AI shows promise in detecting dyslexia (difficulty reading due to problems identifying speech sounds and learning how they relate to letters and words) and dysgraphia (a neurological condition and learning difference in which someone has difficulty with writing for their age level) from what children write on paper and tablets.
The new study from the University at Buffalo outlines how artificial intelligence-powered handwriting analysis may serve as an early detection tool for dyslexia and dysgraphia among young children. This is in the form of a framework for developing an AI-integrated screening tool that can identify writing-based behavioural indicators of dyslexia and dysgraphia in children’s handwriting.
The research aims to augment current screening tools which are effective but can be costly, time-consuming and focus on only one condition at a time. The methodology deployed AI to identify spelling issues, poor letter formation, writing organization problems and other indicators of dyslexia and dysgraphia.
Current screening tools are expensive, require additional administration time beyond regular classroom activities, and are designed to screen exclusively for one condition, not for both dyslexia and dysgraphia, which often share some common behavioural characteristics.
The researchers used the Dysgraphia and Dyslexia Behavioral Indicator Checklist (DDBIC) to identify symptoms overlapping between dyslexia and dysgraphia.This emthodology seeks to establish appropriate educational trajectories by identifying areas of instructional need associated with writing during the early years of schooling.
Designing AI-enhanced tools from the end users’ standpoint
To begin the research, the science team gathered insight from teachers, speech-language pathologists and occupational therapists to help ensure the AI models they’re developing are viable in the classroom and other settings. This was in order to build AI-enhanced tools, from the end users’ standpoint.
Lead researcher Venu Govindaraju explains the significance of the study: “Catching these neurodevelopmental disorders early is critically important to ensuring that children receive the help they need before it negatively impacts their learning and socio-emotional development. Our ultimate goal is to streamline and improve early screening for dyslexia and dysgraphia, and make these tools more widely available, especially in underserved areas.”
Gathering data
The scienitsts collected paper and tablet writing samples from kindergarten through 5th grade students at an elementary school in Reno, U.S.. This part of the study was approved by an ethics board, and the data was anonymized to protect student privacy.
The scientists used these data to further validate the DDBIC tool. The tool focuses on 17 behavioural cues that occur before, during and after writing. The researchers also took the opportunity to train AI models to complete the DDBIC screening process. From this, they were able to compare how effective the models are compared to people administering the test.
The resultant models can:
- Detect motor difficulties by analyzing writing speed, pressure and pen movements.
- Examine visual aspects of handwriting, including letter size and spacing.
- Convert handwriting to text, spotting misspellings, letter reversals and other errors.
- Identify deeper cognitive issues based on grammar, vocabulary and other factors.
Going forwards
Ultimately, the researchers hope to develop a computer tool that combines all models, and can summarise their findings. From this, they expect, to be able to provide a comprehensive assessment.
While the research signals a potential benefit, there is a shortage of handwriting examples from children to train AI models with.
The study appears in the journal SN Computer Science, titled “AI-Enhanced Child Handwriting Analysis: A Framework for the Early Screening of Dyslexia and Dysgraphia.”
