Please login first
Classification-based screening of Parkinson’s disease patients through graph and handwriting signal
1, 2 , 2 , 3, 4 , 1, 5 , * 2, 6
1  Sapienza University of Rome
2  Technoscience
3  AGIF Associazione Grafologica Italo-Francese
4  Policlinico Universitario Agostino Gemelli
5  ICEmB
6  Department of Management and Law - University of Rome "Tor Vergata"
Academic Editor: Nunzio Cennamo


Parkinson disease (PD) is one of the most common neurodegenerative diseases, affecting millions of people worldwide, especially the elderly population, and its main motor symptoms usually are bradykinesia, tremor and rigidity. In the last decade, there have been a lot of studies concerning the research of reliable markers for the early diagnosis of it, since this can lead to a significant improvement in quality of life for the patients.

It has been demonstrated that handwriting impairment can be an important early marker for the detection of this disease.

The aim of this study is to propose a simple and quick way to discriminate PD patients from controls through handwriting tasks using machine learning techniques. We developed a telemonitoring system based on a user-friendly application for digitising tablets that enabled on us to collect real-time information about position, pressure, and inclination of the digital pen during the experiment and, simultaneously, to supply visual feedback on the screen to the subject. The data can be collected remotely, in order to allow the patients to execute tasks in the comfort and safety of their home, reducing the demand on hospital services. Handwriting data from 20 PD patients and 20 control subjects were collected: Information about position, pressure, and inclination of the pen during the tasks have been extracted through a software developed by our team. the participants have been asked to draw an Archimedean spiral and ten concentric circles, and to write the cursive bigram “le”, two Italian sentences and seven lines of free text. In this way, we were able to compute features linked to kinematics, pressure, geometry, and energy of the strokes.

Keywords: Graph signal; handwariting signal; Parkinson's; machine learning; telemonitoring