Predictive modeling for early dyslexia severity assessment in children using ML algorithms

Dyslexia is a widespread learning disorder that impacts a child's reading ability, writing, and comprehension skills, thereby affecting their capacity to read words, spell, and comprehend written material. Early detection is important since early intervention enhances learning. This study introduces a predictive model with a view to detecting dyslexia levels in children through guided quizzes and surveys carried out under parental supervision. The process of assessment has a two-stage process, and it starts with a series of initial questions that test the language ability of the child, patterns of reading, and intellectual capacity. Depending on these answers, the model pinpoints children who are likely to be dyslexic. They are then advised to undergo a second, more in-depth assessment, which helps to narrow down the diagnosis by examining certain indicators more closely. The primary objective of this model is to allow for early identification, thus allowing parents and teachers to implement suitable learning approaches and interventions. Through the identification of dyslexia at its early stages, the model seeks to improve educational support systems to enable children to acquire proper reading skills and enhance their academic performance as a whole.