A Genetic Approach Wrapped Support Vector Machine for Feature Selection Applied to Parkinson's Disease Diagnosi

Abstract

Parkinson’s disease (PD) is found to be a challenging issue which can offer a computerized estimate about classification of PD to patient people and healthy for normal people. Due to the importance of that problem, several types of biomedical data can be analyzed to
accurately detect PD by using different learning methods. This work considers the diagnosis of PD based on voice data by using non-linear support vector machine (SVM). However SVM is known as the one of the fast and accurate learning methods, selection of relevant feature elements of PD dataset can be effective on improving the classification performance of SVM. To this end, this paper proposed an SVM in parallel with GA based feature reduction model for selecting the most relevant features to get Parkinson's disease. The
GA-SVM resulted in improved accuracy, sensitivity and area under curve (95%, 98% and 92% respectively) compared to the other learning methods and feature selection algorithms. The GA-SVM provides a better, more accurate identification for presence of vocal disorder from speech recordings leading to more timely diagnosis.

Keywords

• Parkinson’s Disease (PD),Feature Selection,Genetic Algorithm (GA),Classification,Support Vector Machine (SVM)

References

1. 1. Harel, B.-T., Cannizzaro, .S, Cohen, H., Reilly ,N., Snyder ,P.-J.: Article title. Journal of Neurolinguistics 17(6), 439–453 (2004)
2. 2. Singh, N., Pillay, V., Choonara, Y.-E.: Advances in the treatment of Parkinson’s disease. Progress in Neurobiology 81(1), 29–44 (2007)
3. 3. Jankovic, J.:Parkinsons disease: clinical features and diagnosis. Journal of Neurology, Neurosurgery Psychiatry 79, 368–376 (2008)
4. 4. Massano, J., Bhatia, K.-P.: Clinical approach to Parkinson’s disease: features, diagnosis, and principles of management. Cold Spring Harbor Perspectives in Medicine 2(6), (2012)
5. 5. Lan, K.-C., Shih, V.-Y.: Early Diagnosis of Parkinson’s Disease Using a Smartphone. Procedia Comput. Sci. 34, 305–312 (2014)
6. 6. Ma, C., Ouyang, J., Chen, H.-L., Zhao, X.-H.: An efficient diagnosis system for Parkinson’s disease using kernel-based extreme learning machine with subtractive clustering features weighting approach. Comput Math Methods Med 2014, 1–14 (2014)
7. 7. Hossen, A., Muthuraman, M., Raethjen, J., Deuschl, G., Heute, U.: Discrimination of Parkinsonian tremor from essential tremor by implementation of a wavelet-based soft-decision technique on EMG and accelerometer signals. Biomed Signal Process Control 5, 18 (2010)
8. 8. Daliri, M.-R.: Chi square distance kernel of the gaits for the diagnosis of Parkinson’s disease. Biomed Signal Process Control 8(1), 66–70 (2013)

9. 9. Duffy, R.-J. Motor Speech Disorders: Substrates, Differential Diagnosis and Management. 2nd Edition, Elsevier Mosby, St. Louis. (2005)
10. 10. Ho, A.-K., Lansek, R., Marigliani, C., Bradshaw, J.-L., Gates, S.: Speech Impairment in a Large Sample of Patients with Parkinson’s Disease. Behaviour Neurology 11, 131–137 (1998)
11. 11. Sapir, S., Spielman, J.-L., Ramig, L.-O., Story, B.-H., Fox, C.: Effects of intensive voice treatment (the Lee Silverman voice treatment [LSVT]) on vowel articulation in dysarthric individuals with idiopathic Parkinson disease: Acoustic and perceptual findings. J. Speech. Lang. Hear. Res. 50, 899–912 (2007)
12. 12. Rahn, D.-A., Chou, M., Jiang, J.-J., Zhang, Y.: Phonatory Impairment in Parkinson’s Disease: Evidence from Nonlinear Dynamic Analysis and Perturbation Analysis. Journal of Voice 21 64–71 (2007)
13. 13. Peng, B., Wang, S., Zhou, Z., Liu, Y., Tong, B., Zhang, T., Dai, Y.: A multilevel-ROI-features-based machine learning method for detection of morphometric biomarkers in Parkinson’s disease. Neurosci. Lett. 651, 88–94 (2017)
14. 14. Salvatore, C., Cerasa, A., Castiglioni, I., Gallivanone, F., Augimeri, A., Lopezd, M., Arabia, G., Morelli, M., Gilardi, M.-C., Quattrone A.: Machine learning on brain MRIdata for differential diagnosis of Parkinson’s disease and ProgressiveSupranuclear. Palsy, J. Neurosci. Methods 222, 230–237 (2014)
15. 15. Yang, S., Zheng, F., Luo, X., Cai, S., Wu, Y., Liu, K., Wu, M., Chen, Krishnan, J.-S: Effective dysphonia detection using feature dimension reduction and kernel density estimation for patients with Parkinson’s disease. PLoS One 9(2):e88825 (2014)
16. 16. Kotsavasiloglou, C., Kostikis, N., Hristu-Varsakelis, D., Arnaoutoglou M.: Machine learning-based classification of simple drawing movements in Parkinson’s disease. Biomed. Signal Process. Control 31 174–180 (2017)
17. 17. Kaya, E., Findik, O., Babaoglu, I., Arslan, A. Effect of discretization method on the diagnosis of Parkinson’s disease. International Journal of Innovative Computing, Information and Control 7 4669–4678 (2011)
18. 18. Tsanas, A., Little, M.-A., McSharry, P.-E., Spielman, J., Ramig, L.-O.: Novel speechsignal processing algorithms for high-accuracy classification of Parkinson’sdisease. IEEE Trans. Biomed. Eng. 59, 1264–1271 (2012)
19. 19. Sakar, B.-E., Isenkul, M.-E., Sakar, C.-O., Sertbas, A., Gurgen, F., Delil, S., Apaydin, H., Kursun, O.: Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings. IEEE J Biomed Health Inform 17(4), 828–834 (2013)
20. 20. Can, M.: Neural networks to diagnose the Parkinson’s disease. South East Europe Journal of Soft Computing 2(1), (2013)
21. 21. Shahsavari, M.-K., Rashidi, H., Bakhsh H.-R.: Efficient classification of Parkinsons disease using extreme learning machine and hybrid particle swarm optimization. In: 2016 4th International Conference on Control, Instrumentation, and Automation (ICCIA), pp. 148–154. IEEE, Qazvin (2016)
22. 22. Visalakshi, S., Radha, V.: A literature review of feature selection techniques and applications: Review of feature selection in data mining. In: IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) pp. 1-6. (2014)
23. 23. Jong, K.-D.: Learning With Genetic Algorithms: an Overview, MachineLearning 3, Kluwer Academic publishers (1988)
24. 24. Yana, K., Zhang, D.: Feature selection and analysis on correlated gas sensor datawith recursive feature elimination, Sens. Actuators B: Chem. 212, 353–363 (2015)
25. 25. Shahbaba, B., Neal, R.: Nonlinear models using Dirichlet process mixtures. Journal of Machine Learning Research, 10, 1829–1850 (2009)
26. 26. Little, M.-A., McSharry, P.-E., Hunter, E.-J., Ramig L.-O.: Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease. IEEE Transactions on Biomedical Engineering 56, 1015–1022 (2009)
27. 27. Das, R. : A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Systems with Applications 37 (2), 1568–1572 (2010)
28. 28. Guo, P.-F., Bhattacharya, P., Kharma, N.: Advances in detecting Parkinson’s disease. Medical Biometrics 6165, 306–314 (2010)
29. 29. Ozcift, A., Gulten, A.: Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms. Computer Methods and Programs in Biomedicine 104(3), 443–451 (2011)
30. 30. Chen, H.-L., Huang, C.-C., Yu, X. G.: An efficient diagnosis system for detection of Parkinson’s disease using fuzzy k-nearest neighbor approach. Expert Systems with Applications 40(1), 263–271 (2013) 31. Chen, H.-L., Wang, G., Ma, C., Cai, Z.-N., Liu, W.-B., Wang, S.-J.: An efficient hybrid kernel extreme learning machine approach for early diagnosis of Parkinson’s disease. Neurocomputing 184(4745), 131–144 (2016)
31. 32. Peker, M., Sen, B., Delen, D.: Computer-Aided Diagnosis of Parkinson’s Disease Using Complex-Valued Neural Networks and mRMR Feature Selection Algorithm. J Healthc Eng. 6(3), 281–302 (2015)
32. 33. Lahmiri, S., Shmuel, A.: Detection of Parkinson’s disease based on voice patterns ranking and optimized support vector machine. Biomed. Signal Process Control 49 2019, 427–433 (2019)
33. 34. Goldberg, D.-E.: Genetic algorithms in search, optimization and machine learning. Addison-Wesley, New York (1998)
34. 35. Gokulnath, C.-B., Shantharajah, S.-P.: An optimized feature selection based on genetic approach and support vector machine for heart disease. Cluster Comput 1-11 (2018)
35. 36. Yan, H., Zheng, J., Jiang, Y., Peng, C., Xiao, S.: Selecting critical clinical features for heart diseases diagnosis with a real-coded genetic algorithm. Appl. Soft Comput 8, 1105–1111 (2008)
36. 37. Fayyad, U., Irani, K.: Multi-interval discretization of continuous valued attributes for classification learning. in: Proceeding of The International JointConference on Artificial Intelligence, pp. 1022–1029 (1993)
37. 38. Chao, C.-F. Horng M.-H.: The construction of support vector machine classifier using the firefly algorithm. Comput Intell Neurosci 2015, 8 (2015)
38. 39. Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning, DataMining, Inference, and Prediction second edition. SpringerVerlag, New York (2009)