Methodological issues in the creation of a diagnosis tool for dysgraphia

Problèmes méthodologiques liés à la création d'un outil de diagnostic de la dysgraphie

Louis Deschamps (1) , Clement Gaffet (1) , Saifeddine Aloui (1) , Jérôme Boutet (1) , Vincent Brault (2) , Etienne Labyt (1)

1 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
2 SVH - Statistique pour le Vivant et l’Homme

Asselborn et al. have created a diagnosis tool for dysgraphia, based on dynamic data acquired with common graphic tablets. The results they obtained seem very satisfactory. According to the authors, their work “can be deployed directly as a diagnostics tool”. We think that this conclusion should be qualified, as we have detected some methodological issues that we perceive to be important. In this comment, we outline three main arguments and several concerns that motivate our opinion.

Mots clés: Dysgraphia; Methodological issues; Machine learning application

Mots clés: Dysgraphie; Problèmes méthodologiques

Domaines: Applications [stat.AP]; Méthodologie [stat.ME]

Louis Deschamps, Clement Gaffet, Saifeddine Aloui, Jérôme Boutet, Vincent Brault, et al.. Methodological issues in the creation of a diagnosis tool for dysgraphia. npj Digital Medicine, 2019, 2, pp.36:1-3. ⟨10.1038/s41746-019-0114-0⟩. ⟨hal-02136874⟩