A Speech Signal Processing Approach for Early Detection of Parkinson's Disease
(2024) In Bachelor's Theses in Mathematical Sciences FMSL01 20241Mathematical Statistics
- Abstract
- Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterised by motor and non-motor symptoms, including significant speech impairments. Early and accurate diagnosis is crucial for effective management and treatment. However, traditional diagnostic methods are often limited because they rely on subjective assessments and only detect symptoms after they have become noticeable. This thesis explores the use of vowel articulation as a biomarker for detecting Parkinson’s disease, utilising acoustic analysis and machine learning techniques to create a predictive model. The study uses a dataset of speech recordings from individuals with and without PD, collected through Voice Diagnostics. Through a preprocessing and feature... (More)
- Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterised by motor and non-motor symptoms, including significant speech impairments. Early and accurate diagnosis is crucial for effective management and treatment. However, traditional diagnostic methods are often limited because they rely on subjective assessments and only detect symptoms after they have become noticeable. This thesis explores the use of vowel articulation as a biomarker for detecting Parkinson’s disease, utilising acoustic analysis and machine learning techniques to create a predictive model. The study uses a dataset of speech recordings from individuals with and without PD, collected through Voice Diagnostics. Through a preprocessing and feature extraction process, relevant acoustic features are analysed. These features are then used to train a XGBoost machine learning model. The performance of the model is evaluated using metrics such as accuracy and the features were selected with the use of RFECV and Shapley scores. Results indicate model based on features from short form vowel extraction perform worse than previous work where longer vowel sounds were used. The model could not effectively distinguish between PD and non-PD speech patterns. The model achieves a moderately high classification accuracy on test data demonstrating the feasibility of this approach for PD diagnosis but lacks in reliability due to high variance in cross validation measurements. The findings suggest that, at this stage, integrating vowel sound analysis based on natural sentences into clinical practice does not improve early PD detection compared to previous work. Further work is required before this method can be used as a non-invasive and objective diagnostic tool. This research contributes to the growing body of literature on speech-based diagnostics and underscores the potential of machine learning in healthcare. Future work could expand on these findings by exploring larger datasets, additional acoustic features, and the application of this methodology to other neurological disorders. (Less)
- Popular Abstract
- Could your voice reveal early signs of Parkinson's disease? Scientists have been working on an innovative way to detect this brain disorder by analyzing how people pronounce vowels during normal speech. Think of it like a high-tech hearing test that picks up subtle changes in speech that might signal Parkinson's before other symptoms become obvious.
Currently, diagnosing Parkinson's often relies on doctors observing visible symptoms, which typically appear only after the disease has progressed. But what if we could spot it earlier? Using mathematical analysis and machine learning, researchers examined speech recordings from people with and without Parkinson's to see if there were telltale differences in how they pronounced vowels.
... (More) - Could your voice reveal early signs of Parkinson's disease? Scientists have been working on an innovative way to detect this brain disorder by analyzing how people pronounce vowels during normal speech. Think of it like a high-tech hearing test that picks up subtle changes in speech that might signal Parkinson's before other symptoms become obvious.
Currently, diagnosing Parkinson's often relies on doctors observing visible symptoms, which typically appear only after the disease has progressed. But what if we could spot it earlier? Using mathematical analysis and machine learning, researchers examined speech recordings from people with and without Parkinson's to see if there were telltale differences in how they pronounced vowels.
The analysis showed very little promise in identifying Parkinson's, most likely due to the low sample size. Previous studies that used longer vowel sounds were much more reliable. The results suggest that analyzing quick vowel sounds from everyday sentences isn't yet ready for use in real life scenarios. However, this research opens up exciting possibilities for developing better diagnostic tools that are both painless and objective. Future studies could explore this approach with larger groups of people.
This reimagined way of diagnosis could one day be as simple as having a conversation with your doctor although more research is needed before we get there. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9178588
- author
- Mattisson, Philip LU and Samuelsson Forsdik, Fanny
- supervisor
- organization
- course
- FMSL01 20241
- year
- 2024
- type
- M2 - Bachelor Degree
- subject
- keywords
- Machine learning, Mathematical statistics, Parkinson's Disease, Vocal features
- publication/series
- Bachelor's Theses in Mathematical Sciences
- report number
- LUTFMS-4015-2024
- ISSN
- 1654-6229
- other publication id
- 2024:K22
- language
- English
- id
- 9178588
- date added to LUP
- 2024-12-12 15:38:28
- date last changed
- 2025-01-21 13:05:17
@misc{9178588,
abstract = {{Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterised by motor and non-motor symptoms, including significant speech impairments. Early and accurate diagnosis is crucial for effective management and treatment. However, traditional diagnostic methods are often limited because they rely on subjective assessments and only detect symptoms after they have become noticeable. This thesis explores the use of vowel articulation as a biomarker for detecting Parkinson’s disease, utilising acoustic analysis and machine learning techniques to create a predictive model. The study uses a dataset of speech recordings from individuals with and without PD, collected through Voice Diagnostics. Through a preprocessing and feature extraction process, relevant acoustic features are analysed. These features are then used to train a XGBoost machine learning model. The performance of the model is evaluated using metrics such as accuracy and the features were selected with the use of RFECV and Shapley scores. Results indicate model based on features from short form vowel extraction perform worse than previous work where longer vowel sounds were used. The model could not effectively distinguish between PD and non-PD speech patterns. The model achieves a moderately high classification accuracy on test data demonstrating the feasibility of this approach for PD diagnosis but lacks in reliability due to high variance in cross validation measurements. The findings suggest that, at this stage, integrating vowel sound analysis based on natural sentences into clinical practice does not improve early PD detection compared to previous work. Further work is required before this method can be used as a non-invasive and objective diagnostic tool. This research contributes to the growing body of literature on speech-based diagnostics and underscores the potential of machine learning in healthcare. Future work could expand on these findings by exploring larger datasets, additional acoustic features, and the application of this methodology to other neurological disorders.}},
author = {{Mattisson, Philip and Samuelsson Forsdik, Fanny}},
issn = {{1654-6229}},
language = {{eng}},
note = {{Student Paper}},
series = {{Bachelor's Theses in Mathematical Sciences}},
title = {{A Speech Signal Processing Approach for Early Detection of Parkinson's Disease}},
year = {{2024}},
}