Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem

<i>Background and Objectives</i>: Recently, many studies have focused on the early detection of Parkinson’s disease (PD). This disease belongs to a group of neurological problems that immediately affect brain cells and influence the movement, hearing, and various cognitive functions. Med...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hayder Mohammed Qasim, Oguz Ata, Mohammad Azam Ansari, Mohammad N. Alomary, Saad Alghamdi, Mazen Almehmadi
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	Parkinson detection machine learning PCA RFE SMOTE Medicine (General) R5-920
Acceso en línea:	https://doaj.org/article/9ec56e081d0a43d880e4435b66c74842
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9ec56e081d0a43d880e4435b66c74842
record_format	dspace
spelling	oai:doaj.org-article:9ec56e081d0a43d880e4435b66c748422021-11-25T18:18:40ZHybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem10.3390/medicina571112171648-91441010-660Xhttps://doaj.org/article/9ec56e081d0a43d880e4435b66c748422021-11-01T00:00:00Zhttps://www.mdpi.com/1648-9144/57/11/1217https://doaj.org/toc/1010-660Xhttps://doaj.org/toc/1648-9144<i>Background and Objectives</i>: Recently, many studies have focused on the early detection of Parkinson’s disease (PD). This disease belongs to a group of neurological problems that immediately affect brain cells and influence the movement, hearing, and various cognitive functions. Medical data sets are often not equally distributed in their classes and this gives a bias in the classification of patients. We performed a Hybrid feature selection framework that can deal with imbalanced datasets like PD. Use the SOMTE algorithm to deal with unbalanced datasets. Removing the contradiction from the features in the dataset and decrease the processing time by using Recursive Feature Elimination (RFE), and Principle Component Analysis (PCA). <i>Materials and Methods</i>: PD acoustic datasets and the characteristics of control subjects were used to construct classification models such as Bagging, K-nearest neighbour (KNN), multilayer perceptron, and the support vector machine (SVM). In the prepressing stage, the synthetic minority over-sampling technique (SMOTE) with two-feature selection RFE and PCA were used. The PD dataset comprises a large difference between the numbers of the infected and uninfected patients, which causes the classification bias problem. Therefore, SMOTE was used to resolve this problem. <i>Results</i>: For model evaluation, the train–test split technique was used for the experiment. All the models were Grid-search tuned, the evaluation results of the SVM model showed the highest accuracy of 98.2%, and the KNN model exhibited the highest specificity of 99%. <i>Conclusions</i>: the proposed method is compared with the current modern methods of detecting Parkinson’s disease and other methods for medical diseases, it was noted that our developed system could treat data bias and reach a high prediction of PD and this can be beneficial for health organizations to properly prioritize assets.Hayder Mohammed QasimOguz AtaMohammad Azam AnsariMohammad N. AlomarySaad AlghamdiMazen AlmehmadiMDPI AGarticleParkinson detectionmachine learningPCARFESMOTEMedicine (General)R5-920ENMedicina, Vol 57, Iss 1217, p 1217 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Parkinson detection machine learning PCA RFE SMOTE Medicine (General) R5-920
spellingShingle	Parkinson detection machine learning PCA RFE SMOTE Medicine (General) R5-920 Hayder Mohammed Qasim Oguz Ata Mohammad Azam Ansari Mohammad N. Alomary Saad Alghamdi Mazen Almehmadi Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem
description	<i>Background and Objectives</i>: Recently, many studies have focused on the early detection of Parkinson’s disease (PD). This disease belongs to a group of neurological problems that immediately affect brain cells and influence the movement, hearing, and various cognitive functions. Medical data sets are often not equally distributed in their classes and this gives a bias in the classification of patients. We performed a Hybrid feature selection framework that can deal with imbalanced datasets like PD. Use the SOMTE algorithm to deal with unbalanced datasets. Removing the contradiction from the features in the dataset and decrease the processing time by using Recursive Feature Elimination (RFE), and Principle Component Analysis (PCA). <i>Materials and Methods</i>: PD acoustic datasets and the characteristics of control subjects were used to construct classification models such as Bagging, K-nearest neighbour (KNN), multilayer perceptron, and the support vector machine (SVM). In the prepressing stage, the synthetic minority over-sampling technique (SMOTE) with two-feature selection RFE and PCA were used. The PD dataset comprises a large difference between the numbers of the infected and uninfected patients, which causes the classification bias problem. Therefore, SMOTE was used to resolve this problem. <i>Results</i>: For model evaluation, the train–test split technique was used for the experiment. All the models were Grid-search tuned, the evaluation results of the SVM model showed the highest accuracy of 98.2%, and the KNN model exhibited the highest specificity of 99%. <i>Conclusions</i>: the proposed method is compared with the current modern methods of detecting Parkinson’s disease and other methods for medical diseases, it was noted that our developed system could treat data bias and reach a high prediction of PD and this can be beneficial for health organizations to properly prioritize assets.
format	article
author	Hayder Mohammed Qasim Oguz Ata Mohammad Azam Ansari Mohammad N. Alomary Saad Alghamdi Mazen Almehmadi
author_facet	Hayder Mohammed Qasim Oguz Ata Mohammad Azam Ansari Mohammad N. Alomary Saad Alghamdi Mazen Almehmadi
author_sort	Hayder Mohammed Qasim
title	Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem
title_short	Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem
title_full	Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem
title_fullStr	Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem
title_full_unstemmed	Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem
title_sort	hybrid feature selection framework for the parkinson imbalanced dataset prediction problem
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9ec56e081d0a43d880e4435b66c74842
work_keys_str_mv	AT haydermohammedqasim hybridfeatureselectionframeworkfortheparkinsonimbalanceddatasetpredictionproblem AT oguzata hybridfeatureselectionframeworkfortheparkinsonimbalanceddatasetpredictionproblem AT mohammadazamansari hybridfeatureselectionframeworkfortheparkinsonimbalanceddatasetpredictionproblem AT mohammadnalomary hybridfeatureselectionframeworkfortheparkinsonimbalanceddatasetpredictionproblem AT saadalghamdi hybridfeatureselectionframeworkfortheparkinsonimbalanceddatasetpredictionproblem AT mazenalmehmadi hybridfeatureselectionframeworkfortheparkinsonimbalanceddatasetpredictionproblem
_version_	1718411335829553152

Hybrid Feature Selection Framework for the Parkinson Imbalanced Dataset Prediction Problem

Ejemplares similares