Accessible Dyslexia Detection with Real-Time Reading Feedback through Robust Interpretable Eye-Tracking Features

Abstract

Developing reliable, quantifiable, and accessible metrics for dyslexia diagnosis and tracking represents an important goal, considering the widespread nature of dyslexia and its negative impact on education and quality of life. In this study, we observe eye-tracking data from 15 dyslexic and 15 neurotypical Serbian school-age children who read text segments presented on different color configurations. Two new eye-tracking features were introduced that quantify the amount of spatial complexity of the subject’s gaze through time and inherently provide information regarding the locations in the text in which the subject struggled the most. The features were extracted from the raw eye-tracking data (x, y coordinates), from the original data gathered at 60 Hz, and from the downsampled data at 30 Hz, examining the compatibility of features with low-cost or custom-made eye-trackers. The features were used as inputs to machine learning algorithms, and the best-obtained accuracy was 88.9% for 60 Hz and 87.8% for 30 Hz. The features were also used to analyze the influence of background/overlay color on the quality of reading, and it was shown that the introduced features separate the dyslexic and control groups regardless of the background/overlay color. The colors can, however, influence each subject differently, which implies that an individualistic approach would be necessary to obtain the best therapeutic results. The performed study shows promise in dyslexia detection and evaluation, as the proposed features can be implemented in real time as feedback during reading and show effectiveness at detecting dyslexia with data obtained using a lower sampling rate.

Reliability of a Tablet Computer-Based Dyslexia Screening Application Using an Eye-Tracking System

“…In individuals with dyslexia, the patterns of eye movement during reading are well documented. These patterns include an increase in fixation time and frequency, a reduction in saccade length, a higher rate of backward saccades (regressions), and, as a result, a slower reading speed [13][14][15][16][17]. This study successfully measured these characteristic patterns of the reading process in dyslexia using a tablet-based application.…”

“…These studies attempted to determine and apply measurable parameters of eye movement observed in dyslexia. Eye movements in dyslexic children differ from those in normal children [13][14][15][16][17]. Dyslexia is not an eye movement disorder; however, the differences in eye movement reflect problems of accuracy and fluency in the reading process of dyslexia.…”

Hebbian Control of Fixations in a Dyslexic Reader: A Case Report

“…In particular, the dyslexic reader makes more and longer fixations (about twice as many as a normal reader) and has longer reading times. Such observations have been made in different languages [12,13,15,30]. However, the causal relationship remains the subject of debate [44].…”

“…This excess of fixations in dyslexia, which has been studied by many groups [2,5,10,17-22] using different currently available eye-tracking systems [23], seems to provide a useful guide for detecting and predicting dyslexia using machine learning based on the eyetracking technique [24][25][26][27][28][29][30][31]. The role of external crowding [32,33] has been studied and discussed in developmental dyslexia [34,35].…”