EXPLORING THE USE OF PHONOLOGICAL FEATURES FOR PARKINSON’S DISEASE DETECTION

Parkinson’s disease (PD) is a neurodegenerative disorder that causes motor and non-motor symptoms. Speech impairments are one of the early symptoms of PD, but they are not always fully exploited by clinicians. In this study, the use of phonological features extracted from speech
data collected from Spanish-speaking patients was explored to predict PD patients from healthy subjects using phonet, which was trained on Spanish data, and PhonVoc, which was trained on English
data. These features were then used to train and test several machine learning models. The XGBoost
model achieved the best performance in classifying patients from HCs, with an accuracy of over 0.76.
However, the model performed better when using a phonological model trained on Spanish data rather than English data.