Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Interpretable Parkinson's Disease Detection Using Group-Wise Scaling

Momeni, Niloofar LU orcid ; Whitling, Susanna LU and Jakobsson, Andreas LU orcid (2025) In IEEE Access 13. p.29147-29161
Abstract

This study is aimed at detecting Parkinson's disease by analyzing voice measurements made using a mobile phone. The key objectives include creating a model that ensures accurate predictions while maintaining interpretability, consistent with the existing literature on Parkinson's disease. We introduce a novel group-wise scaling method to address typical age and biological sex biases in the datasets, demonstrating 9.5% improvement over conventional scaling for three publicly available data sets. We also show the importance of evaluating the developed model on unseen individuals to achieve reliable classification results. The developed model is shown to offer an accuracy of 82% for unseen individuals, surpassing current state-of-the-art... (More)

This study is aimed at detecting Parkinson's disease by analyzing voice measurements made using a mobile phone. The key objectives include creating a model that ensures accurate predictions while maintaining interpretability, consistent with the existing literature on Parkinson's disease. We introduce a novel group-wise scaling method to address typical age and biological sex biases in the datasets, demonstrating 9.5% improvement over conventional scaling for three publicly available data sets. We also show the importance of evaluating the developed model on unseen individuals to achieve reliable classification results. The developed model is shown to offer an accuracy of 82% for unseen individuals, surpassing current state-of-the-art approaches. Furthermore, we offer insights into the decision-making of the model using Shapley additive explanation values. Our analysis reveals that shorter and less variable voiced segments and more variable unvoiced segments, suggesting a monotone voice pattern with frequent pauses, increase the likelihood of classifying the voice as a Parkinson's disease voice. Additionally, greater variability and rate of voiced segments, low variability of unvoiced segments, higher pitch variation, and spectral flux, suggesting continuous phonation and dynamic modulation, correlate with healthy voices. These features align well with the relevant medical literature, confirming our results. The significance of our proposed model lies in its generalizability and reliability for Parkinson's disease detection, potentially decelerating disease progression, reducing healthcare costs, and improving quality of life for patients.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
age and sex bias, mPower database, Parkinson's disease detection, vocal features interpretability, voice anomaly detection
in
IEEE Access
volume
13
pages
15 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • scopus:85217947331
ISSN
2169-3536
DOI
10.1109/ACCESS.2025.3540600
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2013 IEEE.
id
dc4a5f85-8458-42fe-93ce-1e43b6b2d877
date added to LUP
2025-07-04 14:15:53
date last changed
2025-07-04 14:17:14
@article{dc4a5f85-8458-42fe-93ce-1e43b6b2d877,
  abstract     = {{<p>This study is aimed at detecting Parkinson's disease by analyzing voice measurements made using a mobile phone. The key objectives include creating a model that ensures accurate predictions while maintaining interpretability, consistent with the existing literature on Parkinson's disease. We introduce a novel group-wise scaling method to address typical age and biological sex biases in the datasets, demonstrating 9.5% improvement over conventional scaling for three publicly available data sets. We also show the importance of evaluating the developed model on unseen individuals to achieve reliable classification results. The developed model is shown to offer an accuracy of 82% for unseen individuals, surpassing current state-of-the-art approaches. Furthermore, we offer insights into the decision-making of the model using Shapley additive explanation values. Our analysis reveals that shorter and less variable voiced segments and more variable unvoiced segments, suggesting a monotone voice pattern with frequent pauses, increase the likelihood of classifying the voice as a Parkinson's disease voice. Additionally, greater variability and rate of voiced segments, low variability of unvoiced segments, higher pitch variation, and spectral flux, suggesting continuous phonation and dynamic modulation, correlate with healthy voices. These features align well with the relevant medical literature, confirming our results. The significance of our proposed model lies in its generalizability and reliability for Parkinson's disease detection, potentially decelerating disease progression, reducing healthcare costs, and improving quality of life for patients.</p>}},
  author       = {{Momeni, Niloofar and Whitling, Susanna and Jakobsson, Andreas}},
  issn         = {{2169-3536}},
  keywords     = {{age and sex bias; mPower database; Parkinson's disease detection; vocal features interpretability; voice anomaly detection}},
  language     = {{eng}},
  pages        = {{29147--29161}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Access}},
  title        = {{Interpretable Parkinson's Disease Detection Using Group-Wise Scaling}},
  url          = {{http://dx.doi.org/10.1109/ACCESS.2025.3540600}},
  doi          = {{10.1109/ACCESS.2025.3540600}},
  volume       = {{13}},
  year         = {{2025}},
}