A Machine Learning Method To Process Voice Samples For Identification Of Parkinson’s Disease

This study explores the use of machine learning approaches for the automatic detection of Parkinson’s disease using voice recordings. The study collected samples from 50 people with specialist-diagnosed Parkinson’s disease and 50 healthy controls and applied machine learning classification with voice features related to phonation. Additionally, a novel application of a pre-trained convolutional neural network (Inception V3) with transfer learning was used to analyze the spectrograms of the sustained vowel from these samples. Results showed the superiority of the deep learning model for the task of classifying people with Parkinson’s disease as distinct from healthy controls.