Detecting Parkinson's Disease - A Comparison of Machine Learning Models with Differentially Private Dimension Reduction

• Manuel Edvar Bento Filho Federal University of Ceará
• Maria de Lourdes Maia Silva Federal University of Ceará
• Patrícia Vieira da Silva Barros Federal University of Ceará
• César Lincoln Cavalcante Mattos Federal University of Ceará
• Javam de Castro Machado Federal University of Ceará

DOI: https://doi.org/10.5753/sbbd.2020.13650

Abstract

This paper aims to present a comparison of machine learning models using two dimensionality reduction approaches in data pre-processing, one private and one non-private. The problem is to classify patients as having Parkinson's disease or not. Models were compared based on their ability to diagnose the disease based on a collection of vocal data. The results obtained indicate that the Gaussian and Random Forest process models were the best approaches without and with differential privacy restriction, respectively.

Keywords: Parkinson's Disease, Dimensionality Reduction, Machine Learning, Differential Privacy

References

Chaudhuri, K., Sarwate, A., and Sinha, K. (2012). Near-optimal differentially private principal components. In Advances in Neural Information Processing Systems, pages 989–997.

Das, R. (2010). A comparison of multiple classification methods for diagnosis of parkinson disease. Expert Systems with Applications, 37(2): 1568–1572.

Dias, A. E. and Limongi, J. C. P. (2003). Tratamento dos distúrbios da voz na doença de parkinson: o método lee silverman. Arquivos de Neuro-Psiquiatria, 61(1): 61–66.

Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., and Naor, M. (2006). Our data, ourselves: Privacy via distributed noise generation. In Annual International Conference on the Theory and Applications of Cryptographic Techniques, pages 486–503. Springer.

Dwork, C., Roth, A., et al. (2014). The algorithmic foundations of differential privacy. Foundations and Trends in Theoretical Computer Science, 9(3-4): 211–407.

Ramani, R. G. and Sivagami, G. (2011). Parkinson disease classification using data mining algorithms. International journal of computer applications, 32(9): 17–22.

Sakar, C. O. and Kursun, O. (2010). Telediagnosis of parkinson’s disease using measurements of dysphonia. Journal of medical systems, 34(4): 591–599.

Sakar, C. O., Serbes, G., Gunduz, A., Tunc, H. C., Nizam, H., Sakar, B. E., Tutuncu, M.,Aydin, T., Isenkul, M. E., and Apaydin, H. (2019). A comparative analysis of speech signal processing algorithms for parkinson’s disease classification and the use of the tunable q-factor wavelet transform. Applied Soft Computing, 74: 255–263.