Dyslexia, affecting an estimated 10% to 20% of the global population, significantly impairs learning capabilities, underscoring the need for innovative and accessible diagnostic methods. This paper explores the effectiveness of eye-tracking technology combined with machine learning algorithms as a cost-effective approach for early dyslexia detection.

By analyzing general eye movement patterns—such as prolonged fixation durations and erratic saccades—we propose an enhanced method for identifying eye-tracking-based dyslexia features. A Random Forest Classifier was employed to detect dyslexia, achieving an accuracy of 88.58%. Additionally, hierarchical clustering methods were applied to identify varying severity levels of dyslexia.

This analysis integrates diverse methodologies across different populations and settings, demonstrating the potential of this technology to identify individuals with dyslexia, including those with borderline traits, through non-invasive means. The integration of eye-tracking with machine learning represents a significant advancement in dyslexia diagnostics, offering a highly accurate and accessible method for clinical research.