Analysis of voice recordings features for Classification of Parkinson's Disease

Parkinson's disease (PD) is a chronic neurodegenerative disease. Motor symptoms are very mild in the early stages, making diagnosis difficult. Recent studies have shown that the use of patient voice recordings can aid in early diagnosis. Although the analysis of such recordings is costly from a clinical perspective, machine learning techniques are making their processing increasingly accurate and efficient. Voice recordings contain many features, but it is unknown which ones are relevant to the diagnosis of this disease. This paper proposes the use of machine learning models combined with feature selection methods for the classification of PD patients. The results show that this approach is appropriate since it drastically reduces the number of features maintining high classification performance.