Predicting Dyslexia and Reading Speed in Adolescents from Eye Movements in Reading and Non-Reading Tasks: A Machine Learning Approach

There is evidence that abnormalities in eye movements exist during reading in dyslexic individuals. A few recent studies applied Machine Learning (ML) classifiers to such eye movement data to predict dyslexia. A general problem with these studies is that eye movement data sets are limited to reading saccades and fixations that are confounded by reading difficulty, e.g., it is unclear whether abnormalities are the consequence or the cause of reading difficulty. Recently, Ward and Kapoula used LED targets (with the REMOBI & AIDEAL method) to demonstrate abnormalities of large saccades and vergence eye movements in depth demonstrating intrinsic eye movement problems independent from reading in dyslexia. In another study, binocular eye movements were studied while reading two texts: one using the "Alouette" text, which has no meaning and requires word decoding, the other using a meaningful text. It was found the Alouette text exacerbates eye movement abnormalities in dyslexics. In this paper, we more precisely quantify the quality of such eye movement descriptors for dyslexia detection. We use the descriptors produced in the four different setups as input to multiple classifiers and compare their generalization performances. Our results demonstrate that eye movement data from the Alouette test predicts dyslexia with an accuracy of 81.25%; similarly, we were able to predict dyslexia with an accuracy of 81.25% when using data from saccades to LED targets on the Remobi device and 77.3% when using vergence movements to LED targets. Noticeably, eye movement data from the meaningful text produced the lowest accuracy (70.2%). In a subsequent analysis, ML algorithms were applied to predict reading speed based on eye movement descriptors extracted from the meaningful reading, then from Remobi saccade and vergence tests. Remobi vergence eye movement descriptors can predict reading speed even better than eye movement descriptors from the meaningful reading test.