Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease
Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor impairment, as well as tremors, stiffness, and rigidity. Besides the typical motor symptomatology, some Parkinsonians experience non-motor symptoms such as hyposmia, constipation, urinary dysfunction, orthost...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-03-01
|
Series: | Bioengineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2306-5354/9/3/116 |
_version_ | 1797472799246254080 |
---|---|
author | Nalini Chintalapudi Gopi Battineni Mohmmad Amran Hossain Francesco Amenta |
author_facet | Nalini Chintalapudi Gopi Battineni Mohmmad Amran Hossain Francesco Amenta |
author_sort | Nalini Chintalapudi |
collection | DOAJ |
description | Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor impairment, as well as tremors, stiffness, and rigidity. Besides the typical motor symptomatology, some Parkinsonians experience non-motor symptoms such as hyposmia, constipation, urinary dysfunction, orthostatic hypotension, memory loss, depression, pain, and sleep disturbances. The correct diagnosis of PD cannot be easy since there is no standard objective approach to it. After the incorporation of machine learning (ML) algorithms in medical diagnoses, the accuracy of disease predictions has improved. In this work, we have used three deep-learning-type cascaded neural network models based on the audial voice features of PD patients, called Recurrent Neural Networks (RNN), Multilayer Perception (MLP), and Long Short-Term Memory (LSTM), to estimate the accuracy of PD diagnosis. A performance comparison between the three models was performed on a sample of the subjects’ voice biomarkers. Experimental outcomes suggested that the LSTM model outperforms others with 99% accuracy. This study has also presented loss function curves on the relevance of good-fitting models to the detection of neurodegenerative diseases such as PD. |
first_indexed | 2024-03-09T20:07:19Z |
format | Article |
id | doaj.art-fa822df328264d82bbb1aa7e9b536fef |
institution | Directory Open Access Journal |
issn | 2306-5354 |
language | English |
last_indexed | 2024-03-09T20:07:19Z |
publishDate | 2022-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Bioengineering |
spelling | doaj.art-fa822df328264d82bbb1aa7e9b536fef2023-11-24T00:30:23ZengMDPI AGBioengineering2306-53542022-03-019311610.3390/bioengineering9030116Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s DiseaseNalini Chintalapudi0Gopi Battineni1Mohmmad Amran Hossain2Francesco Amenta3Centre of Clinical Research, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, ItalyCentre of Clinical Research, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, ItalyCentre of Clinical Research, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, ItalyCentre of Clinical Research, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, ItalyParkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor impairment, as well as tremors, stiffness, and rigidity. Besides the typical motor symptomatology, some Parkinsonians experience non-motor symptoms such as hyposmia, constipation, urinary dysfunction, orthostatic hypotension, memory loss, depression, pain, and sleep disturbances. The correct diagnosis of PD cannot be easy since there is no standard objective approach to it. After the incorporation of machine learning (ML) algorithms in medical diagnoses, the accuracy of disease predictions has improved. In this work, we have used three deep-learning-type cascaded neural network models based on the audial voice features of PD patients, called Recurrent Neural Networks (RNN), Multilayer Perception (MLP), and Long Short-Term Memory (LSTM), to estimate the accuracy of PD diagnosis. A performance comparison between the three models was performed on a sample of the subjects’ voice biomarkers. Experimental outcomes suggested that the LSTM model outperforms others with 99% accuracy. This study has also presented loss function curves on the relevance of good-fitting models to the detection of neurodegenerative diseases such as PD.https://www.mdpi.com/2306-5354/9/3/116Parkinson’s diseasedeep learningneural networksmodel fittingearly detection |
spellingShingle | Nalini Chintalapudi Gopi Battineni Mohmmad Amran Hossain Francesco Amenta Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease Bioengineering Parkinson’s disease deep learning neural networks model fitting early detection |
title | Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease |
title_full | Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease |
title_fullStr | Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease |
title_full_unstemmed | Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease |
title_short | Cascaded Deep Learning Frameworks in Contribution to the Detection of Parkinson’s Disease |
title_sort | cascaded deep learning frameworks in contribution to the detection of parkinson s disease |
topic | Parkinson’s disease deep learning neural networks model fitting early detection |
url | https://www.mdpi.com/2306-5354/9/3/116 |
work_keys_str_mv | AT nalinichintalapudi cascadeddeeplearningframeworksincontributiontothedetectionofparkinsonsdisease AT gopibattineni cascadeddeeplearningframeworksincontributiontothedetectionofparkinsonsdisease AT mohmmadamranhossain cascadeddeeplearningframeworksincontributiontothedetectionofparkinsonsdisease AT francescoamenta cascadeddeeplearningframeworksincontributiontothedetectionofparkinsonsdisease |