The neurological condition known as dyslexia, which is more common in men, has a substantial impact on reading and comprehension skills, especially in school-age children. Poor academic achievement and long-term effects on self-esteem are possible outcomes of this disorder. This work investigates the application of the Random Forest algorithm, a machine learning method renowned for its accuracy and resilience, to enhance the diagnosis of dyslexia. In order to categorize people with dyslexia, the Random Forest algorithm is applied to a dataset of behavioural and brain markers. The goal is to find patterns and biomarkers that can help with early detection. This method uses Random Forests' ensemble nature to improve model reliability and generalization, addressing major issues in dyslexia diagnosis such the necessity for interpretable biomarkers and the possibility of overfitting. The study's findings show that the Random Forest algorithm has the capacity to detect dyslexia with clinically meaningful accuracy, providing a promising tool for early intervention and assistance.
Keywords: Dyslexia, Neurological condition, Machine learning, Early identification, Data anonymization technique.