Saccadic Detection in Virtual Gaming for Dyslexia Classification

Dyslexia (aka reading disability) is the most common cause of learning disabilities. It affects children across language orthographies, despite adequate intelligence and educational opportunity. Studies have shown that identifying children with dyslexia at young age is crucial to provide effective intervention to improve learning outcomes. Recently we demonstrated that children with reading disability exhibit impaired performance on a virtual maze learning task across language orthographies. Using a machine learning algorithm, we have achieved a classification accuracy up to 80%. This paper presents an algorithm, including image segmentation, synchronization of image and text data, saccade detection, and event alignment, using the eye-gazing data recorded from an eye tracker during maze-solving tasks. The saccadic events detected by this algorithm showed good correlation with the incorrect decisions participants made during maze-solving, which could be an additional variable to be used in the machine learning algorithm to enhance the accuracy for dyslexia classification.