A Flexible Replication-Based Classification Approach for Parkinson’s Disease Detection by Using Voice Recordings
Detecting Parkinson’s disease (PD) by using a noninvasive low-cost tool based on acoustic features automatically extracted from voice recordings has become a topic of interest. A two-stage classification approach has been developed to differentiate PD subjects from healthy people by using acoustic features obtained from replicated voice recordings. The proposed hierarchical model has been specifically developed to handle replicated data and considers a dimensional reduction of the feature space as well as the use of mixtures of normal distributions to describe the latent variables in the second order of hierarchy. The approach has been applied to a database of acoustic features obtained from 40 PD subjects and 40 healthy controls, improving results compared to previous models.
KeywordsBayesian binary hierarchical model Common principal components Mixtures of normal distributions Parkinson’s disease Replicated measurements Voice recordings
Thanks to the anonymous participants and to Carmen Bravo and Rosa María Muñoz for carrying out the voice recordings and providing information from the people with PD. We are grateful to the Asociación Regional de Parkinson de Extremadura and Confederación Española de Personas con Discapacidad Física y Orgánica for providing support in the experiment development.
This research has been supported by UNAM-DGAPA-PAPIIT, Mexico (Project IA106416), Ministerio de Economía, Industria y Competitividad, Spain (Projects MTM2014-56949-C3-3-R and MTM2017-86875-C3-2-R), Junta de Extremadura, Spain (Projects IB16054 and GRU18108), and the European Union (European Regional Development Funds).
- 1.Buonaccorsi, J.P.: Measurement Error: Models. Methods and Applications. Chapman and Hall/CRC, Boca Raton, FL (2010)Google Scholar
- 4.Chen, M.H., Shao, Q.M., Ibrahim, J.G.: Monte Carlo Methods in Bayesian Computation. Series in Statistics. Springer, Berlin (2000)Google Scholar
- 6.Flury, B.: Common Principal Components and Related Models. Wiley, New York (1988)Google Scholar
- 7.Flury, B.N.: Common principal components analysis in K groups. J. Am. Stat. Assoc. 79(388), 892–898 (1984)Google Scholar
- 11.Jolliffe, I.T.: Principal Component Analysis, 2nd edn. Springer, New York (2002)Google Scholar
- 14.McLachlan, G.J., Krishnan, T.: The EM Algorithm and Extensions, 2nd edn. Wiley, New York (2007)Google Scholar
- 18.Orozco-Arroyave, J.R., Arias-Londoño, J.D., Vargas-Bonilla, J.F., Nöth, E.: Analysis of speech from people with Parkinson’s disease through nonlinear dynamics. In: Drugman, T., Dutoit, T. (eds.) Advances in Nonlinear Speech Processing. Lecture Notes in Artificial Intelligence, vol. LNAI 7911, pp. 112–119. Springer, Berlin (2013)CrossRefGoogle Scholar
- 19.Pahuja, G., Nagabhushan, T.N.: A comparative study of existing machine learning approaches for Parkinson’s disease detection. IETE J. Res. 1–11 (2018)Google Scholar
- 21.Pérez, C.J., Naranjo, L., Martín, J., Campos-Roca, Y.: A latent variable-based Bayesian regression to address recording replication in Parkinson’s disease. In: EURASIP: Proceedings of the 22nd European Signal Processing Conference (EUSIPCO-2014), pp. 1447–1451. IEEE, Lisbon, Portugal (2014)Google Scholar
- 23.Richardson, S., Green, P.J.: On Bayesian analysis of mixtures with an unknown number of components. J. R. Stat. Soc. Ser B (Methodol.) 59(4), 731–792 (1997)Google Scholar
- 26.Saifer, A., Ali, D.S.M.: A review on Parkinson’s disease diagnosis through speech. Int. J. Sci. Res. Sci. Technol. 4(5), 36–45 (2018)Google Scholar