A new study coordinated by Sapienza Department of Human Neuroscience, proposed an innovative remote monitoring system for neurodegenerative patients based on analysis of handwriting through machine learning algorithms. The results of the work were published in the journal Frontiers in Aging Neuroscience. Handwriting is an acquired cognitive and motor task of a certain complexity, which provides an interesting window of observation on brain function. For this reason, handwriting monitoring provides useful biological information, especially in neurodegenerative patients: indeed, writing disorders are frequently observed in patients with neurodegenerative diseases, including Parkinson’s disease (microscopy) and Alzheimer’s disease (graphic). A multidisciplinary research team, coordinated by Antonio Soba subordinate Sapienza Department of Human Neuroscience, proposed the analysis of typing through artificial intelligence as an innovative system for remote monitoring, in telemedicine, for neurological patients. The system, which relies on the accuracy of machine learning algorithms in detecting certain typing “patterns” attributable to physiological aging in healthy people, is an alternative to the usual outpatient clinical assessment.
The study was conducted in cooperation with the departments of Information, Electronics, and Telecommunications Engineering by Sapienza, IRCCS Neuromed, and the Department of Neuroscience at the University of Cincinnati in Ohio. The researchers recruited 156 healthy, right-handed people and divided them into three age groups: 51 young adults between the ages of 18 and 32, 40 adults between the ages of 37 and 57, and finally 63 adults. years. Each was asked to write their name and surname with a black ballpoint pen 10 times on a white sheet of paper, and then photograph their writing sample with a smartphone and send it to the researchers. “The main scientific goal of our study – explains Antonio Soba – is the accuracy of automatic analysis of writing using artificial intelligence algorithms, which are able to determine the gradual reduction in character amplitude due to physiological aging and, accordingly, attribute each writing sample to a specific age group of the author.” “Although previous research has already shown changes in age-related typing prowess, for the analysis of a large amount of data in the telemedicine field, approaches based on more complex analysis techniques such as machine learning.” He adds: Analyzing writing using artificial intelligence algorithms Simon Scardabani, co-author of the study – made thanks to the use of a convolutional neural network – an artificial network specialized for processing images and digital signals – capable of automatically converting characters into parameters of interest. It is a simple, environmental, low-cost and easy-to-use method in various fields. Indeed, in addition to the observed effects in the neurological field, it can contribute, for example, to the historical dating of a particular document, thanks to the automatic assessment of the age of the person who wrote it. In particular, in the medical-legal field, it can be easier to date a will at the time of drafting or signature. “Our hope – concludes Francesco Asico-author of the study – is that teletyping analysis and the use of artificial intelligence algorithms could constitute an innovative biomarker of aging in the future, with significant impact in the field of neurodegenerative disease diagnosis and according to telemedicine methods.”
“Infuriatingly humble social media buff. Twitter advocate. Writer. Internet nerd.”