Differential diagnosis of vergence and saccade disorders in dyslexia

Can Saccade and Vergence Properties Discriminate Stroke Survivors from Individuals with Other Pathologies? A Machine Learning Approach

Recent studies applying machine learning (ML) to saccade and vergence eye movements have demonstrated the ability to distinguish individuals with dyslexia, learning disorders, or attention disorders from healthy individuals or those with other pathologies. Stroke patients are known to exhibit visual deficits and eye movement disorders. This study focused on saccade and vergence measurements using REMOBI technology V3 and the Pupil Core eye tracker. Eye movement data were automatically analyzed with the AIDEAL V3 (Artificial Intelligence Eye Movement Analysis) cloud software developed by Orasis-Ear. This software computes multiple parameters for each type of eye movement, including the latency, accuracy, velocity, duration, and disconjugacy. Three ML models (logistic regression, support vector machine, random forest) were applied to the saccade and vergence eye movement features provided by AIDEAL to identify stroke patients from other groups: a population of children with learning disorders and a population with a broader spectrum of dysfunctions or pathologies (including children and adults). The different classifiers achieved macro F1 scores of up to 75.9% in identifying stroke patients based on the saccade and vergence parameters. An additional ML analysis using age-matched groups of stroke patients and adults or seniors reduced the influence of large age differences. This analysis resulted in even higher F1 scores across all three ML models, as the comparison group predominantly included healthy individuals, including some with presbycusis. In conclusion, ML applied to saccade and vergence eye movement parameters, as measured by the REMOBI and AIDEAL technology, is a sensitive method for the detection of stroke-related sequelae. This approach could be further developed as a clinical tool to evaluate recovery, compensation, and the evolution of neurological deficits in stroke patients.

The perceptual span in dyslexic reading and visual search

Many studies have attempted to identify the root cause of dyslexia. Different theories of dyslexia have proposed either a phonological, attentional, or visual deficit. While research has used eye-tracking to study dyslexia, only two previous studies have used the moving-window paradigm to explore the perceptual span in dyslexic reading, and none have done so in visual search. The present study analysed the perceptual span using both reading and visual search tasks to identify language-independent attentional impairments in dyslexics. We found equivocal evidence that the perceptual span was impaired in dyslexic reading and no evidence of impairment in visual search. However, dyslexic participants did show deficits in the visual search task, with lower search accuracy and shorter saccades compared with controls. These results lend support for a visual, rather than attentional or phonological, account of dyslexia.

Efficient diagnostic classification of diverse pathologies through contextual eye movement data analysis with a novel hybrid architecture

The analysis of eye movements has proven valuable for understanding brain function and the neuropathology of various disorders. This research aims to utilize eye movement data analysis as a screening tool for differentiation between eight different groups of pathologies, including scholar, neurologic, and postural disorders. Leveraging a dataset from 20 clinical centers, all employing AIDEAL and REMOBI eye movement technologies this study extends prior research by considering a multi-annotation setting, incorporating information from recordings from saccade and vergence eye movement tests, and using contextual information (e.g. target signals and latency of the eye movement relative to the target and confidence level of the quality of eye movement recording) to improve accuracy while reducing noise interference. Additionally, we introduce a novel hybrid architecture that combines the weight-sharing feature of convolution layers with the long-range capabilities of the transformer architecture to improve model efficiency and reduce the computation cost by a factor of 3.36, while still being competitive in terms of macro F1 score. Evaluated on two diverse datasets, our method demonstrates promising results, the most powerful discrimination being Attention & Neurologic; with a macro F1 score of up to 78.8%; disorder. The results indicate the effectiveness of our approach in classifying eye movement data from different pathologies and different clinical centers accurately, thus enabling the creation of an assistant tool in the future.

The effect of online visual games on visual perception, oculomotor, and balance skills of children with developmental dyslexia during the COVID-19 pandemic

PURPOSE

To evaluate the effect of online visual games on the balance, visual perception, and oculomotor skills of children with developmental dyslexia during the COVID-19 pandemic.

METHODS

In this single-blind randomized clinical trial, 50 children with developmental dyslexia, aged 7 to 11 years, were recruited from rehabilitation centers in Tehran, Iran, using a convenience sampling strategy. Participants were randomly divided into two groups: intervention (25) and control (25), with close matching based on sex, age, IQ, and type of disease. The interventions consisted of web-based online computer games focusing on visual perception and oculomotor skills. Outcome measures included the Test of Visual Perception Skills-Revised, the Pediatric Balance Scale, and videonystagmography. The Wechsler Intelligence Scale for Children-IV and the Reading and Dyslexia Test were used to evaluate IQ and reading skills, respectively.

RESULTS

The intervention group exhibited significant post-intervention improvements in the Test of Visual Perception Skills-Revised, tracking gain, saccade latency, and saccade velocity scores (all P < 0.001). In contrast, the control group showed no significant differences in these tests in pre- and post-intervention (all P > 0.05). Notably, post-intervention comparisons between the groups revealed significant differences in smooth pursuit eye movements (P < 0.001), saccade latency (P = 0.027), and saccade velocity (P < 0.001). The Pediatric Balance Scale scores remained unchanged in both groups post-intervention (intervention: P = 0.317; control: P = 0.999). Game face validity was affirmed with impact scores above 1.5 for all items, suggesting that the games were straightforward, clear, and relevant.

CONCLUSION

Online visual games enhanced oculomotor and visual perception skills in children with dyslexia but did not influence balance skills.

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.

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

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.

Disconjugate Eye Movements in Dyslexic Adolescents While Viewing Op Art: A Creative Handicap?

Op art was created, in part, to produce illusions of movement. Given that dyslexics have been shown to have impaired visuo-postural axis deficits, it may be possible that dyslexics see illusions different than their non-dyslexic peers. To test this theory, we measured eye movement and posture in 47 dyslexic (18 female, 29 male; mean age 15.4) and 44 non dyslexic (22 female, 22 male; mean age 14.8) adolescents while they viewed three works of art by Op artist Bridget Riley. They then responded to a questionnaire about how they felt while viewing the artworks. Dyslexics demonstrated significantly slower saccades in terms of average velocity that was particularly disturbed in paintings that manipulated depth. Subjectively, dyslexics felt much more destabilized compared to their peers; however, there was not a significant difference in objective postural measurements between the two groups. The sensation of destabilization was positively correlated with appreciation in non-dyslexic adolescents. These subjective results suggest that dyslexics may be more sensitive to movement in depth, which could be related to the instability in vergence movements. Whereas this instability represents a hinderance in relation to reading, it could be an advantage while viewing paintings such as these.

A Case for Studying Naturalistic Eye and Head Movements in Virtual Environments

Using head mounted displays (HMDs) in conjunction with virtual reality (VR), vision researchers are able to capture more naturalistic vision in an experimentally controlled setting. Namely, eye movements can be accurately tracked as they occur in concert with head movements as subjects navigate virtual environments. A benefit of this approach is that, unlike other mobile eye tracking (ET) set-ups in unconstrained settings, the experimenter has precise control over the location and timing of stimulus presentation, making it easier to compare findings between HMD studies and those that use monitor displays, which account for the bulk of previous work in eye movement research and vision sciences more generally. Here, a visual discrimination paradigm is presented as a proof of concept to demonstrate the applicability of collecting eye and head tracking data from an HMD in VR for vision research. The current work’s contribution is 3-fold: firstly, results demonstrating both the strengths and the weaknesses of recording and classifying eye and head tracking data in VR, secondly, a highly flexible graphical user interface (GUI) used to generate the current experiment, is offered to lower the software development start-up cost of future researchers transitioning to a VR space, and finally, the dataset analyzed here of behavioral, eye and head tracking data synchronized with environmental variables from a task specifically designed to elicit a variety of eye and head movements could be an asset in testing future eye movement classification algorithms.

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.

Dyslexics' Fragile Oculomotor Control Is Further Destabilized by Increased Text Difficulty

Dyslexic adolescents demonstrate deficits in word decoding, recognition, and oculomotor coordination as compared to healthy controls. Our lab recently showed intrinsic deficits in large saccades and vergence movements with a Remobi device independent from reading. This shed new light on the field of dyslexia, as it has been debated in the literature whether the deficits in eye movements are a cause or consequence of reading difficulty. The present study investigates how these oculomotor problems are compensated for or aggravated by text difficulty. A total of 46 dyslexic and 41 non-dyslexic adolescents' eye movements were analyzed while reading L'Alouette, a dyslexia screening test, and 35 Kilos D'Espoir, a children's book with a reading age of 10 years. While reading the more difficult text, dyslexics made more mistakes, read slower, and made more regressive saccades; moreover, they made smaller amplitude saccades with abnormal velocity profiles (e.g., higher peak velocity but lower average velocity) and significantly higher saccade disconjugacy. While reading the simpler text, these differences persisted; however, the difference in saccade disconjugacy, although present, was no longer significant, nor was there a significant difference in the percentage of regressive saccades. We propose that intrinsic eye movement abnormalities in dyslexics such as saccade disconjugacy, abnormal velocity profiles, and cognitively associated regressive saccades can be particularly exacerbated if the reading text relies heavily on word decoding to extract meaning; increased number of regressive saccades are a manifestation of reading difficulty and not a problem of eye movement per se. These interpretations are in line with the motor theory of visual attention and our previous research describing the relationship between binocular motor control, attention, and cognition that exists outside of the field of dyslexia.

The Relation between Physiological Parameters and Colour Modifications in Text Background and Overlay during Reading in Children with and without Dyslexia

Reading is one of the essential processes during the maturation of an individual. It is estimated that 5-10% of school-age children are affected by dyslexia, the reading disorder characterised by difficulties in the accuracy or fluency of word recognition. There are many studies which have reported that coloured overlays and background could improve the reading process, especially in children with reading disorders. As dyslexia has neurobiological origins, the aim of the present research was to understand the relationship between physiological parameters and colour modifications in the text and background during reading in children with and without dyslexia. We have measured differences in electroencephalography (EEG), heart rate variability (HRV), electrodermal activities (EDA) and eye movements of the 36 school-age (from 8 to 12 years old) children (18 with dyslexia and 18 of control group) during the reading task in 13 combinations of background and overlay colours. Our findings showed that the dyslexic children have longer reading duration, fixation count, fixation duration average, fixation duration total, and longer saccade count, saccade duration total, and saccade duration average while reading on white and coloured background/overlay. It was found that the turquoise background, turquoise overlay, and yellow background colours are beneficial for dyslexic readers, as they achieved the shortest time duration of the reading tasks when these colours were used. Additionally, dyslexic children have higher values of beta (15-40 Hz) and the broadband EEG (0.5-40 Hz) power while reading in one particular colour (purple), as well as increasing theta range power while reading with the purple overlay. We have observed no significant differences between HRV parameters on white colour, except for single colours (purple, turquoise overlay, and yellow overlay) where the control group showed higher values for mean HR, while dyslexic children scored higher with mean RR. Regarding EDA measure, we found systematically lower values in children with dyslexia in comparison to the control group. Based on the present results, we can conclude that both pastel and intense background/overlays are beneficial for reading of both groups and all sensor modalities could be used to better understand the neurophysiological origins in dyslexic children.