Detecting Phase-Synchrony Connectivity Anomalies in EEG Signals. Application to Dyslexia Diagnosis

Abstract

Objective Dyslexia diagnosis is a challenging task, since traditional diagnosis methods are not based on biological markers but on behavioural tests. Although dyslexia diagnosis has been addressed by these tests in clinical practice, it is difficult to extract information about the brain processes involved in the different tasks and, then, to go deeper into its biological basis. Thus, the use of biomarkers can contribute not only to the diagnosis but also to a better understanding of specific learning disorders such as dyslexia. In this work, we use Electroencephalography (EEG) signals to discover differences among controls and dyslexic subjects using signal processing and artificial intelligence techniques. Specifically, we measure phase synchronization among channels, to reveal the functional brain network activated during auditory processing. On the other hand, to explore synchronicity patterns risen by low-level auditory processing, we used specific stimuli consisting in band-limited white noise, modulated in amplitude at different frequencies. The differential information contained in the functional (i.e., synchronization) network has been processed by an anomaly detection system that addresses the problem of subjects variability by an outlier-detection method based on vector quantization. The results, obtained for 7 years-old children, show that the proposed method constitutes an useful tool for clinical use, with the area under ROC curve (AUC) values up to 0.95 in differential diagnosis tasks.

Complex Pearson Correlation Coefficient for EEG Connectivity Analysis

“…By averaging over the trial set, the proposed measures could also be used as a solution to improve the prediction results of the phases of the synchronization and desynchronization tasks [34]. The potential application of CPCC also lies in the assessment of mental stress levels using functional connectivity as a parameter [35,36] and in the diagnosis dyslexia [37]. In addition, the proposed measures could be used as parameters for the evaluation of simulated EEG data based on the theory of functional connectivity of the brain [38].…”

From brain to education through machine learning: Predicting literacy and numeracy skills from neuroimaging data

“…The SVM, which is implemented in several decoding toolboxes as a default method (e.g., The Decoding Toolbox; Hebart et al, 2014), is useful for classifying among different groups, such as children with learning disability versus controls. However, studies have also used other techniques, such as logistic regressions (Cui et al, 2016), decision tree (Torres-Ramos et al, 2020), random forest (RF) (Nemmi et al, 2023), naïve Bayes classifiers (NBC) (Formoso et al, 2021), discriminant analysis (DA) (Bach et al, 2013), k-nearest neighbors (kNN) (Ventura-Campos et al, 2013), and artificial neural networks (ANN) (Tomaz Da Silva et al, 2021).…”

“…Using sMRI (GM) data, but with a larger sample size including children from three different countries (130 children with dyslexia and 109 typically-developing children), Płoński et al (2017) replicated these findings. Finally, some studies have reported successful classification between children with and without dyslexia based on task-electroencephalogram (EEG) with word comprehension (Zainuddin et al, 2018) and auditory stimuli listening (Formoso et al, 2021), and resting magnetoencephalography (MEG) signals (Dimitriadis et al, 2018). Although many of the studies above rely on rest-fMRI or sMRI data, more recent studies have also used task-fMRI data.…”