A groundbreaking study from the University at Buffalo demonstrates how artificial intelligence can transform the early detection of learning disabilities in children through handwriting analysis.
The research, published in the journal SN Computer Science on May 14, 2025, outlines a framework that uses AI to identify subtle patterns in children's handwriting that correlate with dyslexia and dysgraphia. Led by Venu Govindaraju, SUNY Distinguished Professor in Computer Science and Engineering, the team built upon his previous pioneering work in handwriting recognition technology that has been used by the U.S. Postal Service for mail sorting.
"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," explains Govindaraju, who serves as the corresponding author of the study.
The AI system analyzes various aspects of handwriting, including letter formation, spacing, writing speed, pressure, and pen movements. It can detect spelling issues, organization problems, and other indicators that might be missed in traditional assessments. While previous research has focused primarily on dysgraphia detection, this new approach aims to identify both conditions simultaneously.
To develop their models, the researchers collaborated with Abbie Olszewski from the University of Nevada, Reno, who co-developed the Dysgraphia and Dyslexia Behavioral Indicator Checklist (DDBIC). The team collected writing samples from kindergarten through 5th-grade students and is using this data to train AI models that can complete the screening process.
This technology addresses a critical nationwide shortage of speech-language pathologists and occupational therapists who typically diagnose these conditions. Current screening tools, while effective, are often costly, time-consuming, and focus on only one condition at a time. The AI-powered approach could make early detection more widely available, particularly in underserved communities.
The work is part of the National AI Institute for Exceptional Education, a UB-led research organization developing AI systems to identify and assist young children with speech and language processing disorders. By enabling earlier intervention, this technology could significantly improve educational outcomes for millions of children worldwide.