mini-Mental State Examination (MMSE), Dementia Rating Scale (DRS), Scales of Outcomes of Parkinson's Disease (SCOPA-COG), Hooper Visual Organization Test (HVOT), Judgment of Line Orientation, Form V (JLO), and Clock drawing task - CLOX (1 and 2). Results: The mean MMSE score was 24.8±3.03 and 54.8% of the patients performed correctly in the copy of a pentagon drawing, with a medium-level performance in most tests. Good correlations were detected between JLO versus SCOPA Assembling patterns (0.67), JLO versus HVOT (0.56), JLO versus CLOX2 (0.64), SCOPA Figure Composition versus HVOT (0.54), CLOX1 versus CLOX2 (0.43), and DRS Construction versus CLOX2 (0.42). Discussion: Although correlations were detected, not all were strong, probably because the tests employed do not measure solely visuospatial functions, but also other skills such as attention, motor ability and executive functions. A limitation of the present study was the lack of a control group for the establishment of adequate standards for this population.


Sign in / Sign up

Export Citation Format

Share Document