Automated human-level diagnosis of dysgraphia using a consumer tablet
Thibault Asselborn, Thomas Gargot, Lukasz Kidzinski, Wafa Johal, David Cohen, Caroline Jolly, Pierre Dillenbourg
The academic and behavioural progress of children is associated with the development of reading and writing skills. Dysgraphia, characterised as a handwriting disability, is usually associated with dyslexia, developmental coordination disorder (dyspraxia), or attention deficit disorder, which are all developmental disorders. Dysgraphia can seriously impair children in their everyday lives and can require therapeutic care.
Therefore, early detection of handwriting problems is of great importance in paediatrics. Since the beginning of the 20th century, numerous handwriting scales have been developed to assess the quality of penmanship. However, these tests usually involve experts investigating sentences written by the subject on paper. They are subjective, expensive, and poorly scaled. Moreover, they ignore potentially important motor control characteristics such as writing dynamics, pen pressure, or pen tilt. With the increasing availability of digital tablets, features to measure these ignored characteristics are now easily accessible at a lower cost.
In our studies, we developed a diagnostic tool that only requires a tablet. We tested the data of 298 children, including 56 with dysgraphia. Children performed the BHK test on a digital tablet covered with a sheet of paper. We created 53 handwriting features describing various aspects of handwriting and used the Random Forest classifier to diagnose dysgraphia. Our method achieved 96.6% sensibility and 99.2% specificity. Given the intra-rater levels in the BHK test, our technique has comparable accuracy for experts. It can be used directly as a diagnostics tool.
