A machine learning method to process voice samples for identification of Parkinson’s disease
Abstract Machine learning approaches have been used for the automatic detection of Parkinson’s disease with voice recordings being the most used data type due to the simple and non-invasive nature of acquiring such data. Although voice recordings captured via telephone or mobile devices allow much e...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-47568-w |
| _version_ | 1797452969442017280 |
|---|---|
| author | Anu Iyer Aaron Kemp Yasir Rahmatallah Lakshmi Pillai Aliyah Glover Fred Prior Linda Larson-Prior Tuhin Virmani |
| author_facet | Anu Iyer Aaron Kemp Yasir Rahmatallah Lakshmi Pillai Aliyah Glover Fred Prior Linda Larson-Prior Tuhin Virmani |
| author_sort | Anu Iyer |
| collection | DOAJ |
| description | Abstract Machine learning approaches have been used for the automatic detection of Parkinson’s disease with voice recordings being the most used data type due to the simple and non-invasive nature of acquiring such data. Although voice recordings captured via telephone or mobile devices allow much easier and wider access for data collection, current conflicting performance results limit their clinical applicability. This study has two novel contributions. First, we show the reliability of personal telephone-collected voice recordings of the sustained vowel /a/ in natural settings by collecting samples from 50 people with specialist-diagnosed Parkinson’s disease and 50 healthy controls and applying machine learning classification with voice features related to phonation. Second, we utilize a novel application of a pre-trained convolutional neural network (Inception V3) with transfer learning to analyze the spectrograms of the sustained vowel from these samples. This approach considers speech intensity estimates across time and frequency scales rather than collapsing measurements across time. We show the superiority of our deep learning model for the task of classifying people with Parkinson’s disease as distinct from healthy controls. |
| first_indexed | 2024-03-09T15:16:48Z |
| format | Article |
| id | doaj.art-a5a8fcb059ba40419521d1b1842cd2f4 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:16:48Z |
| publishDate | 2023-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a5a8fcb059ba40419521d1b1842cd2f42023-11-26T13:04:44ZengNature PortfolioScientific Reports2045-23222023-11-011311910.1038/s41598-023-47568-wA machine learning method to process voice samples for identification of Parkinson’s diseaseAnu Iyer0Aaron Kemp1Yasir Rahmatallah2Lakshmi Pillai3Aliyah Glover4Fred Prior5Linda Larson-Prior6Tuhin Virmani7Georgia Institute of TechnologyBiomedical Informatics, University of Arkansas for Medical SciencesBiomedical Informatics, University of Arkansas for Medical SciencesNeurology, University of Arkansas for Medical SciencesNeurology, University of Arkansas for Medical SciencesBiomedical Informatics, University of Arkansas for Medical SciencesBiomedical Informatics, University of Arkansas for Medical SciencesBiomedical Informatics, University of Arkansas for Medical SciencesAbstract Machine learning approaches have been used for the automatic detection of Parkinson’s disease with voice recordings being the most used data type due to the simple and non-invasive nature of acquiring such data. Although voice recordings captured via telephone or mobile devices allow much easier and wider access for data collection, current conflicting performance results limit their clinical applicability. This study has two novel contributions. First, we show the reliability of personal telephone-collected voice recordings of the sustained vowel /a/ in natural settings by collecting samples from 50 people with specialist-diagnosed Parkinson’s disease and 50 healthy controls and applying machine learning classification with voice features related to phonation. Second, we utilize a novel application of a pre-trained convolutional neural network (Inception V3) with transfer learning to analyze the spectrograms of the sustained vowel from these samples. This approach considers speech intensity estimates across time and frequency scales rather than collapsing measurements across time. We show the superiority of our deep learning model for the task of classifying people with Parkinson’s disease as distinct from healthy controls.https://doi.org/10.1038/s41598-023-47568-w |
| spellingShingle | Anu Iyer Aaron Kemp Yasir Rahmatallah Lakshmi Pillai Aliyah Glover Fred Prior Linda Larson-Prior Tuhin Virmani A machine learning method to process voice samples for identification of Parkinson’s disease Scientific Reports |
| title | A machine learning method to process voice samples for identification of Parkinson’s disease |
| title_full | A machine learning method to process voice samples for identification of Parkinson’s disease |
| title_fullStr | A machine learning method to process voice samples for identification of Parkinson’s disease |
| title_full_unstemmed | A machine learning method to process voice samples for identification of Parkinson’s disease |
| title_short | A machine learning method to process voice samples for identification of Parkinson’s disease |
| title_sort | machine learning method to process voice samples for identification of parkinson s disease |
| url | https://doi.org/10.1038/s41598-023-47568-w |
| work_keys_str_mv | AT anuiyer amachinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT aaronkemp amachinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT yasirrahmatallah amachinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT lakshmipillai amachinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT aliyahglover amachinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT fredprior amachinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT lindalarsonprior amachinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT tuhinvirmani amachinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT anuiyer machinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT aaronkemp machinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT yasirrahmatallah machinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT lakshmipillai machinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT aliyahglover machinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT fredprior machinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT lindalarsonprior machinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease AT tuhinvirmani machinelearningmethodtoprocessvoicesamplesforidentificationofparkinsonsdisease |