Abstract
Objectives
This paper focuses on developing a regularization-based feature selection approach to select the most effective attributes from the Parkinson’s speech dataset. Parkinson’s disease is a medical condition that progresses as the dopamine-producing nerve cells are affected. Early diagnosis often reduces the effect on the individuals, minimizes the advancement over time. In recent times, intelligent computational models are used in many complex cases to diagnose a clinical condition with high precision. These models are intended to find meaningful representation from the data to diagnose the disease. Machine learning acts as a tool, gears up the model learning process through a mathematical baseline. But, not in all cases, machine learning will be demanded to perform optimally. It comes with a few constraints, mainly the representation of the data. The learning models expect a clean, noise-free input, which in-turns produces better discriminative patterns over different categories of classes.
Methods
The proposed model identified five candidate features as predictors. This feature subset is trained with different varieties of supervised classifiers to trace out the best-performing model.
Results
The results are validated through accuracy, precision, recall, and receiver’s operational characteristic curves. The proposed regularization- based feature selection model outperformed the benchmark algorithms by attaining 100% accuracy on most of the classifiers, other than linear discriminant analysis (99.90%) and naïve Bayes (99.51%).
Conclusions
This paper exhibits the need for intelligent models to analyze complex data patterns to assist medical practitioners in better disease diagnosis. The results exhibit that the regularization methods find the best features based on their importance score, which improved the model performance over other feature selection methods.
-
Research funding: No funding support.
-
Author contributions: Kamalakannan Kaliyan and Anandharaj Ganesan contributed equally.
-
Competing interests: Authors state no conflict of interest.
-
Informed consent: Informed consent was obtained from all individuals included in this study.
-
Ethical approval: Not applicable.
References
1. Marras, C, Beck, JC, Bower, JH, Roberts, E, Ritz, B, Ross, GW, et al.. Prevalence of Parkinson’s disease across North America. Npj Parkinson’s Dis 2018;4:1–7. https://doi.org/10.1038/s41531-018-0058-0.Search in Google Scholar PubMed PubMed Central
2. Ragothaman, M, Murgod, UA, Gururaj, G, Kumaraswamy, SD, Muthane, U. Lower risk of Parkinson’s disease in an admixed population of European and Indian origins. Mov Disord 2003;18:912–4. https://doi.org/10.1002/mds.10449.Search in Google Scholar PubMed
3. Gourie-Devi, M, Gururaj, G, Satishchandra, P, Subbakrishna, DK. Prevalence of neurological disorders in Bangalore, India: a community-based study with a comparison between urban and rural areas. Neuroepidemiology 2003;23:261–8. https://doi.org/10.1159/000080090.Search in Google Scholar PubMed
4. Surathi, P, Jhunjhunwala, K, Yadav, R, Pal, PK. Research in Parkinson’s disease in India: a review. Ann Indian Acad Neurol 2016;19:9–20. https://doi.org/10.4103/0972-2327.167713.Search in Google Scholar PubMed PubMed Central
5. Razdan, S, Kaul, RL, Motta, A, Kaul, S, Bhatt, RK. Prevalence and pattern of major neurological disorders in rural Kashmir (India) in 1986. Neuroepidemiology 1994;13:113–9. https://doi.org/10.1159/000110368.Search in Google Scholar PubMed
6. Braak, H, Ghebremedhin, E, Rüb, U, Bratzke, H, Del Tredici, K. Stages in the development of Parkinson’s disease-related pathology. Cell Tissue Res 2004;318:121–34. https://doi.org/10.1007/s00441-004-0956-9.Search in Google Scholar PubMed
7. Lewis, SJG, Foltynie, T, Blackwell, AD, Robbins, TW, Owen, AM, Barker, RA. Heterogeneity of Parkinson’s disease in the early clinical stages using a data driven approach. J Neurol Neurosurg Psychiatr 2005;76:343–8. https://doi.org/10.1136/jnnp.2003.033530.Search in Google Scholar PubMed PubMed Central
8. Brooks, DJ. Imaging approaches to Parkinson disease. J Nucl Med 2010;51:596–609. https://doi.org/10.2967/jnumed.108.059998.Search in Google Scholar PubMed
9. Armstrong, MJ, Okun, MS. Diagnosis and treatment of Parkinson disease: a review. JAMA 2020;323:548–60. https://doi.org/10.1001/jama.2019.22360.Search in Google Scholar PubMed
10. Pedrosa, DJ, Timmermann, L. Management of Parkinson’s disease. Neuropsychiatric Dis Treat 2013;9:321–40. https://doi.org/10.2147/ndt.s32302.Search in Google Scholar PubMed PubMed Central
11. Oh, SL, Hagiwara, Y, Raghavendra, U, Yuvaraj, R, Arunkumar, N, Murugappan, M, et al.. A deep learning approach for Parkinson’s disease diagnosis from EEG signals. Neural Comput Appl 2020;32:10927–33. https://doi.org/10.1007/s00521-018-3689-5.Search in Google Scholar
12. Pereira, CR, Weber, SA, Hook, C, Rosa, GH, Papa, JP. Deep learning-aided Parkinson’s disease diagnosis from handwritten dynamics. In: 29th SIBGRAPI conference on graphics, patterns and images. Sao Paulo, Brazil; 2016.10.1109/SIBGRAPI.2016.054Search in Google Scholar
13. Vásquez-Correa, JC, Arias-Vergara, T, Orozco-Arroyave, JR, Eskofier, B, Klucken, J, Nöth, E. Multimodal assessment of Parkinson’s disease: a deep learning approach. IEEE J Biomed Health Inf 2018;23:1618–30. https://doi.org/10.1109/JBHI.2018.2866873.Search in Google Scholar PubMed
14. Shen, D, Wu, G, Suk, HI. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017;19:221–48. https://doi.org/10.1146/annurev-bioeng-071516-044442.Search in Google Scholar PubMed PubMed Central
15. Litjens, G, Kooi, T, Bejnordi, BE, Setio, AAA, Ciompi, F, Ghafoorian, M, et al.. A survey on deep learning in medical image analysis. Med Image Anal 2017;42:60–88. https://doi.org/10.1016/j.media.2017.07.005.Search in Google Scholar PubMed
16. Kuresan, H, Samiappan, D, Ghosh, S, Gupta, AS. Early diagnosis of Parkinson’s disease based on non-motor symptoms: a descriptive and factor analysis. J Ambient Intell Humaniz Comput 2021 Mar 1. https://doi.org/10.1007/s12652-021-02944-0 [Epub ahead of print].Search in Google Scholar
17. Yadav, S, Singh, MK. Hybrid machine learning classifier and ensemble techniques to detect Parkinson’s disease patients. SN Comput Sci 2021;2:1–10. https://doi.org/10.1007/s42979-021-00587-8.Search in Google Scholar
18. Sahu, B, Mohanty, SN. CMBA-SVM: a clinical approach for Parkinson disease diagnosis. Int J Inf Technol 2021;13:647–55. https://doi.org/10.1007/s41870-020-00569-8.Search in Google Scholar
19. Pramanik, M, Pradhan, R, Nandy, P, Bhoi, AK, Barsocchi, P. Machine learning methods with decision forests for Parkinson’s detection. Appl Sci 2021;11:581. https://doi.org/10.3390/app11020581.Search in Google Scholar
20. Anudeep, P, Mourya, P, Anandhi, T. Parkinson’s disease detection using machine learning techniques. In: Advances in electronics, communication and computing. Singapore: Springer; 2021.10.1007/978-981-15-8752-8_49Search in Google Scholar
21. Senturk, ZK. Early diagnosis of Parkinson’s disease using machine learning algorithms. Med Hypotheses 2020;138:109603. https://doi.org/10.1016/j.mehy.2020.109603.Search in Google Scholar PubMed
22. Gunduz, H. Deep learning-based Parkinson’s disease classification using vocal feature sets. IEEE Access 2019;7:115540–51. https://doi.org/10.1109/access.2019.2936564.Search in Google Scholar
23. Sakar, BE, Isenkul, ME, Sakar, CO, Sertbas, A, Gurgen, F, Delil, S, et al.. Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings. IEEE J Biomed Health Inf 2013;17:828–34. https://doi.org/10.1109/jbhi.2013.2245674.Search in Google Scholar
24. Chandrashekar, G, Sahin, F. A survey on feature selection methods. Comput Electr Eng 2014;40:16–28. https://doi.org/10.1016/j.compeleceng.2013.11.024.Search in Google Scholar
25. Guyon, I, Elisseeff, A. An introduction to variable and feature selection. J Mach Learn Res 2003;3:1157–82.Search in Google Scholar
26. Jović, A, Brkić, K, Bogunović, N. A review of feature selection methods with applications. In: 2015 38th international convention on information and communication technology, electronics and microelectronics. Opatija, Croatia; 2015.10.1109/MIPRO.2015.7160458Search in Google Scholar
27. Fonti, V, Belitser, E. Feature selection using lasso. VU Amst Res Pap Bus Anal 2017;30:1–25.Search in Google Scholar
28. Paul, S, Drineas, P. Feature selection for ridge regression with provable guarantees. Neural Comput 2016;28:716–42. https://doi.org/10.1162/neco_a_00816.Search in Google Scholar PubMed
29. Karthik, S, Sudha, M. A regularization-based feature scoring criterion on candidate genetic marker selection of sporadic motor neuron disease. In: Intelligent data engineering and analytics. Singapore: Springer; 2021.10.1007/978-981-15-5679-1_30Search in Google Scholar
30. Sekaran, K, Sudha, M. Predicting autism spectrum disorder from associative genetic markers of phenotypic groups using machine learning. J Ambient Intell Humaniz Comput 2020;12:3257–70. https://doi.org/10.1007/s12652-020-02155-z.Search in Google Scholar
31. Cunningham, P, Cord, M, Delany, SJ. Supervised learning. In: Machine learning techniques for multimedia. Berlin, Heidelberg: Springer; 2008.10.1007/978-3-540-75171-7_2Search in Google Scholar
32. Karthik, S, Sudha, M. A survey on machine learning approaches in gene expression classification in modelling computational diagnostic system for complex diseases. Int J Eng Adv Technol 2018;8:182–91.Search in Google Scholar
33. Karthik, S, Sudha, M. Diagnostic gene biomarker selection for Alzheimer’s classification using machine learning. Int J Innovative Technol Explor Eng 2019;8:2348–52. https://doi.org/10.35940/ijitee.l3372.1081219.Search in Google Scholar
34. Karthik, S, Perumal, RS, Mouli, PC. Breast cancer classification using deep neural networks. In: Knowledge computing and its applications. Singapore: Springer; 2018.10.1007/978-981-10-6680-1_12Search in Google Scholar
35. Sekaran, K, Sudha, M. Prediction of lipopolysaccharides simulation responsiveness on gene expression profiles of major depression disorder affected cases using machine learning. Int J Sci Technol Res 2019;8:21–4.Search in Google Scholar
36. Pedregosa, F, Varoquaux, G, Gramfort, A, Michel, V, Thirion, B, Grisel, O, et al.. Scikit-learn: machine learning in Python. J Mach Learn Res 2011;12:2825–30.Search in Google Scholar
37. Raschka, S. Python machine learning. Birmingham: Packt Publishing Ltd; 2015.Search in Google Scholar
38. Sekaran, K, Sudha, M. Predicting drug responsiveness with deep learning from the effects on gene expression of obsessive–compulsive disorder affected cases. Comput Commun 2020;151:386–94. https://doi.org/10.1016/j.comcom.2019.12.049.Search in Google Scholar
39. Karthik, S, Sudha, M. Predicting bipolar disorder based non-overlapping genetic phenotypes using deep neural network. Evol Intell 2021;14:619–34. https://doi.org/10.1007/s12065-019-00346-y.Search in Google Scholar
40. Kamalakannan, K, Anandharaj, G. Stacked autoencoder based feature compression for optimal classification of Parkinson disease from vocal feature vectors using immune algorithms. Int J Adv Comput Sci Appl 2021;12:470–6. https://doi.org/10.14569/ijacsa.2021.0120558.Search in Google Scholar
41. Kamalakannan, K, Anandharaj, DG. Deep feature selection from the vocal features for effective classification of Parkinson’s disease. Int J Adv Sci Technol 2020;29:1661–72.Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
