DysLexML: Screening Tool for Dyslexia Using Machine Learning

Asvestopoulou, Thomais; Manousaki, Victoria; Psistakis, Antonis; Smyrnakis, Ioannis; Andreadakis, Vassilios; Aslanides, Ioannis M.; Papadopouli, Maria

doi:10.48550/arxiv.1903.06274

Cited by 10 publications

(18 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The text was written in the subjects' native language, Serbian, which has a perfect matching between letters and phonemes. Considering dyslexia detection in such languages (the ones with a shallow orthographic system) is often quite difficult; an accuracy of 94% achieved on the balanced dataset used in this paper (F1 score 0.93 and AUROC 0.96) (Table 2) shows a promising result that is comparable to the ones achieved in the literature [29,30,32,33,[35][36][37][39][40][41] which were performed on languages with deeper orthographic systems. As the Serbian language has a shallow orthographic system, making dyslexia harder to diagnose, we consider the observed subject pool relevant for the performed research purposes for a language such as Serbian.…”

Section: Discussionsupporting

confidence: 68%

“…As the Serbian language has a shallow orthographic system, making dyslexia harder to diagnose, we consider the observed subject pool relevant for the performed research purposes for a language such as Serbian. Although the number of participants used in this study is lower than the subject groups found in the literature [28,29,36,39,40], the number of total used trials (378 trials, explained in Section 3.1) provided enough data for the performed type of machine learning analysis.…”

Section: Discussionmentioning

confidence: 99%

“…A study including 69 children (32 with dyslexia) was conducted in [36]. The children were aged 8.5-12.5 and read two text paragraphs in Greek.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

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

Vajs

Ković

Papić

et al. 2022

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionsupporting

confidence: 68%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Vajs

Ković

Papić

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In a previous study conducted by the lab, it was found that dyslexics had more difficulty with binocular coordination while reading a more complex, nonsense text than when they were reading an easier text that carried a narrative. Indeed, another study has demonstrated that predictive power of determining dyslexia was stronger while studying more difficult texts [ 35 ]. We therefore concluded that dyslexics’ oculomotor profiles were destabilized while reading more complex nonsense texts.…”

Section: Methodsmentioning

confidence: 99%

Creativity, Eye-Movement Abnormalities, and Aesthetic Appreciation of Magritte’s Paintings

Ward

Kapoula

2022

Brain Sciences

View full text Add to dashboard Cite

Dyslexic children have been shown to be more creative than their non-dyslexic counterparts. They have also been shown to have an abnormal oculomotor profile while viewing targets in free space, making vergence or saccadic eye movements while reading or when viewing Op art. They show a slower deceleration of their eye movements and a difficulty in coordinating their two eyes to obtain single fused vision in depth. Interestingly, their abnormal oculo-motor profile is exacerbated while reading more difficult texts. Given these differences, we postulate that dyslexics’ increased creativity may be related to their different eye movement control affecting how they perceive the world. Therefore, we decided to measure adolescent dyslexics’ creativity, oculomotor profile, and subjective responses while they viewed three paintings by Magritte. These were chosen to stimulate the perception of hidden conceptual spaces or stimulate conflict between the perception of the figural and textural content. For the first time to our knowledge, dyslexic adolescents were demonstrated to be more creative in terms of flexibility and fluidity than their non-dyslexic peers. Subjectively, while viewing the Magritte paintings, dyslexics reported fewer conceptual spaces and fewer hidden words than their non-dyslexic peers; thus, they confabulated less than non-dyslexics. Dyslexics also demonstrated an abnormal oculomotor profile similar to those that we have shown when reading, viewing randomized targets, and while perceiving illusions of depth in Op art paintings, in that they demonstrated difficulty with disconjugation and abnormalities in their eye velocity profiles. We propose there may be a link between dyslexic increased creativity and their eye movement abnormalities. Similar to reading nonsense text, we propose that Magritte’s contradictory paintings exacerbate dyslexics’ eye movement abnormalities. These eye movement abnormalities while viewing these particular paintings might provide a physiological signature suggesting a contribution of their unusual eye control to their higher creativity scores.

show abstract

“…Asvestopoulou et al [ 3 ] reported evidence for the predictive capacity of eye movement abnormalities during reading texts and the dependency of the predictive power on the type of reading text. In a more recent study, El Hmimdi et al [ 4 ] investigated predicting dyslexia using a set of linear and nonlinear classifiers, by considering all eye movement features (latency, peak and average velocity, duration, amplitude, disconjugacy during post-saccadic drifts or of the saccade itself, etc.…”

Section: Introductionmentioning

confidence: 99%

Predicting Dyslexia in Adolescents from Eye Movements during Free Painting Viewing

et al. 2022

View full text Add to dashboard Cite

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.

show abstract

DysLexML: Screening Tool for Dyslexia Using Machine Learning

Cited by 10 publications

References 0 publications

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

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

Creativity, Eye-Movement Abnormalities, and Aesthetic Appreciation of Magritte’s Paintings

Predicting Dyslexia in Adolescents from Eye Movements during Free Painting Viewing

Contact Info

Product

Resources

About