This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: A study by Politecnico di Milano and the University of Insubria (Varese and Como) has been published in PLOS Digital Health. The study involved more than 700 children from primary and lower secondary school.
The participants used the THInkPen (Tele-Health Ink Pen) while completing two BVSCO-3 tasks from the Battery for the Clinical Assessment of Writing and Orthographic Skills. This is the most widely used test in Italy for assessing writing difficulties, dysgraphia and dysorthography. Its innovative feature is that the sensorized ink pen enriches the information provided by clinical tests, as required by the latest approved guidelines on Specific Learning Disorders, while allowing users to write on paper just like with a standard pen.
This represents a substantial difference compared with other screening tools, such as tablets. Its use during testing made it possible to highlight relevant characteristics of children's writing processes and provide a large amount of detailed information. From the data collected, digital indicators related to different aspects of writing were computed, such as pressure on the paper, movement fluency, pen inclination and the frequency of signals transmitted to the device through its sensors.
The data were subsequently analyzed to assess their correlation with clinical scores, model their progression across school grades and identify their usefulness in detecting writing difficulties using artificial intelligence algorithms developed for this task. The results revealed significant and consistent relationships between the digital indicators and the clinical scores, confirming the ability of these indicators to reliably reflect performance characteristics. Binary classification AI models successfully distinguished students with writing difficulties (identified on the basis of their BVSCO-3 results) from other students, while explainable artificial intelligence (XAI) techniques made it possible to identify the reasons underlying below-average performance, paving the way for targeted interventions.
The statistical analysis across school grades also showed that the digital indicators faithfully reproduced the well-established pattern of improvement in writing observed from one grade to the next, demonstrating their sensitivity in capturing the development of graphomotor skills. The study stems from the PRIN research project "e-School 2.0," coordinated by the Department of Electronics, Information and Bioengineering—DEIB at Politecnico di Milano, in collaboration with the University of Insubria. "The use of THInkPen to analyze not only the final written product, but the entire writing process, could support the early identification of writing difficulties in schools, thus facilitating the timely and effective activation of clinical services," explains Simona Ferrante, a professor at DEIB and coordinator of the Politecnico di Milano research team.
"This aspect is particularly relevant in light of the growing demand that Child and Adolescent Neuropsychiatry services face and the resulting long waiting lists," adds Dr. Cristiano Termine, professor of child neuropsychiatry at the University of Insubria. "School difficulties are one of the main reasons why children are referred for assessment by these services, but not all the difficulties experienced by students necessarily require specialist clinical evaluation.
Extract — continue reading at the source.
