Abstract
We present an assessment of the practical value of existing traditional and non-standard measures for discriminating healthy people from people with Parkinson?s disease (PD) by detecting dysphonia. We introduce a new measure of dysphonia, Pitch Period Entropy (PPE), which is robust to many uncontrollable confounding effects including noisy acoustic environments and normal, healthy variations in voice frequency. We collected sustained phonations from 31 people, 23 with PD. We then selected 10 highly uncorrelated measures, and an exhaustive search of all possible combinations of these measures finds four that in combination lead to overall correct classification performance of 91.4%, using a kernel support vector machine. In conclusion, we find that non-standard methods in combination with traditional harmonics-to-noise ratios are best able to separate healthy from PD subjects. The selected non-standard methods are robust to many uncontrollable variations in acoustic environment and individual subjects, and are thus well-suited to telemonitoring applications.
Similar content being viewed by others
Article PDF
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Little, M., McSharry, P., Hunter, E. et al. Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease. Nat Prec (2008). https://doi.org/10.1038/npre.2008.2298.1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/npre.2008.2298.1
Keywords
This article is cited by
-
Binary Hybrid Artificial Hummingbird with Flower Pollination Algorithm for Feature Selection in Parkinson’s Disease Diagnosis
Journal of Bionic Engineering (2024)
-
Hybrid CNN-LSTM model with efficient hyperparameter tuning for prediction of Parkinson’s disease
Scientific Reports (2023)
-
The ForEx++ based decision tree ensemble approach for robust detection of Parkinson’s disease
Journal of Ambient Intelligence and Humanized Computing (2023)
-
Artificial Intelligence Model for Parkinson Disease Detection Using Machine Learning Algorithms
Biomedical Materials & Devices (2023)