In this study, we propose a novel remote health monitoring system to accurately predict Parkinson’s
disease severity using a signomial regression method. In order to characterize the Parkinson’s disease
severity, sixteen biomedical voice measurements associated with symptoms of the Parkinson’s disease, are
used to develop the telemonitoring model for early detection of the Parkinson’s disease. The proposed
approach could be utilized for not only prediction purposes, but also interpretation purposes in practice,
providing an explicit description of the resulting function in the original input space. Compared to the
accuracy performance with the existing methods, the proposed algorithm produces less error rate for
predicting Parkinson’s disease severity.