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

Identifying dyslexia in school pupils from eye movement and demographic data using artificial intelligence

This paper represents our research results in the pursuit of the following objectives: (i) to introduce a novel multi-sources data set to tackle the shortcomings of the previous data sets, (ii) to propose a robust artificial intelligence-based solution to identify dyslexia in primary school pupils, (iii) to investigate our psycholinguistic knowledge by studying the importance of the features in identifying dyslexia by our best AI model. In order to achieve the first objective, we collected and annotated a new set of eye-movement-during-reading data. Furthermore, we collected demographic data, including the measure of non-verbal intelligence, to form our three data sources. Our data set is the largest eye-movement data set globally. Unlike the previously introduced binary-class data sets, it contains (A) three class labels and (B) reading speed. Concerning the second objective, we formulated the task of dyslexia prediction as regression and classification problems and scrutinized the performance of 12 classifications and eight regressions approaches. We exploited the Bayesian optimization method to fine-tune the hyperparameters of the models: and reported the average and the standard deviation of our evaluation metrics in a stratified ten-fold cross-validation. Our studies showed that multi-layer perceptron, random forest, gradient boosting, and k-nearest neighbor form the group having the most acceptable results. Moreover, we showed that although separately using each data source did not lead to accurate results, their combination led to a reliable solution. We also determined the importance of the features of our best classifier: our findings showed that the IQ, gender, and age are the top three important features; we also showed that fixation along the y-axis is more important than other fixation data. Dyslexia detection, eye fixation, eye movement, demographic, classification, regression, artificial intelligence.

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

When reading, dyslexic readers exhibit more and longer fixations than normal readers. However, there is no significant difference when dyslexic and control readers perform only visual tasks on a string of letters, showing the importance of cognitive processes in reading. This linguistic and cognitive processing requirement in reading is often perturbed for dyslexic readers by perceived additional letters and word mirror images superposed on the primary images on the primary cortex, inducing internal visual crowding. Here, we show that while for a normal reader, the number and the duration of fixations remain invariant whatever the nature of the lighting, the excess of fixations and total duration of reading can be controlled for a dyslexic reader using the Hebbian mechanisms to erase extra images in optimized pulse-width lighting. In this case, the number of fixations can then be reduced by a factor of about 1.8, recovering the normal reading experiment.

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

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.

Predicting Dyslexia in Adolescents from Eye Movements during Free Painting Viewing

It is known that dyslexics present eye movement abnormalities. Previously, we have shown that eye movement abnormalities during reading or during saccade and vergence testing can predict dyslexia successfully. The current study further examines this issue focusing on eye movements during free exploration of paintings; the dataset was provided by a study in our laboratory carried by Ward and Kapoula. Machine learning (ML) classifiers were applied to eye movement features extracted by the software AIDEAL: a velocity threshold analysis reporting amplitude speed and disconjugacy of horizontal saccades. In addition, a new feature was introduced that concerns only the very short periods during which the eyes were moving, one to the left the other to the right; such periods occurred mostly during fixations between saccades; we calculated a global index of the frequency of such disconjugacy segments, of their duration and their amplitude. Such continuous evaluation of disconjugacy throughout the time series of eye movements differs from the disconjugacy feature that describes inequality of the saccade amplitude between the two eyes. The results show that both AIDEAL features, and the Disconjugacy Global Index (DGI) enable successful categorization of dyslexics from non-dyslexics, at least when applying this analysis to the specific paintings used in the present study. We suggest that this high power of predictability arises from both the content of the paintings selected and the physiologic relevance of eye movement features extracted by the AIDEAL and the DGI.

Spatiotemporal Eye-Tracking Feature Set for Improved Recognition of Dyslexic Reading Patterns in Children

Considering the detrimental effects of dyslexia on academic performance and its common occurrence, developing tools for dyslexia detection, monitoring, and treatment poses a task of significant priority. The research performed in this paper was focused on detecting and analyzing dyslexic tendencies in Serbian children based on eye-tracking measures. The group of 30 children (ages 7–13, 15 dyslexic and 15 non-dyslexic) read 13 different text segments on 13 different color configurations. For each text segment, the corresponding eye-tracking trail was recorded and then processed offline and represented by nine conventional features and five newly proposed features. The features were used for dyslexia recognition using several machine learning algorithms: logistic regression, support vector machine, k-nearest neighbor, and random forest. The highest accuracy of 94% was achieved using all the implemented features and leave-one-out subject cross-validation. Afterwards, the most important features for dyslexia detection (representing the complexity of fixation gaze) were used in a statistical analysis of the individual color effects on dyslexic tendencies within the dyslexic group. The statistical analysis has shown that the influence of color has high inter-subject variability. This paper is the first to introduce features that provide clear separability between a dyslexic and control group in the Serbian language (a language with a shallow orthographic system). Furthermore, the proposed features could be used for diagnosing and tracking dyslexia as biomarkers for objective quantification.