IT Diagnostics of Parkinson’s Disease Based on the Analysis of Voice Markers and Machine Learning
https://doi.org/10.35596/1729-7648-2023-21-3-102-110
Abstract
The results of studying the parameters of the spectra of speech signals by machine learning with the use of neural networks are presented. This study was carried out in order to confirm experimentally the possibility of performing an assessment of these parameters for the detection of Parkinson’s disease in the early stages (IT diagnostics). During the study, the public database was used, which systematized the spectra of vowel sounds uttered by patients with Parkinson’s disease. The applied method is binary data classification. In the course of the study, the speech data spectrum was first preprocessed, which consisted of filtering it in order to remove its noise components and eliminate bursts and gaps in it. Then the parameters of the processed spectrum of speech data were determined: average value, maximum and minimum, peak, wavelet coefficients, MFCC and TQWT. After that, the object was selected using the PCA algorithm. The model was trained using the Knn and Random Forest algorithms, as well as the Bayesian neural network. The Bayesian optimization algorithm and the GridSearch method were used to find the best model hyperparameters. It has been established that when using Knn, Random Forest and Bayesian neural network, it is possible to increase the accuracy of recognition of Parkinson’s disease by 94.7; 88.16 and 74.74 %, respectively. A similar study by other scientists showed that the recognition accuracy of data sets was only 86 %.
About the Authors
U. A. Vishniakou
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Vishniakou Uladzimir Anatolievich, Dr. of Sci. (Tech.), Professor at the Department of Infocommunication Technologies
220013, Minsk, P. Brovki St., 6
Tel.: +375 44 486-71-82
Xia YiWei
Belarusian State University of Informatics and Radioelectronics
Belarus
Belarus
Postgraduate at the Department of Infocommunication Technologies
Minsk
References
1. Davie C. A. (2008) A Review of Parkinson’s Disease. British Medical Bulletin. 86 (1), 109‒127.
2. Braak H., Ghebremedhin E., Rüb U., Bratzke H., Del Tredici K. (2004) Stages in the Development of Parkinson’s Disease-Related Pathology. Cell and Tissue Research. 318 (1), 121‒134.
3. Upadhya S. S., Cheeran A. N. (2018) Discriminating Parkinson and Healthy People Using Phonation and Cepstral Features of Speech. Computer Science. 143, 197‒202.
4. Putri F., Caesarendra W., Pamanasari E. D., Ariyanto M., Setiawan J. D. (2018) Parkinson Disease Detection Based on Voice and EMG Pattern Classification Method for Indonesian Case Study. Journal of Energy, Mechanical, Material, and Manufacturing Engineering. 3 (2), 87‒98.
5. Zhang M. L., Zhou Z. H. (2007) ML-KNN: a Lazy Learning Approach to Multi-Label Learning. Pattern Recognition. 40 (7), 2038‒2048.
6. Palimkar P., Shaw R. N., Ghosh A. (2022) Machine Learning Technique to Prognosis Diabetes Disease: Random Forest Classifier Approach. Advanced Computing and Intelligent Technologies. Springer, Singapore. 219–244.
7. Kareem S. W, Alyousuf F. Q., Ahmad K., Hawezi R., Awla H. (2022) Structure Learning of Bayesian Network: a Review. Qalaai Zanist Journal. 7 (1), 956‒975.
8. Sakar C. O., Serbes G., Gunduz A., Tunc H. C., Nizam H. (2019) A Comparative Analysis of Speech Signal Processing Algorithms for Parkinson’s Disease Classification and the Use of the Tunable Q-Factor Wavelet Transform. Applied Soft Computing. 74 (4), 255‒263.
9. Upadhya S. S., Cheeran A. N., Nirmal J. H. (2017) Statistical Comparison of Jitter and Shimmer Voice Features for Healthy and Parkinson Affected Persons. Electrical, Computer and Communication Technologies. IEEE. 1‒6.
10. Holmes J. R., Oates M. J., Phyland J. D., Hughes J. A. (2000) Voice Characteristics in the Progression of Parkinson’s Disease. International Journal of Language & Communication Disorders. 35 (3), 407‒418.
11. Abdurrahman G., Sintawati M. (2020) Implementation of Xgboost for Classification of Parkinson’s Disease. Journal of Physics. 1538 (1), 1‒12.
12. Tsanas A., Little M., McSharry P. E., Ramig L. O. (2010) New Nonlinear Markers and Insights into Speech Signal Degradation for Effective Tracking of Parkinson’s Disease Symptom Severity. NOLTA, Poland. 457–460.
13. Erdogdu S. B., Serbes G., Sakar C. O. (2017) Analyzing the Effectiveness of Vocal Features in Early Telediagnosis of Parkinson’s Disease. PloS One. 12 (8), 1‒18.
14. Selesnick I. W. (2011) Wavelet Transform with Tunable Q-Factor. IEEE Transactions on Signal Processing. 59 (8), 3560‒3575.
15. Visa S., Ramsay B., Ralescu A. L., Esther van der Knaap (2011) Confusion Matrix-Based Feature Selection. Artificial Intelligence and Cognitive Science. 710 (1), 120‒127.
16. Maćkiewicz A., Ratajczak W. (1993) Principal Components Analysis (PCA). Computers & Geosciences. 19 (3), 303‒342.
17. Fawcett T. (2006) An Introduction to ROC Analysis. Pattern Recognition Letters. 27 (8), 861‒874.
Review
For citations:
Vishniakou U.A., YiWei X. IT Diagnostics of Parkinson’s Disease Based on the Analysis of Voice Markers and Machine Learning. Doklady BGUIR. 2023;21(3):102-110. https://doi.org/10.35596/1729-7648-2023-21-3-102-110
Views: 359
Email this article 