A scalable and freely accessible machine learning–based web application for the early detection of dyslexia

Isha Puri, New York, USA 16-18

I built an application that can accurately screen children for dyslexia using just the standard inbuilt laptop webcam! My application records a video of a child reading a standard passage on the screen, tracks the movements of the pupils using a highly accurate eye-tracking methodology, and then determines the average fixation duration. Based on this metric, the application was able to predict if a child has a higher risk of dyslexia with an accuracy of 90.18%, as tested on a dataset of real dyslexic patients with 370 samples classified as high or low risk.

Show more