scholarly journals An ensemble feature selection framework for early detection of Parkinson's disease based on feature correlation analysis

2021 ◽  
Author(s):  
Sarfaraz Masood ◽  
Khwaja Wisal ◽  
Om Pal ◽  
Chanchal Kumar
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Feature Selection ◽  
Large Population ◽  
Feature Selection Method ◽  
Sampling Strategy ◽  
Chi Square ◽  
Accurate Identification ◽  
Initial Symptoms ◽  
Selection Framework

Parkinson’s disease (PD) is a highly common neurological disease affecting a large population worldwide. Several studies revealed that the degradation of voice is one of its initial symptoms, which is also known as dysarthria. In this work, we attempt to explore and harness the correlation between various features in the voice samples observed in PD subjects. To do so, a novel two-level ensemble-based feature selection method has been proposed, whose results were combined with an MLP based classifier using K-fold cross-validation as the re-sampling strategy. Three separate benchmark datasets of voice samples were used for the experimentation work. Results strongly suggest that the proposed feature selection framework helps in identifying an optimal set of features which further helps in highly accurate identification of PD patients using a Multi-Layer Perceptron from their voice samples. The proposed model achieves an overall accuracy of 98.3%, 95.1% and 100% on the three selected datasets respectively. These results are significantly better than those achieved by a non-feature selection based option, and even the recently proposed chi-square based feature selection option.

CROWD: Crow Search and Deep Learning based Feature Extractor for Classification of Parkinson’s Disease

2021 ◽  
Vol 21 (3) ◽  
pp. 1-18
Author(s):  
Mehedi Masud ◽  
Parminder Singh ◽  
Gurjot Singh Gaba ◽  
Avinash Kaur ◽  
Roobaea Alrobaea Alghamdi ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Feature Selection ◽  
Deep Learning ◽  
Missing Values ◽  
Feature Vector ◽  
Feature Selection Method ◽  
Healthcare Sector ◽  
Brain Cells ◽  
Speech Impairment

Edge Artificial Intelligence (AI) is the latest trend for next-generation computing for data analytics, particularly in predictive edge analytics for high-risk diseases like Parkinson’s Disease (PD). Deep learning learning techniques facilitate edge AI applications for enhanced, real-time handling of data. Dopamine is the cause of Parkinson’s that happens due to the interference of brain cells that produce the substance to regulate the communication of brain cells. The brain cells responsible for generating the dopamine perform adaptation, control, and movement with fluency. Parkinson’s motor symptoms appear on the loss of 60% to 80% of cells, due to the non-production of appropriate dopamine. Recent research found a close connection between the speech impairment and PD. Many researchers have developed a classification algorithm to identify the PD from speech signals. In this article, Adaptive Crow Search Algorithm (ACSA) and Deep Learning (DL)–based optimal feature selection method are introduced. The proposed model is the combination of CROW Search and Deep learning (CROWD) stack sparse autoencoder neural network. Parkinson’s dataset is taken for the experiment from the Irvine dataset repository at the University of California (UCI). In the first phase, dataset cleaning is performed to handle the missing values in the dataset. After that, the proposed ACSA algorithm is employed to find the scrunched feature vector. Furthermore, stack spare autoencoder with seven hidden layers is employed to generate the compressed feature vector. The performance of the proposed CROWD autoencoder model is compared with three feature selection approaches for six supervised classification techniques. The experiment result demonstrates that the performance of the proposed CROWD autoencoder feature selection model has outperformed the benchmarked feature selection techniques: (i) Maximum Relevance (mRMR) (ii) Recursive Feature Elimination (RFE), and (iii) Correlation-based Feature Selection (CFS), to classify Parkinson’s disease. This research has significance in the healthcare sector for the enhancement of classification accuracy up to 0.96%.

scholarly journals Feature Selection and Radial Basis Function Network for Parkinson Disease Classification

2017 ◽  
Vol 2 (3) ◽  
pp. 167-171
Author(s):  
Ashraf Osman Ibrahim ◽  
Walaa Akif Hussien ◽  
Ayat Mohammoud Yagoop ◽  
Mohd Arfian Ismail
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Feature Selection ◽  
Parkinson Disease ◽  
Radial Basis Function ◽  
Basis Function ◽  
Radial Basis Function Network ◽  
Feature Selection Method ◽  
Selection Method ◽  
Radial Basis

Recently, several works have focused on detection of a different disease using computational intelligence techniques. In this paper, we applied feature selection method and radial basis function neural network (RBFN) to classify the diagnosis of Parkinson’s disease. The feature selection (FS) method used to reduce the number of attributes in Parkinson disease data. The Parkinson disease dataset is acquired from UCI repository of large well-known data sets. The experimental results have revealed significant improvement to detect Parkinson’s disease using feature selection method and RBF network.

scholarly journals Correlates of the discrepancy between objective and subjective cognitive functioning in non-demented patients with Parkinson’s disease

2021 ◽  
Author(s):  
Mattia Siciliano ◽  
Lugi Trojano ◽  
Rosa De Micco ◽  
Valeria Sant’Elia ◽  
Alfonso Giordano ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Linear Regression ◽  
Cognitive Functioning ◽  
Rating Scale ◽  
Regression Analyses ◽  
Chi Square ◽  
Cognitive Measure ◽  
Objective Evidence ◽  
Cognitive Discrepancy

Abstract Background Subjective complaints of cognitive deficits are not necessarily consistent with objective evidence of cognitive impairment in Parkinson’s disease (PD). Here we examined the factors associated with the objective-subjective cognitive discrepancy. Methods We consecutively enrolled 90 non-demented patients with PD who completed the Parkinson’s Disease Cognitive Functional Rating Scale (subjective cognitive measure) and the Montreal Cognitive Assessment (MoCA; objective cognitive measure). The patients were classified as “Overestimators”, “Accurate estimators”, and “Underestimators” on the basis of the discrepancy between the objective vs. subjective cognitive measures. To identify the factors distinguishing these groups from each other, we used chi-square tests or one-way analyses of variance, completed by logistic and linear regression analyses. Results Forty-nine patients (54.45%) were classified as “Accurate estimators”, 29 (32.22%) as “Underestimators”, and 12 (13.33%) as “Overestimators”. Relative to the other groups, the “Underestimators” scored higher on the Fatigue Severity Scale (FSS), Beck Depression Inventory (BDI), and Parkinson Anxiety Scale (p < 0.01). Logistic regression confirmed that FSS and BDI scores distinguished the “Underestimators” group from the others (p < 0.05). Linear regression analyses also indicated that FSS and BDI scores positively related to objective-subjective cognitive discrepancy (p < 0.01). “Overestimators” scored lower than other groups on the MoCA’s total score and attention and working memory subscores (p < 0.01). Conclusion In more than 45% of consecutive non-demented patients with PD, we found a ‘mismatch’ between objective and subjective measures of cognitive functioning. Such discrepancy, which was related to the presence of fatigue and depressive symptoms and frontal executive impairments, should be carefully evaluated in clinical setting.

Sign in / Sign up

Export Citation Format

Share Document