Addressing voice recording replications for Parkinson’s disease detection

作者：

Highlights：

• A general subject-based Bayesian approach has been proposed.

• Special treatment is provided for the probit model.

• Latent variables are used to provide a predictive model that can handle replications.

• A Gibbs sampling-based method is derived to compute the model parameters.

• The approach is used to discriminate healthy people from people suffering PD.

摘要

•A general subject-based Bayesian approach has been proposed.•Special treatment is provided for the probit model.•Latent variables are used to provide a predictive model that can handle replications.•A Gibbs sampling-based method is derived to compute the model parameters.•The approach is used to discriminate healthy people from people suffering PD.

论文关键词：Bayesian binary regression,Gibbs sampling,Latent variables,Parkinson’s disease,Speech recordings,Voice features

论文评审过程：Received 15 December 2014, Revised 25 October 2015, Accepted 27 October 2015, Available online 31 October 2015, Version of Record 18 November 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.10.034