Parkinson’s Disease (PD) is one of the most common non-curable neurodegenerative diseases. Diagnosis is achieved clinically on the basis of different symptoms with considerable delays from the onset of neurodegenerative processes in the central nervous system. In this study, we investigated early and full-blown PD patients based on the analysis of their voice characteristics with the aid of the most commonly employed machine learning (ML) techniques. A custom dataset was made with hi-fi quality recordings of vocal tasks gathered from Italian healthy control subjects and PD patients, divided into early diagnosed, off-medication patients on the one hand, and mid-advanced patients treated with L-Dopa on the other. Following the current state-of-the-art, several ML pipelines were compared usingdifferent feature selection and classification algorithms, and deep learning was also explored with a custom CNN architecture. Results show how feature-based ML and deep learning achieve comparable results in terms of classification, with KNN, SVM and naïve Bayes classifiers performing similarly, with a slight edge for KNN. Much more evident is the predominance of CFS as the best feature selector. The selected features act as relevant vocal biomarkers capable of differentiating healthy subjects, early untreated PD patients and mid-advanced L-Dopa treated patients.

Background: Experimental studies using qualitative or quantitative analysis have demonstrated that the human voice progressively worsens with ageing. These studies, however, have mostly focused on specific voice features without examining their dynamic interaction. To examine the complexity of age-related changes in voice, more advanced techniques based on machine learning have been recently applied to voice recordings but only in a laboratory setting. We here recorded voice samples in a large sample of healthy subjects. To improve the ecological value of our analysis, we collected voice samples directly at home using smartphones. Methods: 138 younger adults (65 males and 73 females, age range: 15–30) and 123 older adults (47 males and 76 females, age range: 40–85) produced a sustained emission of a vowel and a sentence. The recorded voice samples underwent a machine learning analysis through a support vector machine algorithm. Results: The machine learning analysis of voice samples from both speech tasks discriminated between younger and older adults, and between males and females, with high statistical accuracy. Conclusions: By recording voice samples through smartphones in an ecological setting, we demonstrated the combined effect of age and gender on voice. Our machine learning analysis demonstrates the effect of ageing on voice.