What is Dysgraphia?

Dysgraphia is a neurological disorder characterized by writing disabilities.
Specifically, the disorder causes a person’s writing to be distorted or incorrect. In children, the disorder generally emerges when they are first introduced to writing. They make inappropriately sized and spaced letters, or write wrong or misspelled words, even thorough instruction has been provided. Children with the disorder may have other learning disabilities; however, they usually have no social or other academic problems.

Is there any treatment?

Treatment for Dysgraphia varies and may include treatment for motor disorders to help control writing movements. Other treatments may address impaired memory or other neurological problems.

Current Research on Dysgraphia

One of the biggest challenges the dysgraphia community has is a lack of a standardize test or tool to know if the child is dysgraphic or not. To know this early would help significantly in the child’s academic endeavors. Below is a list of some work that is ongoing that we are monitoring.

“Dysgraphia Detection Through Machine Learning” (2020)

Dr.’s Peter Drotar and Marek Dobes, of Slovakia, have completed studies using an advanced Machine Learning adaptive boosting algorithm to determine dysgraphic from non-dysgraphic students. Their work demonstrated an 80% accuracy in making this judgement independent of sex, age, or handedness. To read their recent publication in Nature, click link below.
Recent Publication

BOLD (June 2018)

BOLD is an interdisciplinary initiative dedicated to spreading the word about how children and young people develop and learn. Researchers at various stages of their careers – some are associated with the Jacobs Foundation, others are not – as well as science journalists, policymakers, and practitioners have their say on this platform. Thibault Asselborn, Doctoral Student Swiss Federal Institute of Technology Lausanne, Zürich, Switzerland, published on the BOLD platform a paper on their work in detecting Dysgraphia early. “To address these issues, my lab has developed a digital version of the BHK test that can be administered on a tablet computer. Based on data from over 1,000 children, we created a machine-learning algorithm to predict dysgraphia that correctly identifies about 95% of children diagnosed as “dysgraphic” using the conventional version of the BHK test.”