A Comparison of Classification Methods for Diagnosis of Parkinson's

Abdullah Elen; Emre Avuclu

doi:10.18201/ijisae.2020466309

Authors

Abdullah Elen Bandirma Onyedi Eylul University https://orcid.org/0000-0003-1644-0476
Emre Avuclu Aksaray University https://orcid.org/0000-0002-1622-9059

DOI:

https://doi.org/10.18201/ijisae.2020466309

Keywords:

Machine learning, Classification, Parkinson's disease

Abstract

Abstract: Parkinson's is a neurological health problem and one of the most common diseases affecting more than four million people worldwide. Recent studies have shown that deterioration of vocal cords, especially from Parkinson's, provides important information in the diagnosis and follow-up of the disease. In this study, a database of biomedical voice recordings from 32 people of different ages and genders was used to diagnose Parkinson's disease. With this database, the performance comparison of the machine learning algorithms k-Nearest Neighborhood (k-NN) and Naïve Bayes (NB) classifiers were performed. Seven different distance measurement methods (Chebychev, Correlation, Cosine, Euclidean, Hamming, Mahalanobis, and Spearman) for the k-NN and five different distribution methods (Uniform kernel, Epanechnikov kernel, Gaussian kernel, Triangular kernel and Normal distribution) for the NB classifier were performed in the performance process and separate tests were performed. The data obtained from these tests were compared with statistical measurements. In experimental studies, we used 10-fold cross validation technique for Parkinson dataset. Better results were obtained from k-NN classification algorithm than Naive Bayes classification algorithm. While k-NN mean accuracy score was 82.34%, this ratio was obtained as 74.15% for NB. Mahalanobis distance measurement method was found to give better results.

Downloads

Download data is not yet available.

References

Adams, R.D., And Victor, M., And Ropper, AH., 1997, Principles of Neurology 6th ed., NY: McGraw-Hill, New York, 1067-1078.

Waters, CH., Çev: Büyükkal B., 2000, Parkinson Hastalığının Tanı ve Tedavisi , Turgut Yayıncılık ve Tic. A.ş., İstanbul.

Apaydın, H. (2001). Parkinson hastalığının klinik özellikleri. Parkinson Hastalığı ve Hareket Bozuklukları Dergisi, 4(2), 114-24.

Hoehn, M.M., Yahr, M.D. (1967). Parkinsonism: onset, progression and mortality. Neurology, 17, 427-42.

Tugwell, C. (2008). Parkinson’s Disease on Focus. Chicago: Pharmaceutical Press, 7-8.

Aydınlı, I. (2005). Ağrının Patofizyolojisi. Türk Fiz. Tıp Rehab. Derg., 51 (özel ek B), 8-13.

Ford, B., Louis, E.D., Greene, P. and Fahn, S. (1996). Oral and genital pain syndromes in Parkinson’s disease. Movement Disorder, 11(4), 421-6.

Little, M.A., McSharry, P.E., Hunter, E.J., Spielman, J., Ramig, L.O. (2009). Suitability of Dysphonia Measurements for Telemonitoring of Parkinson’s Disease. IEEE Transactions on Biomedical Engineering, 56(4), 1015-1022.

Tsanas, A., Little, M.A., Mcsharry, P.E. And Ramig, L.O. (2009). Accurate Telemonitoring of Parkinson’s Disease Progression by Non-Invasive Speech Tests. Nature Precedings.

Revett, K., Gorunescu, F. And Salem, A.B.M. (2009). Feature Selection in Parkinson’s Disease: A Rough Sets Approach. Proceedings of the International Multiconference on Computer Science and Information Technology, Poland, 425-428.

Tsanas, A., Little, M.A., Mcsharry, P.E. And Ramig, L.O. (2010). Enhanced Classical Dysphonia Measures and Sparse Regression for Telemonitoring of Parkinson's Disease Progression. IEEE International Conference on Acoustics Speech and Signal, 594-597.

Fahn, S., and Przedborski, S., 2000, Parkinsonizm. In: Rowland Lp Ed. Merritt’s Textbook of Neurology. 10th Ed., Lippincott Williams & Wilkins, Philadelphia, 9789752771819, pp. 679-693.

Quinn, N., And Critchley, P., And Marsden, CD., 1987, Young onset Parkinson’s Disease. Mov Disord., 2(2), pp.73-91.

Apaydın, H., Özekmekci, S. (2008). Parkinson Hastalığı: Hasta ve Yakınları için El Kitabı. İstanbul: Parkinson Hastalığı Derneği, 6-15.

Elen, A., & Avuçlu, E. (2019). Diagnosis of Parkinson's Disease Using K-NN Classifier with Various Distance Measurements, 1st International Science and Innovation Congress, pp. 2-8, Pamukkale, Denizli/TR.

Avuçlu, E., & Elen, A. (2020). Evaluation of train and test performance of machine learning algorithms and Parkinson diagnosis with statistical measurements. Med Biol Eng Comput 58, 2775–2788. doi: 10.1007/s11517-020-02260-3

Zhou, J., Li, C., Arslan, C.A. et al. Performance evaluation of hybrid FFA-ANFIS and GA-ANFIS models to predict particle size distribution of a muck-pile after blasting. Engineering with Computers (2019) doi: 10.1007/s00366-019-00822-0

Kishor, N., Singh, S.P., Raghuvanshi, A.S. et al. Engineering with Computers (2007) 23: 71. doi: 10.1007/s00366-006-0024-z

Salim Lahmiri, Amir Shmuel, Performance of machine learning methods applied to structural MRI and ADAS cognitive scores in diagnosing Alzheimer’s disease, Biomedical Signal Processing and Control, Volume 52, 2019, Pages 414-419, ISSN 1746-8094, doi: 10.1016/j.bspc.2018.08.009.

Cover, T., and Hart, P., “Nearest Neighbor Pattern Classification”, IEEE Transactions on Information Theory, 13(1): 21-27 (1967).

Orhan, U. and Adem, K., “The Effects of Probability Factors in Naive Bayes Method”, Elektrik-Elektronik ve Bilgisayar Mühendisliği Sempozyumu, Bursa, 722-724 (2012).

Krishna, P. R. and De, S. K., “Naive-Bayes Classification using Fuzzy Approach”, Third International Conference on Intelligent Sensing and Information Processing, Bangalore/India, 61-64 (2005).