Parkinson’s disease (PD) is one of the most widespread neurodegenerative diseases worldwide, affected by a number of alterations, among which speech impairments that, interestingly, manifests up to 10 years before other major evidences (e.g. motor impairments). In this regard, we investigated the feasibility of a model based on the temporal evolution of speech attractors in the reconstructed phase space to identify hallmarks of PD identification and progression. To this end, the adopted dataset was made of vocal emissions of 46 de-novo and 54 mid-advanced People with PD, plus 113 healthy counterpart. A statistical analysis was applied to test the identified hallmarks effectiveness for diagnostic support, monitoring, and staging of the disease. According to the obtained results, the adopted approach of considering the temporal evolution of speech attractors in the reconstructed phase-space results effective to discriminate among the three groups of pathological or healthy voices.
Questo è uno degli articoli scientifici pubblicati da uno o più collaboratori e data scientist di synbrAIn. LEGGI L'ARTICOLO COMPLETO