Diagnosis of Parkinson’s Disease Using SVM Classifier

2020 ◽  
pp. 2150011
Author(s):  
G. Wiselin Jiji ◽  
A. Rajesh ◽  
P. Johnson Durai Raj
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Early Diagnosis ◽  
Active Contour ◽  
Motor System ◽  
Svm Classifier ◽  
Common Disease ◽  
Morphological Operation ◽  
Aged People ◽  
Speech Data

Parkinson’s disease (PD) is the most common disease that affects aged people which leads to dopamine-producing cells in substantia nigra to be damaged when motor system degenerates. Clinical Diagnosis of Parkinson’s disease at the earlier stage is very difficult. This work is carried out to find the significance of cognition function of basal ganglia (BG) region and speech data values. The BG can be segmented using morphological operation and active contour algorithm. Co-occurrences features are extracted and out of 720 features, the promising 110 features are selected using variance method. More promising 22 features are selected in speech data and both features are individually classified using SVM to find out the efficiency in Diagnosis. The outcome shows cognition function of BG performing a major role in early diagnosis of Parkinson’s disease when compared to speech data.

scholarly journals Toxic Models of Parkinson's Disease: History and Prospects

2021 ◽  
Vol 6 (3) ◽  
pp. 78-84
Author(s):  
D. S. Yaroshenko ◽  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Basal Ganglia ◽  
Early Diagnosis ◽  
Brain Stem ◽  
Genetic Predisposition ◽  
Common Disease ◽  
Extrapyramidal System ◽  
Early Stages ◽  
The Brain

The review article presents data on the history of research of extrapyramidal system dysfunctions, modern ideas about the etiology and diagnosis of Parkinson's disease, as the most common disease of the group of extrapyramidal disorders. Currently, no concept of effective therapy for patients with extrapyramidal system dysfunction has been developed, but it has been proven that the probability of developing the disease largely depends on the genetic predisposition and the level of environmental pollution. In the early stages, the disease is slow and asymptomatic, but gradually more than half of patients with Parkinson's disease die, and others need outside care. According to experts, in the near future, Parkinson's disease will become a problem for a significant part of people, because today it affects more and more people of working age. Under such conditions, reliable and early diagnosis of the disease is of great importance, which guarantees timely and most effective treatment. Modern therapies fail to stop the progressive death of the dopaminergic neurons of the substantia nigra, but traditional treatment can achieve symptomatic relief. Currently, it is known that the probability of developing Parkinson's disease depends on the genetic predisposition and the level of man-made environmental stress. The researchers consider that the pathological development of Parkinson's disease in the brain begins in the lower structures of the brain stem with the involvement of the caudal-Rostral nuclei, as well as the involvement of the cortico-basal ganglia-cerebellar pathways. The pathological process affects the ascending pathways and gradually passes to the midbrain, directly to the black substance, spreads from there and weakens the mesocortex and neocortex. Injuries in the brain stem lead to disorganization of the cortico-basal ganglia and cerebellar pathways, followed by the formation of alternative pathways to compensate for the initial disorders in the early stages of the disease. In addition, in Parkinson's disease, intracellular Lewy bodies and neurites formed by the protein alpha-synuclein are created, which are found in the autopsy material of most patients. Poor results of diagnostic evaluation and treatment of Parkinson's disease are usually associated with a lack of understanding of the pathogenesis of Parkinson's disease. The study of the biological basis and pathogenesis of Parkinson's disease is an important task of a whole complex of scientific studies of extrapyramidal system dysfunction. Conclusion. The article discusses the creation of toxic models of Parkinson's disease in vivo and in vitro, which help to recreate the pathogenesis of the disease for early diagnosis and the development of new ways to treat neurodegenerative diseases. In toxic models of Parkinsonism, not only deficits of motor functions such as bradykinesia, tremor, and posture disorders are actively studied, but also non-motor symptoms such as sleep disorders, neuropsychiatric and cognitive abnormalities

scholarly journals m-ark-Support Vector Machine for Early Detection of Parkinson’s Disease from Speech Signals

2021 ◽  
Vol 15 ◽  
pp. 34-41
Author(s):  
Luca Parisi ◽  
Amir Zaernia ◽  
Renfei Ma ◽  
Mansour Youseffi
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Early Detection ◽  
Early Diagnosis ◽  
Real Life ◽  
Kernel Functions ◽  
Support Vector ◽  
Margin Width ◽  
Speech Data ◽  
Benchmark Datasets

Recent advances in the state-of-the-art open-source kernel functions for support vector machines (SVMs) have widened the choices of benchmark kernels for Machine Learning (ML)-based classification. However, it is still challenging to achieve margin maximisation in SVM, and further evidence is required to ensure such novel kernel functions can have translational applications with tangible impact. Noteworthily, m-arcsinh, freely available in scikit-learn, was preliminarily proven as a benchmark kernel function on 15 datasets in its seminal paper. Quantifying the benefit from leveraging this kernel in a specific application is essential to provide further evidence of its accuracy and reliability on real-life supervised ML-aided tasks. Thus, the predictive capability of SVM, including that with Lagrange multipliers for the first time coupled with m-arcsinh (m-ark-SVM with soft margin; m-arK-SVM with hard margin), is hereby assessed in aiding early detection of Parkinson’s Disease (PD) from speech data. This is important to leverage the m-arcsinh kernel ‘trick’ to maximise the margin width and, therefore, the linear separability of input speech features via automated pattern recognition. In this study, we demonstrate the accuracy and reliability of m-ark-SVM to aid early diagnosis of PD, evaluated against other gold standard kernel functions. Two benchmark datasets from the University of California-Irvine (UCI) database, pre-processed solely via min-max normalisation, were used to discriminate between speech patterns of 72 healthy subjects and 211 patients with PD. Overtraining was avoided via cross validation and the models were developed and tested in Python 3.7. The supervised model (m-ark-SVM) could detect early Parkinson’s Disease with 87.18% and 86.9% classification accuracy from the two datasets respectively (F1- scores: 85 and 86.2% correspondingly). Furthermore, the model achieved high precision (89.2% and 86.8%) and specificity (87% and 86.8%). Thus, this study validates the application of m-arcsinh to aid real-life supervised ML-based classification, in particular early diagnosis of Parkinson’s Disease from speech data.

Current Therapeutic Strategies and Perspectives for Neuroprotection in Parkinson’s Disease

2020 ◽  
Vol 26 (37) ◽  
pp. 4738-4746
Author(s):  
Mohan K. Ghanta ◽  
P. Elango ◽  
Bhaskar L. V. K. S.
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Early Diagnosis ◽  
Neurodegenerative Disorder ◽  
Therapeutic Strategies ◽  
Neuroprotective Agents ◽  
Striatal Neurons ◽  
The Status ◽  
Advanced Stages ◽  
Dopaminergic Pathways

Parkinson’s disease is a progressive neurodegenerative disorder of dopaminergic striatal neurons in basal ganglia. Treatment of Parkinson’s disease (PD) through dopamine replacement strategies may provide improvement in early stages and this treatment response is related to dopaminergic neuronal mass which decreases in advanced stages. This treatment failure was revealed by many studies and levodopa treatment became ineffective or toxic in chronic stages of PD. Early diagnosis and neuroprotective agents may be a suitable approach for the treatment of PD. The essentials required for early diagnosis are biomarkers. Characterising the striatal neurons, understanding the status of dopaminergic pathways in different PD stages may reveal the effects of the drugs used in the treatment. This review updates on characterisation of striatal neurons, electrophysiology of dopaminergic pathways in PD, biomarkers of PD, approaches for success of neuroprotective agents in clinical trials. The literature was collected from the articles in database of PubMed, MedLine and other available literature resources.

scholarly journals The Role of Salivary Biomarkers in the Early Diagnosis of Alzheimer’s Disease and Parkinson’s Disease

Diagnostics ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 371
Author(s):  
Patrycja Pawlik ◽  
Katarzyna Błochowiak
Keyword(s):  
Alzheimer’S Disease ◽  
Parkinson’S Disease ◽  
Alzheimer's Disease ◽  
Parkinson's Disease ◽  
Early Diagnosis ◽  
Neurodegenerative Diseases ◽  
Diagnostic Tool ◽  
Clinical Symptoms ◽  
Early Screening ◽  
Salivary Biomarkers

Many neurodegenerative diseases present with progressive neuronal degeneration, which can lead to cognitive and motor impairment. Early screening and diagnosis of neurodegenerative diseases such as Alzheimer’s disease (AD) and Parkinson’s disease (PD) are necessary to begin treatment before the onset of clinical symptoms and slow down the progression of the disease. Biomarkers have shown great potential as a diagnostic tool in the early diagnosis of many diseases, including AD and PD. However, screening for these biomarkers usually includes invasive, complex and expensive methods such as cerebrospinal fluid (CSF) sampling through a lumbar puncture. Researchers are continuously seeking to find a simpler and more reliable diagnostic tool that would be less invasive than CSF sampling. Saliva has been studied as a potential biological fluid that could be used in the diagnosis and early screening of neurodegenerative diseases. This review aims to provide an insight into the current literature concerning salivary biomarkers used in the diagnosis of AD and PD. The most commonly studied salivary biomarkers in AD are β-amyloid1-42/1-40 and TAU protein, as well as α-synuclein and protein deglycase (DJ-1) in PD. Studies continue to be conducted on this subject and researchers are attempting to find correlations between specific biomarkers and early clinical symptoms, which could be key in creating new treatments for patients before the onset of symptoms.

scholarly journals Can Biomarkers Help the Early Diagnosis of Parkinson’s Disease?

2017 ◽  
Vol 33 (5) ◽  
pp. 535-542 ◽  
Author(s):  
Weidong Le ◽  
Jie Dong ◽  
Song Li ◽  
Amos D. Korczyn
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Early Diagnosis

scholarly journals Molecular and functional variation in iPSC-derived sensory neurons

2017 ◽  
Author(s):  
Jeremy Schwartzentruber ◽  
Stefanie Foskolou ◽  
Helena Kilpinen ◽  
Julia Rodrigues ◽  
Kaur Alasoo ◽  
...  
Keyword(s):  
Gene Expression ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Chromatin Accessibility ◽  
Nervous System Development ◽  
Sensory Function ◽  
Neuronal Cultures ◽  
Common Disease ◽  
Specific Method ◽  
Causal Variants

AbstractInduced pluripotent stem cells (iPSCs), and cells derived from them, have become key tools to model biological processes and disease mechanisms, particularly in cell types such as neurons that are difficult to access from living donors. Here, we present the first map of regulatory variants in an iPSC-derived cell type. To investigate genetic contributions to human sensory function, we performed 123 differentiations of iPSCs from 103 unique donors to a sensory neuronal fate, and measured gene expression, chromatin accessibility, and neuronal excitability. Compared with primary dorsal root ganglion, where sensory nerves collect near the spinal cord, gene expression was more variable across iPSC-derived neuronal cultures, particularly in genes related to differentiation and nervous system development. Single cell RNA-sequencing revealed that although the majority of cells are neuronal and express the expected marker genes, a substantial fraction have a fibroblast-like expression profile. By applying an allele-specific method we identify 3,778 quantitative trait loci influencing gene expression, 6,318 for chromatin accessibility, and 2,097 for RNA splicing at FDR 10%. A number of these overlap with common disease associations, and suggest candidate causal variants and target genes. These include known causal variants at SNCA for Parkinson’s disease and TNFRSF1A for multiple sclerosis, as well as new candidates for migraine, Parkinson’s disease, and schizophrenia.

scholarly journals A Simple and Effective Approach Based on a Multi-Level Feature Selection for Automated Parkinson’s Disease Detection

2022 ◽  
Vol 12 (1) ◽  
pp. 55
Author(s):  
Fatih Demir ◽  
Kamran Siddique ◽  
Mohammed Alswaitti ◽  
Kursat Demir ◽  
Abdulkadir Sengur
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Feature Selection ◽  
Early Diagnosis ◽  
Neurodegenerative Disorder ◽  
Bayesian Optimization ◽  
L1 Norm ◽  
Bayesian Optimization Algorithm ◽  
Knn Classifier ◽  
Multi Level

Parkinson’s disease (PD), which is a slowly progressing neurodegenerative disorder, negatively affects people’s daily lives. Early diagnosis is of great importance to minimize the effects of PD. One of the most important symptoms in the early diagnosis of PD disease is the monotony and distortion of speech. Artificial intelligence-based approaches can help specialists and physicians to automatically detect these disorders. In this study, a new and powerful approach based on multi-level feature selection was proposed to detect PD from features containing voice recordings of already-diagnosed cases. At the first level, feature selection was performed with the Chi-square and L1-Norm SVM algorithms (CLS). Then, the features that were extracted from these algorithms were combined to increase the representation power of the samples. At the last level, those samples that were highly distinctive from the combined feature set were selected with feature importance weights using the ReliefF algorithm. In the classification stage, popular classifiers such as KNN, SVM, and DT were used for machine learning, and the best performance was achieved with the KNN classifier. Moreover, the hyperparameters of the KNN classifier were selected with the Bayesian optimization algorithm, and the performance of the proposed approach was further improved. The proposed approach was evaluated using a 10-fold cross-validation technique on a dataset containing PD and normal classes, and a classification accuracy of 95.4% was achieved.

Sign in / Sign up

Export Citation Format

Share Document