Automated dysgraphia detection by deep learning with SensoGrip

TL;DR

This paper presents a deep learning approach using a sensor-equipped smart pen to accurately and automatically assess handwriting skills and detect dysgraphia, enabling early intervention in more natural writing environments.

Contribution

It introduces a novel deep learning method with automatic feature extraction for dysgraphia detection using a smart pen, improving accuracy and realism over previous tablet-based approaches.

Findings

Accuracy over 99% in grading handwriting capabilities

Root mean square error lower than one

Effective dysgraphia detection in realistic scenarios

Abstract

Dysgraphia, a handwriting learning disability, has a serious negative impact on children's academic results, daily life and overall wellbeing. Early detection of dysgraphia allows for an early start of a targeted intervention. Several studies have investigated dysgraphia detection by machine learning algorithms using a digital tablet. However, these studies deployed classical machine learning algorithms with manual feature extraction and selection as well as binary classification: either dysgraphia or no dysgraphia. In this work, we investigated fine grading of handwriting capabilities by predicting SEMS score (between 0 and 12) with deep learning. Our approach provide accuracy more than 99% and root mean square error lower than one, with automatic instead of manual feature extraction and selection. Furthermore, we used smart pen called SensoGrip, a pen equipped with sensors to capture handwriting dynamics, instead of a tablet, enabling writing evaluation in more realistic scenarios.