About this article
- Submitted: Nov 28, 2025
- Final Revised: May 12, 2026
- Accepted: Jun 08, 2026
- Published: Jun 30, 2026
- Abstract view: 10
- PDF Download: 1
- Volumes: Vol. 4 No. 1 (2026) Pages 43-56
- DOI: 10.63208/21018-241
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright (c) 2026 Author(s)
Cite this article
Abstract
Parkinson’s disease (PD) is a progressive neurodegenerative condition characterized by dopamine depletion in the substantia nigra, which manifests through motor impairments and distinct vocal alterations. Recognizing temporal speech variations as critical biomarkers, this study proposes an optimized Convolutional Neural Network (CNN) framework for the early and precise detection of PD. Utilizing a dataset comprising 195 individuals (147 PD patients and 48 healthy controls), the research implements an advanced preprocessing pipeline involving signal denoising, feature normalization, and Bayesian hyperparameter optimization to refine classification efficiency. Experimental results demonstrate that the CNN classifier achieves a superior diagnostic accuracy of 96.85%, complemented by high sensitivity and a robust F1 score. The model maintains consistent predictive reliability even under suboptimal acoustic conditions, highlighting its capability to identify disease-specific vocal signatures effectively. These findings underscore the potential of the proposed deep learning architecture as a scalable clinical tool for early PD screening, facilitating timely therapeutic interventions and improved patient management within integrated diagnostic workflows.
References
Little, Max Parkinsons, UCI Mach. Learn. Repository, 2008, doi: 10.24432/C59C74.
A. Suppa, G. Costantini, F. Asci, P. Di Leo, M. S. Al-Wardat, G. Di Lazzaro, S. Scalise, A. Pisani, and G. Saggio, “Voice in Parkinson's disease: A machine learning study,” Frontiers Neurol., vol. 13, pp. 55–62, Feb. 2022, doi: 10.3389/fneur.2022.831428.
J. S. Almeida, P. P. Rebouças Filho, T. Carneiro, W. Wei, R. Damaševičius, R. Maskeliunas, and V. H. C. de Albuquerque, “Detecting Parkinson's disease with sustained phonation and speech signals using machine learning techniques,” Pattern Recognit. Lett., vol. 125, pp. 55–62, Jul. 2019, doi: 10.1016/j.patrec.2019.04.005.
L. dos Santos Viana and C. Fantin, “Evolution of mortality due to Parkinson's disease in the capitals of the Brazilian states in the period from 2010 to 2019,” J. Pharmacy Pharmacol., vol. 9, no. 8, pp. 263–272, Jul. 2021.
A. C. Tillmann, “The impact of Brazilian samba on Parkinson's disease: Analysis by the disease subtypes,” Revista Brasileira de Medicina do Esporte, vol. 26, pp. 25–29, Jul. 2020.
B. L. Santos-Lobato, “Genetics of Parkinson's disease in Brazil: A systematic review of monogenic forms,” Arquivos de Neuro-Psiquiatria, vol. 79, pp. 612–623, Jun. 2021.
L. M. Andreis, M. Mariano, L. W. L. Silva, C. D. Bianco, and F. R. Neto, “The impact of Parkinson's disease on general and specific motor aptitudes: A study of older Brazilian adults,” Perceptual Motor Skills, vol. 129, no. 2, pp. 253–268, Apr. 2022.
D. V. Nassif and J. S. Pereira, “Fatigue in Brazilian patients with Parkinson's disease,” Dementia Neuropsychologia, vol. 16, no. 2, pp. 237–242, Jun. 2022.
C. R. Rieder, “Cannabidiol in Parkinson's disease,” Brazilian J. Psychiatry, vol. 42, pp. 126–127, Sep. 2020.
R. A. Saba, “Guidelines for Parkinson's disease treatment: Consensus from the movement disorders scientific department of the Brazilian academy of neurology-motor symptoms,” Arquivos de Neuro-Psiquiatria, vol. 80, pp. 316–329, Aug. 2022.
A. C. Tillmann, “Feasibility of a Brazilian samba protocol for patients with Parkinson's disease: A clinical non-randomized study,” Arquivos de Neuro-Psiquiatria, vol. 78, pp. 13–20, Aug. 2020.
I. Tougui, A. Jilbab, and J. E. Mhamdi, “Machine learning smart system for Parkinson disease classification using the voice as a biomarker,” Healthcare Informat. Res., vol. 28, no. 3, pp. 210–221, Jul. 2022.
Y. Ozkanca, M. Göksu Öztürk, M. N. Ekmekci, D. C. Atkins, C. Demiroglu, and R. Hosseini Ghomi, “Depression screening from voice samples of patients affected by Parkinson's disease,” Digit. Biomarkers, vol. 3, no. 2, pp. 72–82, Jun. 2019.
J. Mei, C. Desrosiers, and J. Frasnelli, “Machine learning for the diagnosis of Parkinson's disease: A review of literature,” Frontiers Aging Neurosci., vol. 13, May 2021, Art. no. 633752.
W. Wang, J. Lee, F. Harrou, and Y. Sun, “Early detection of Parkinson's disease using deep learning and machine learning,” IEEE Access, vol. 8, pp. 147635–147646, 2020.
S. Arora and L. Baghai-Ravary, “Voice-based detection of Parkinson's disease using convolutional neural networks,” 2019, arXiv:1905.10198.
H. Gunduz, “Deep learning-based Parkinson's disease classification using vocal feature sets,” IEEE Access, vol. 7, pp. 115540–115551, 2019.
C. Quan, K. Ren, and Z. Luo, “A deep learning based method for Parkinson's disease detection using dynamic features of speech,” IEEE Access, vol. 9, pp. 10239–10252, 2021.
R. Mathur, V. Pathak, and D. Bandil, “Parkinson's disease prediction using machine learning algorithm,” in Proc. Int. Conf. Power, Energy, Control Transmiss. Syst. (ICPECTS). Cham, Switzerland : Springer, Dec. 2019, pp. 357–363.
A. Tsanas, “A novel telemonitoring system for the assessment of voice and speech quality in Parkinson's disease,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 2, pp. 370–380, Feb. 2020.
N. Khan, “Deep learning in the detection of Parkinson's disease: A systematic review,” in Neurological Sciences. Cham, Switzerland : Springer, 2021.
S. Gaur, P. Kalani, and M. Mohan, “Harmonic-to-noise ratio as speech biomarker for fatigue: K-nearest neighbour machine learning algorithm,” Med. J. Armed Forces India, vol. 80, pp. S120–S126, Dec. 2024.
F. Amato, G. Saggio, V. Cesarini, G. Olmo, and G. Costantini, “Machine learning- and statistical-based voice analysis of Parkinson's disease patients: A survey,” Expert Syst. Appl., vol. 219, Jun. 2023, Art. no. 119651.
H. Byeon, “Comparing ensemble-based machine learning classifiers developed for distinguishing hypokinetic dysarthria from presbyphonia,” Appl. Sci., vol. 11, no. 5, p. 2235, Mar. 2021.
T. K. Redd, J. P. Campbell, J. M. Brown, S. J. Kim, S. Ostmo, R. V. P. Chan, J. Dy, D. Erdogmus, S. Ioannidis, J. Kalpathy-Cramer, and M. F. Chiang, “Evaluation of a deep learning image assessment system for detecting severe retinopathy of prematurity,” Brit. J. Ophthalmol., vol. 103, no. 5, pp. 580–584, May 2019.
H. W. Loh, W. Hong, C. P. Ooi, S. Chakraborty, P. D. Barua, R. C. Deo, J. Soar, E. E. Palmer, and U. R. Acharya, “Application of deep learning models for automated identification of Parkinson's disease: A review (2011–2021),” Sensors, vol. 21, no. 21, p. 7034, Oct. 2021.
G. Pahuja and B. Prasad, “Deep learning architectures for Parkinson's disease detection by using multi-modal features,” Comput. Biol. Med., vol. 146, Jul. 2022, Art. no. 105610.
M. Thakur, S. Dhanalakshmi, H. Kuresan, R. Senthil, R. Narayanamoorthi, and K. W. Lai, “Automated restricted Boltzmann machine classifier for early diagnosis of Parkinson's disease using digitized spiral drawings,” J. Ambient Intell. Humanized Comput., vol. 14, no. 1, pp. 175–189, Jan. 2023.
A. U. Haq, J. P. Li, B. L. Y. Agbley, C. B. Mawuli, Z. Ali, S. Nazir, and S. U. Din, “A survey of deep learning techniques based Parkinson's disease recognition methods employing clinical data,” Expert Syst. Appl., vol. 208, Dec. 2022, Art. no. 118045.
S. Shafiq, S. Ahmed, M. S. Kaiser, M. Mahmud, M. S. Hossain, and K. Andersson, “Comprehensive analysis of nature-inspired algorithms for Parkinson's disease diagnosis,” IEEE Access, vol. 11, pp. 1629–1653, 2023.
H. Shibata, Y. Uchida, S. Inui, H. Kan, K. Sakurai, N. Oishi, Y. Ueki, K. Oishi, and N. Matsukawa, “Machine learning trained with quantitative susceptibility mapping to detect mild cognitive impairment in Parkinson's disease,” Parkinsonism Rel. Disorders, vol. 94, pp. 104–110, Jan. 2022.
D. Hemmerling and M. Wojcik-Pedziwiatr, “Prediction and estimation of Parkinson's disease severity based on voice signal,” J. Voice, vol. 36, no. 3, pp. 439.e9–439.e20, May 2022, doi: 10.1016/j.jvoice.2020.06.004.
B. Karan, S. S. Sahu, J. R. Orozco-Arroyave, and K. Mahto, “Non-negative matrix factorization-based time-frequency feature extraction of voice signal for Parkinson's disease prediction,” Comput. Speech Lang., vol. 69, Sep. 2021, Art. no. 101216.
S. Arora and A. Tsanas, “Assessing Parkinson's disease at scale using telephone-recorded speech: Insights from the Parkinson's voice initiative,” Diagnostics, vol. 11, no. 10, p. 1892, Oct. 2021, doi: 10.3390/diagnostics11101892.
G. Solana-Lavalle and R. Rosas-Romero, “Analysis of voice as an assisting tool for detection of Parkinson's disease and its subsequent clinical interpretation,” Biomed. Signal Process. Control, vol. 66, Apr. 2021, Art. no. 102415.
J. M. Tracy, Y. Özkanca, D. C. Atkins, and R. H. Ghomi, “Investigating voice as a biomarker: Deep phenotyping methods for early detection of Parkinson's disease,” J. Biomed. Informat., vol. 104, Apr. 2020, Art. no. 103362.
N. P. Narendra, B. Schuller, and P. Alku, “The detection of Parkinson's disease from speech using voice source information,” IEEE/ACM Trans. Audio, Speech, Languages Process., vol. 29, pp. 1925–1936, 2021.
D. Kaya, “Automated gender-Parkinson's disease detection at the same time via a hybrid deep model using human voice,” Concurrency Comput., Pract. Exper., vol. 34, no. 26, pp. 119650–119660, Nov. 2022.
L. Moro-Velazquez, J. A. Gomez-Garcia, J. D. Arias-Londoño, N. Dehak, and J. I. Godino-Llorente, “Advances in Parkinson's disease detection and assessment using voice and speech: A review of the articulatory and phonatory aspects,” Biomed. Signal Process. Control, vol. 66, Apr. 2021, Art. no. 102418.
T. Zhang, L. Lin, and Z. Xue, “A voice feature extraction method based on fractional attribute topology for Parkinson's disease detection,” Expert Syst. Appl., vol. 219, Jun. 2023, Art. no. 119650.
O. Karaman, H. Çakin, A. Alhudhaif, and K. Polat, “Robust automated Parkinson disease detection based on voice signals with transfer learning,” Expert Syst. Appl., vol. 178, Sep. 2021, Art. no. 115013.
S. Lahmiri and A. Shmuel, “Detection of Parkinson's disease based on voice patterns ranking and optimized support vector machine,” Biomed. Signal Process. Control, vol. 49, pp. 427–433, Mar. 2019.
M. Hireš, M. Gazda, P. Drotár, N. D. Pah, M. A. Motin, and D. K. Kumar, “Convolutional neural network ensemble for Parkinson's disease detection from voice recordings,” Comput. Biol. Med., vol. 141, Feb. 2022, Art. no. 105021.
A. Ouhmida, A. Raihani, B. Cherradi, and O. Terrada, “A novel approach for Parkinson's disease detection based on voice classification and features selection techniques,” Int. J. Online Biomed. Eng., vol. 17, no. 10, pp. 111–130, Oct. 2021.
A. S. Ashour, M. K. A. Nour, K. Polat, Y. Guo, W. Alsaggaf, and A. El-Attar, “A novel framework of two successive feature selection levels using weight-based procedure for voice-loss detection in Parkinson's disease,” IEEE Access, vol. 8, pp. 76193–76203, 2020.
S. Singh and W. Xu, “Robust detection of Parkinson's disease using harvested smartphone voice data: A telemedicine approach,” Telemedicine E-Health, vol. 26, no. 3, pp. 327–334, Mar. 2020.
T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Cham, Switzerland : Springer, 2009.
L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Aug. 2016, pp. 785–794.
T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Trans. Inf. Theory, vol. IT-13, no. 1, pp. 21–27, Jan. 1967.
M. A. Little, P. E. McSharry, E. J. Hunter, J. Spielman, and L. O. Ramig, “Suitability of dysphonia measurements for telemonitoring of Parkinson's disease,” IEEE Trans. Biomed. Eng., vol. 56, no. 4, pp. 1015–1022, Apr. 2009.
J. G. Švec, P. S. Popolo, and I. R. Titze, “Medição de doses vocais na fala: Procedimento experimental e processamento de sinal,” Logopedia Phoniatrics Vocol., vol. 28, no. 4, pp. 181–192, May 2003.
J. P. Teixeira, D. Ferreira, and S. M. Carneiro, “Análise acústica vocal-determinação do Jitter e Shimmer para diagnóstico de patologias da fala,” in Proc. 6 Congresso Luso-Moçcambicano de Engenharia, 3 Congresso de Engenharia de Moçcambique, 2011, pp. 139–140.