Research Article

Classification of Parkinson’s Disease using Speech Signal with Machine Learning and Deep Learning Approaches

Senjuti Rahman
Ahsanullah University of Science and Technology, Bangladesh.
* Corresponding author
Mehedi Hasan
Rajshahi University of Engineering & Technology, Bangladesh
Ajay Krishno Sarkar
Rajshahi University of Engineering & Technology, Bangladesh
Fayez Khan
Military Institute of Science and Technology (MIST), Bangladesh
DOI icon 10.24018/ejece.2023.7.2.488

Read Counter
2360

Downloads
1285

Citations

Share

Article Sidebar

Submitted 2022-12-10
Published 2023-03-21

Read counter = 2360 times

Table of Contents

Article Main Content

Parkinson's disease (PD) is a chronic neurological condition that is growing in prevalence and manifests both motor and non-motor symptoms. Most PD patients have trouble speaking, writing, and walking during the early stages of the disease. Analysis of speech problems has been effective in identifying Parkinson's disease. According to studies, 90% of Parkinson's disease patients experience speech problems. Even though there is no known cure for Parkinson's disease, using the right medication at an early stage can greatly reduce the symptoms. One of the key categorization issues for the diagnosis of Parkinson's disease is the correct interpretation of speech signals. The major goal of this project is to use deep learning and machine learning approaches to predict and categorize PD patients at an early stage. A trustworthy dataset from the UCI repository for Parkinson disease has been used to evaluate the method's performance. Several classification models are successfully used in this study for classification tasks, including Extreme Gradient Boosting (XGBoost), Ada Boost, Light Gradient Boosting Machine, CatBoost, Gradient Boosting, Random Forest, Ridge, Decision Tree, Logistic Regression, K Neighbors, SVM - Linear Kernel, Naive Bayes, and deep neural networks (DNN1, DNN2, DNN3). The Extreme Gradient Boosting classifier achieved the greatest classification accuracy of 92.18% (among the machine learning classifiers). By using the chosen features as input, the three layer deep neural network (DNN2) has the best accuracy of 95.41% amongst deep learning techniques. The collected results indicate that deep neural networks performed better than machine learning methods.
Keywords: Classification Deep Neural Network Extreme Gradient Boosting Machine Learning Algorithms Parkinson’s Disease

References

  1. Jankovic J. Parkinson?s disease:Clinical features and diagnosis. Journal of neurology, neurosurgery, and psychiatry, 2007:79(4):368?376. doi: 10.1136/jnnp.2007.131045.
     Google Scholar
  2. Sakar CO, Serbes G, Gunduz A, Tunc HC, Nizam H, Sakar H, Tutuncu M, Aydin T, Isenkul ME, Apaydin HA comparative analysis of speech signal processing algorithms for parkinson?s diseaseclassification and the use of the tunable q-factor wavelet transform. Applied Soft Computing. vol. 2019;74:255?263. doi: 10.1016/j.asoc.2018.10.022.
     Google Scholar
  3. Singh N, Pillay V, Choonara YE. Advances in the treatment of Parkinson?s disease. Progress in Neurobiology. 2007;8:29?44. doi: 10.1016/j.pneurobio.2006.11.009.
     Google Scholar
  4. Camara C, Isasi P, Warwick K, Ruiz V, Aziz T.et al. Resting tremor classification and detection in Parkinson?s disease patients. Biomedical Signal Processing and Control. 2015;16:88?97. doi: 10.1016/j.bspc.2014.09.006.
     Google Scholar
  5. Adams W. R. High-accuracy detection of early Parkinson?s Disease using multiple characteristics of finger movement while typing. PLOS ONE. Nov 2017;12(11). doi: 10.1371/journal.pone.0188226.
     Google Scholar
  6. Ma H, Tan T, Zhou H, Gao T. Support Vector Machine-recursive feature elimination for the diagnosis of Parkinson disease based on speech analysis. In Seventh International Conference on Intelligent Control and Information Processing (ICICIP), pp. 34?40, Dec. 2016.
     Google Scholar
  7. Nuvoli S, Spanu A, Fravolini ML, Bianconi F, Cascianelli S, Madeddu G, Palumbo B. [123I]Metaiodobenzylguanidine (MIBG) Cardiac Scintigraphy and Automated Classification Techniques in Parkinsonian Disorders. Molecular Imaging and Biology, 2020; 22(3): 703?710. https://doi.org/10.1007/s11307-019-01406-6.
     Google Scholar
  8. Maass F. et al. Elemental fingerprint: Reassessment of a cerebrospinal fluid biomarker for Parkinson?s disease. Neurobiology of Disease. Feb. 2020;134:104677. doi: 10.1016/j.nbd.2019.104677.
     Google Scholar
  9. Mostafa SA, Mustapha A, Mohammed MA, Hamed RI, Arunkumar N. et al. Examining multiple feature evaluation and classification methods for improving the diagnosis of Parkinson?s disease. Cognitive Systems Research. 2019;54:90?99. doi: 10.1016/j.cogsys.2018.12.004.
     Google Scholar
  10. Braga D, Madureira AM, Coelho L, Ajith R. Automatic detection of Parkinson?s disease based on acoustic analysis of speech. Eng Appl Artif Intell. 2019; 77:148-158. doi: 10.1016/j.engappai.2018.09.018.
     Google Scholar
  11. Haq A, li JP, Memon MH, Khan J, Malik A, Ahmad T, Ali A, Nazir S, Ahad I, and Shahid M. Feature selection based on L1-Norm Support Vector Machine and Effective Recognition System for Parkinson?s disease using voice recordings. IEEE Access, pp. 37718 ? 37734, vol. 7, 2019.
     Google Scholar
  12. Nissar I, Rizvi D.R, Masood S, and Mir A. Voice-based detection of Parkinson?s disease through ensemble machine learning approach: A Performance study. Phat. 19(19): e2. 2020;5:1-8. doi: 10.4108/eai.13-7-2018.162806.
     Google Scholar
  13. Asmae O, Abdelhadi R, Bouchaib C, Sara S, Tajeddine K. Parkinson?s disease identification using KNN and ANN Algorithms based on Voice Disorder. 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), pp. 1 ? 6, Apr. 2020.
     Google Scholar
  14. Senturk ZK. Early diagnosis of Parkinson?s disease using machine learning algorithms. Medical Hypotheses. May 2020;138:109603. doi: 10.1016/j.mehy.2020.109603.
     Google Scholar
  15. Mir WA, Izharuddin, Nissar I. Contribution of Application of Deep Learning Approaches on Biomedical Data in the Diagnosis of Neurological Disorders: A Review on Recent Findings. Communications in computer and information science (CCIS), 2020:87-97. DOI: 10.1007/978-981-15-3666-3_8.
     Google Scholar
  16. Frid A, Kantor A, Svechin D, Manevitz L. M. Diagnosis of Parkinson?s disease from continuous speech using deep convolutional networks without manual selection of features. IEEE International Conference on the Science of Electrical Engineering (ICSEE), 2016: 1? 6.
     Google Scholar
  17. Caliskan A, Badem H, Basturk A, Yuksel M .E. Diagnosis of the Parkinson disease by using deep neural network classifier. Istanbul Univ - J Electr Electron Eng. 2017;17(2);3311-3318.
     Google Scholar
  18. Little MA, McSharry PE, Roberts SJ, Costello DAE, Moroz IM. Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection. Biomedical Engineering Online, Jul. 2007;6(1);23. DOI: 10.1186/1475-925X-6-23.
     Google Scholar
  19. Wasif T, Hossain MIU, Mahmud A. Parkinson disease prediction using feature selection technique in machine learning. 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp. 1-5, 2021.
     Google Scholar
  20. Nissar I, Mir WA, Izharuddin, Shaikh TA. Machine Learning Approaches for Detection and Diagnosis of Parkinson?s Disease - A Review. 7th International Conference on Advanced Computing and Communication Systems (ICACCS), pp. 898-905, 2021.
     Google Scholar
  21. Aiello S, Cliff C, Roark H, Rehak L, Stetsenko P, and Bartz A. Machine Learning with Python and H2O. H2O. ai Inc, 2017.
     Google Scholar
  22. Powers DMW. Evaluation: from Precision, Recall and F-measure to ROC, Informedness, Markedness and Correlation. arXiv: Learning, Dec. 2011;2(1):37. doi: 10.48550/arXiv.2010.16061.
     Google Scholar
  23. Das R. A comparison of multiple classification methods for diagnosis of parkinson disease. Expert Systems with Applications, 2010:37(2):1568?1572.
     Google Scholar
  24. Celik E, Omurca SI. Improving Parkinson?s disease diagnosis with machine learning methods. in Scientific Meeting on Electrical,Electronics & Biomedical Engineering and Computer Science (EBBT) (Istanbul), pp. 1?4, 2019.
     Google Scholar
  25. Dinesh A, He J. Using machine learning to diagnose Parkinson?s disease from voice recordings. in IEEE MIT Undergraduate Research Technology Conference (URTC) (Cambridge, MA),pp. 1?4, 2017.
     Google Scholar
  26. Senturk ZK. Early diagnosis of Parkinson?s disease using machine learning algorithms. Medical Hypotheses, May 2020;138:109603. doi: 10.1016/j.mehy.2020.109603.
     Google Scholar
  27. Shahsavari MK, Rashidi H, Bakhsh HR. Efficient classification of Parkinson?s disease using extreme learning machine and hybrid particle swarm optimization. in 4th International Conference on Control, Instrumentation, and Automation (ICCIA) (Qazvin), pp. 148?154, 2016.
     Google Scholar
  28. Yaman O, Ertam F, Tuncer T. Automated Parkinson?s disease recognition based on statistical pooling method using acoustic features. Medical Hypotheses, Feb. 2020;135:109483. doi: 10.1016/j.mehy.2019.109483.
     Google Scholar
  29. Prince J, Andreotti F, Vos MD. Multi-Source Ensemble Learning for the Remote Prediction of Parkinson?s Disease in the Presence of Source-Wise Missing Data. IEEE Transactions on Biomedical Engineering, 2019;66(5):1402. doi: 10.1109/TBME.2018.2873252.
     Google Scholar
  30. Vlachostergiou A, Tagaris A, Stafylopatis A, Kollias S. Multitask learning for predicting Parkinson?s disease based on medical imaging information, in 25th IEEE International Conference on Image Processing (ICIP), pp. 2052?2056, 2018, Athens.
     Google Scholar
  31. Tracy M, ?zkanca Y, Atkins DC, Ghomi HR. Investigating voice as a biomarker: Deep phenotyping methods for early detection of Parkinson?s disease. J. Biomed. Informat., Apr. 2020;104(103362). doi: 10.1016/j.jbi.2019.103362.
     Google Scholar