Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization

Parkinson’s Disease (PD) is a neurological condition that worsens with time and is characterized bysymptoms such as cognitive impairment andbradykinesia, stiffness, and tremors. Parkinson’s is attributed to the interference of brain cells responsible for dopamine production, a substance regulating c...

Full description

Saved in:
Bibliographic Details
Main Authors: Aarti, Swathi Gowroju, Mst Ismat Ara Begum, A. S. M. Sanwar Hosen
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:BioMedInformatics
Subjects:
Online Access:https://www.mdpi.com/2673-7426/4/4/120
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850240171684921344
author Aarti
Swathi Gowroju
Mst Ismat Ara Begum
A. S. M. Sanwar Hosen
author_facet Aarti
Swathi Gowroju
Mst Ismat Ara Begum
A. S. M. Sanwar Hosen
author_sort Aarti
collection DOAJ
description Parkinson’s Disease (PD) is a neurological condition that worsens with time and is characterized bysymptoms such as cognitive impairment andbradykinesia, stiffness, and tremors. Parkinson’s is attributed to the interference of brain cells responsible for dopamine production, a substance regulating communication between brain cells. The brain cells involved in dopamine generation handle adaptation and control, and smooth movement. Convolutional Neural Networks are used to extract distinctive visual characteristics from numerous graphomotor sample representations generated by both PD and control participants. The proposed method presents an optimal feature selection technique based on Deep Learning (DL) and the Dynamic Bag of Features Optimization Technique (DBOFOT). Our method combines neural network-based feature extraction with a strong optimization technique to dynamically choose the most relevant characteristics from biological data. Advanced DL architectures are then used to classify the chosen features, guaranteeing excellent computational efficiency and accuracy. The framework’s adaptability to different datasets further highlights its versatility and potential for further medical applications. With a high accuracy of 0.93, the model accurately identifies 93% of the cases that are categorized as Parkinson’s. Additionally, it has a recall of 0.89, which means that 89% of real Parkinson’s patients are accurately identified. While the recall for Class 0 (Healthy) is 0.75, meaning that 75% of the real healthy cases are properly categorized, the precision decreases to 0.64 for this class, indicating a larger false positive rate.
format Article
id doaj-art-e2c5aee3f0d344d99cd3728714a3bbd2
institution OA Journals
issn 2673-7426
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series BioMedInformatics
spelling doaj-art-e2c5aee3f0d344d99cd3728714a3bbd22025-08-20T02:00:55ZengMDPI AGBioMedInformatics2673-74262024-11-01442223225010.3390/biomedinformatics4040120Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features OptimizationAarti0Swathi Gowroju1Mst Ismat Ara Begum2A. S. M. Sanwar Hosen3Department of Computer Science and Engineering, Lovely Professional University, Jalandhar 144411, Punjab, IndiaDepartment of Artificial Intelligence and Machine Learning, Sreyas Institute of Engineering and Technology, Hyderabad 500068, Telangana, IndiaDepartment of Biomedical Sciences, Institute for Medical Science, Jeonbuk National University Medical School, Jeonju 54907, Republic of KoreaDepartment of Artificial Intelligence and Big Data, Woosong University, Daejeon 34606, Republic of KoreaParkinson’s Disease (PD) is a neurological condition that worsens with time and is characterized bysymptoms such as cognitive impairment andbradykinesia, stiffness, and tremors. Parkinson’s is attributed to the interference of brain cells responsible for dopamine production, a substance regulating communication between brain cells. The brain cells involved in dopamine generation handle adaptation and control, and smooth movement. Convolutional Neural Networks are used to extract distinctive visual characteristics from numerous graphomotor sample representations generated by both PD and control participants. The proposed method presents an optimal feature selection technique based on Deep Learning (DL) and the Dynamic Bag of Features Optimization Technique (DBOFOT). Our method combines neural network-based feature extraction with a strong optimization technique to dynamically choose the most relevant characteristics from biological data. Advanced DL architectures are then used to classify the chosen features, guaranteeing excellent computational efficiency and accuracy. The framework’s adaptability to different datasets further highlights its versatility and potential for further medical applications. With a high accuracy of 0.93, the model accurately identifies 93% of the cases that are categorized as Parkinson’s. Additionally, it has a recall of 0.89, which means that 89% of real Parkinson’s patients are accurately identified. While the recall for Class 0 (Healthy) is 0.75, meaning that 75% of the real healthy cases are properly categorized, the precision decreases to 0.64 for this class, indicating a larger false positive rate.https://www.mdpi.com/2673-7426/4/4/120Parkinson’s diseasefeature selectiondeep learningdynamic bag of featuresclassificationpredictive modeling
spellingShingle Aarti
Swathi Gowroju
Mst Ismat Ara Begum
A. S. M. Sanwar Hosen
Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization
BioMedInformatics
Parkinson’s disease
feature selection
deep learning
dynamic bag of features
classification
predictive modeling
title Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization
title_full Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization
title_fullStr Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization
title_full_unstemmed Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization
title_short Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization
title_sort optimal feature selection and classification for parkinson s disease using deep learning and dynamic bag of features optimization
topic Parkinson’s disease
feature selection
deep learning
dynamic bag of features
classification
predictive modeling
url https://www.mdpi.com/2673-7426/4/4/120
work_keys_str_mv AT aarti optimalfeatureselectionandclassificationforparkinsonsdiseaseusingdeeplearninganddynamicbagoffeaturesoptimization
AT swathigowroju optimalfeatureselectionandclassificationforparkinsonsdiseaseusingdeeplearninganddynamicbagoffeaturesoptimization
AT mstismatarabegum optimalfeatureselectionandclassificationforparkinsonsdiseaseusingdeeplearninganddynamicbagoffeaturesoptimization
AT asmsanwarhosen optimalfeatureselectionandclassificationforparkinsonsdiseaseusingdeeplearninganddynamicbagoffeaturesoptimization