Review of EEG-based pattern classification frameworks for dyslexia

Deep learning-driven dyslexia detection model using multi-modality data

Background

Dyslexia is a neurological disorder that affects an individual's language processing abilities. Early care and intervention can help dyslexic individuals succeed academically and socially. Recent developments in deep learning (DL) approaches motivate researchers to build dyslexia detection models (DDMs). DL approaches facilitate the integration of multi-modality data. However, there are few multi-modality-based DDMs.

Methods

In this study, the authors built a DL-based DDM using multi-modality data. A squeeze and excitation (SE) integrated MobileNet V3 model, self-attention mechanisms (SA) based EfficientNet B7 model, and early stopping and SA-based Bi-directional long short-term memory (Bi-LSTM) models were developed to extract features from magnetic resonance imaging (MRI), functional MRI, and electroencephalography (EEG) data. In addition, the authors fine-tuned the LightGBM model using the Hyperband optimization technique to detect dyslexia using the extracted features. Three datasets containing FMRI, MRI, and EEG data were used to evaluate the performance of the proposed DDM.

Results

The findings supported the significance of the proposed DDM in detecting dyslexia with limited computational resources. The proposed model outperformed the existing DDMs by producing an optimal accuracy of 98.9%, 98.6%, and 98.8% for the FMRI, MRI, and EEG datasets, respectively. Healthcare centers and educational institutions can benefit from the proposed model to identify dyslexia in the initial stages. The interpretability of the proposed model can be improved by integrating vision transformers-based feature extraction.

Developmental Dyslexia: Insights from EEG-Based Findings and Molecular Signatures-A Pilot Study

Developmental dyslexia (DD) is a learning disorder. Although risk genes have been identified, environmental factors, and particularly stress arising from constant difficulties, have been associated with the occurrence of DD by affecting brain plasticity and function, especially during critical neurodevelopmental stages. In this work, electroencephalogram (EEG) findings were coupled with the genetic and epigenetic molecular signatures of individuals with DD and matched controls. Specifically, we investigated the genetic and epigenetic correlates of key stress-associated genes (NR3C1, NR3C2, FKBP5, GILZ, SLC6A4) with psychological characteristics (depression, anxiety, and stress) often included in DD diagnostic criteria, as well as with brain EEG findings. We paired the observed brain rhythms with the expression levels of stress-related genes, investigated the epigenetic profile of the stress regulator glucocorticoid receptor (GR) and correlated such indices with demographic findings. This study presents a new interdisciplinary approach and findings that support the idea that stress, attributed to the demands of the school environment, may act as a contributing factor in the occurrence of the DD phenotype.

EEG Based Functional Brain Network Analysis and Classification of Dyslexic Children During Sustained Attention Task

Reading is a complex cognitive skill that involves visual, attention, and linguistic skills. Because attention is one of the most important cognitive skills for reading and learning, the current study intends to examine the functional brain network connectivity implicated during sustained attention in dyslexic children. 15 dyslexic children (mean age 9.83±1.85 years) and 15 non-dyslexic children (mean age 9.91±1.97 years) were selected for this study. The children were asked to perform a visual continuous performance task (VCPT) while their electroencephalogram (EEG) signals were recorded. In dyslexic children, significant variations in task measurements revealed considerable omission and commission errors. During task performance, the dyslexic group with the absence of a small-world network had a lower clustering coefficient, a longer characteristic pathlength, and lower global and local efficiency than the non-dyslexic group (mainly in theta and alpha bands). When classifying data from the dyslexic and non-dyslexic groups, the current study achieved the maximum classification accuracy of 96.7% using a k-nearest neighbor (KNN) classifier. To summarize, our findings revealed indications of poor functional segregation and disturbed information transfer in dyslexic brain networks during a sustained attention task.

Transformers for autonomous recognition of psychiatric dysfunction via raw and imbalanced EEG signals

Early identification of mental disorders, based on subjective interviews, is extremely challenging in the clinical setting. There is a growing interest in developing automated screening tools for potential mental health problems based on biological markers. Here, we demonstrate the feasibility of an AI-powered diagnosis of different mental disorders using EEG data. Specifically, this work aims to classify different mental disorders in the following ecological context accurately: (1) using raw EEG data, (2) collected during rest, (3) during both eye open, and eye closed conditions, (4) at short 2-min duration, (5) on participants with different psychiatric conditions, (6) with some overlapping symptoms, and (7) with strongly imbalanced classes. To tackle this challenge, we designed and optimized a transformer-based architecture, where class imbalance is addressed through focal loss and class weight balancing. Using the recently released TDBRAIN dataset (n= 1274 participants), our method classifies each participant as either a neurotypical or suffering from major depressive disorder (MDD), attention deficit hyperactivity disorder (ADHD), subjective memory complaints (SMC), or obsessive-compulsive disorder (OCD). We evaluate the performance of the proposed architecture on both the window-level and the patient-level. The classification of the 2-min raw EEG data into five classes achieved a window-level accuracy of 63.2% and 65.8% for open and closed eye conditions, respectively. When the classification is limited to three main classes (MDD, ADHD, SMC), window level accuracy improved to 75.1% and 69.9% for eye open and eye closed conditions, respectively. Our work paves the way for developing novel AI-based methods for accurately diagnosing mental disorders using raw resting-state EEG data.

Event-related potential and lexical decision task in dyslexic adults: Lexical and lateralization effects

Developmental dyslexia is a specific learning disorder that presents cognitive and neurobiological impairments related to different patterns of brain activation throughout development, continuing in adulthood. Lexical decision tasks, together with electroencephalography (EEG) measures that have great temporal precision, allow the capture of cognitive processes during the task, and can assist in the understanding of altered brain activation processes in adult dyslexics. High-density EEG allows the use of temporal analyses through event-related potentials (ERPs). The aim of this study was to compare and measure the pattern of ERPs in adults with developmental dyslexia and good readers, and to characterize and compare reading patterns between groups. Twenty university adults diagnosed with developmental dyslexia and 23 healthy adult readers paired with dyslexics participated in the study. The groups were assessed in tests of intelligence, phonological awareness, reading, and writing, as well as through the lexical decision test (LDT). During LDT, ERPs were recorded using a 128-channel EEG device. The ERPs P100 occipital, N170 occipito-temporal, N400 centro-parietal, and LPC centro-parietal were analyzed. The results showed a different cognitive profile between the groups in the reading, phonological awareness, and writing tests but not in the intelligence test. In addition, the brain activation pattern of the ERPs was different between the groups in terms of hemispheric lateralization, with higher amplitude of N170 in the dyslexia group in the right hemisphere and opposite pattern in the control group and specificities in relation to the items of the LDT, as the N400 were more negative in the Dyslexia group for words, while in the control group, this ERP was more pronounced in the pseudowords. These results are important for understanding different brain patterns in developmental dyslexia and can better guide future interventions according to the changes found in the profile.

EEG based functional brain networks analysis in dyslexic children during arithmetic task

Developmental Dyslexia is a neuro-developmental disorder that often refers to a phonological processing deficit regardless of average IQ. The present study investigated the distinct functional changes in brain networks of dyslexic children during arithmetic task performance using an electroencephalogram. Fifteen dyslexic children and fifteen normally developing children (NDC) were recruited and performed an arithmetic task. Brain functional network measures such as node strength, clustering coefficient, characteristic pathlength and small-world were calculated using graph theory methods for both groups. Task performance showed significantly less performance accuracy in dyslexics against NDC. The neural findings showed increased connectivity in the delta band and reduced connectivity in theta, alpha, and beta band at temporoparietal, and prefrontal regions in dyslexic group while performing the task. The node strengths were found to be significantly high in delta band (T3, O1, F8 regions) and low in theta (T5, P3, Pz regions), beta (Pz) and gamma band (T4 and prefrontal regions) during the task in dyslexics compared to the NDC. The clustering coefficient was found to be significantly low in the dyslexic group (theta and alpha band) and characteristic pathlength was found to be significantly high in the dyslexic group (theta and alpha band) compared to the NDC group while performing task. In conclusion, the present study shows evidence for poor fact-retrieval mechanism and altered network topology in dyslexic brain networks during arithmetic task performance.

Trends in Dyslexia Research during the Period 1950 to 2020-Theories, Definitions, and Publications

INTRODUCTION

The focus of the present paper is on (1) how dyslexia research and hence definitions have developed during the period 1950-2020 and includes (2) a database search of scientific publications on dyslexia during the same period. The focus is on the definitions of dyslexia and the organization of the network search based on the causal four-level model by Morton and Frith.

METHOD

(1) The definitions are presented in accordance with a historic review of dyslexia research from 1950 to 2020 and based on (2) Google Scholar counts of publications on dyslexia, on defining dyslexia, on dyslexia at the four levels (symptomatic, cognitive, biological, environmental), and by areas (sensorimotor, comorbidity). Finally, a percentage calculation shows the relative development within each level and area by decennium (1950-1960, 1960-1970, 1970-1980, 1990-2000, 2002-2010, 2010-2020).

RESULTS

(1) Of the seven definitions presented, only the definition by the BDA 2007 included the four levels of the causal model. (2) The number of publications increased substantially over the period. However, relatively few publications have defined dyslexia. An increase in publications from 1950 to 2020 was seen across the four levels and two areas-however, with an alteration in the thematic focus over this time span.

SUMMARY

Defining dyslexia has still not reached a consensus. This uncertainty may explain why only one of the seven definitions proved satisfactory according to the four-level model. Along with the general increase in research, publications on dyslexia have increased accordingly during the period 1950 to 2020. Although the symptomatic level has played a dominant role over the whole period, thematic shifts have been seen over these 70 years. In particular, a substantial thematic shift was seen by the turn of the millennium. There has been a relative increase in the focus on literacy at the symptomatic level, on phonological awareness at the cognitive level, in gender at the biological level, and second language learning as comorbidities. However, increases in counts are not alone a valid indication of scientific progress. In particular, the lack of definitional criteria as a basis for participant and method selection should attract much more focus in future studies. The present study underlines the multifactorial nature of dyslexia, as evidenced by a substantial increase in the number of publications on the subject. It is a challenge for future research to continuously use and possibly redefine dyslexia definitions in line with such standards.

Executive function during typing on computer

In recent decades, computer typing has become one of the fundamental tools for personal communication in everyday life. Typing is a multi-level hierarchical process that involves a large number of cognitive and physiological functions. Executive functions (EF), such as working memory and executive control, actively influence the inhibitory and activation processes during typing. Using the example of the work of the IF, one can observe the hierarchical organization of the central and peripheral parts of the nervous system during typing. However, there are not so many studies aimed at studying the neurophysiology of typing, and there were no works devoted to the study of EF in typing. In this regard, this article discusses the potential possibilities of studying EF by typing on a computer and provides examples of experiments and models that can be used in such studies. The article also describes the main psychophysiological studies in which typing was involved and a review of methods for studying and analyzing typing was conducted.