Dysgraphia, a specific learning disability that impairs handwriting and fine motor skills, often remains undetected due to its subtle presentation and lack of standardized screening methods. This paper proposes a computational framework for the early detection of dysgraphia in children, leveraging handwriting analysis as the sole diagnostic input. The dataset comprises handwriting samples of students aged 6-10 years. Feature extraction techniques were applied to quantify aspects such as stroke formation, letter spacing, alignment, pressure patterns, and writing speed. These features were then used to train machine learning classifiers to distinguish between typical and dysgraphic handwriting profiles. The proposed method aims to provide a scalable, costeffective, and non-invasive alternative to conventional diagnostic practices, with potential applications in educational and clinical settings for early intervention and support.