This study evaluates the practical value of traditional and non-standard measures for discriminating healthy individuals from those with Parkinson's disease (PD) by detecting dysphonia. The authors introduce a new measure called Pitch Period Entropy (PPE), which is robust to various uncontrollable factors such as noisy acoustic environments and normal voice frequency variations. They collected sustained phonations from 31 participants, 23 of whom had PD. After selecting 10 highly uncorrelated measures, an exhaustive search of all possible combinations found that four measures—Harmonics-to-Noise Ratio (HNR), Recurrence Period Density Entropy (RPDE), Detrended Fluctuation Analysis (DFA), and PPE—result in an overall correct classification performance of 91.4% using a kernel support vector machine. The study concludes that non-standard methods, combined with traditional harmonics-to-noise ratios, are best for separating healthy from PD subjects. These methods are robust to many uncontrollable variations in the acoustic environment and individual subjects, making them suitable for telemonitoring applications.This study evaluates the practical value of traditional and non-standard measures for discriminating healthy individuals from those with Parkinson's disease (PD) by detecting dysphonia. The authors introduce a new measure called Pitch Period Entropy (PPE), which is robust to various uncontrollable factors such as noisy acoustic environments and normal voice frequency variations. They collected sustained phonations from 31 participants, 23 of whom had PD. After selecting 10 highly uncorrelated measures, an exhaustive search of all possible combinations found that four measures—Harmonics-to-Noise Ratio (HNR), Recurrence Period Density Entropy (RPDE), Detrended Fluctuation Analysis (DFA), and PPE—result in an overall correct classification performance of 91.4% using a kernel support vector machine. The study concludes that non-standard methods, combined with traditional harmonics-to-noise ratios, are best for separating healthy from PD subjects. These methods are robust to many uncontrollable variations in the acoustic environment and individual subjects, making them suitable for telemonitoring applications.