Handwriting is a complex cognitive prowess that deteriorates in patients affected by neurodegenerative diseases, including movement disorders. More in detail, patients with Parkinson's disease (PD) may manifest prominent handwriting abnormalities which have been collectively identified as parkinsonian micrographia. MIcrographia may manifest at the onset of the disease and then worsens progressively with time. Previous techniques released to investigate micrographia in PD relied on perceptual analysis of simple tasks or were based on expensive technological tools, including tablets. However, handwriting can be promptly collected in an ecological scenario, through safe, cheap, and largely available tools. Also, the objective handwriting analysis through artificial intelligence would represent an innovative strategy even superior to previous techniques, since it allows for the analysis of large amounts of data. In this experimental project, the investigators apply a specific machine learning algorithm to analyze handwriting samples recorded in healthy controls and PD patients. The study aims to verify whether the technique proposed by the investigators would be able to detect parkinsonian micrographia objectively, monitor the evolution of handwriting abnormalities and assess the symptomatic improvement of handwriting following L-Dopa administration in PD patients.

Inclusion Criteria:

• Healthy conditions
• clinical diagnosis of Parkinson's disease

Exclusion Criteria:

• cognitive decline

Healthy subjects and patients with idiopathic PD