Dyslexia Diagnosis by EEG Temporal and Spectral Descriptors: An Anomaly Detection Approach

Abstract

Diagnosis of learning difficulties is a challenging goal. There are huge number of factors involved in the evaluation procedure that present high variance among the population with the same difficulty. Diagnosis is usually performed by scoring subjects according to results obtained in different neuropsychological (performance-based) tests specifically designed to this end. One of the most frequent disorders is developmental dyslexia (DD), a specific difficulty in the acquisition of reading skills not related to mental age or inadequate schooling. Its prevalence is estimated between 5% and 12% of the population. Traditional tests for DD diagnosis aim to measure different behavioral variables involved in the reading process. In this paper, we propose a diagnostic method not based on behavioral variables but on involuntary neurophysiological responses to different auditory stimuli. The experiments performed use electroencephalography (EEG) signals to analyze the temporal behavior and the spectral content of the signal acquired from each electrode to extract relevant (temporal and spectral) features. Moreover, the relationship of the features extracted among electrodes allows to infer a connectivity-like model showing brain areas that process auditory stimuli in a synchronized way. Then an anomaly detection system based on the reconstruction residuals of an autoencoder using these features has been proposed. Hence, classification is performed by the proposed system based on the differences in the resulting connectivity models that have demonstrated to be a useful tool for differential diagnosis of DD as well as a method to step towards gaining a better knowledge of the brain processes involved in DD. The results corroborate that nonspeech stimulus modulated at specific frequencies related to the sampling processes developed in the brain to capture rhymes, syllables and phonemes produces effects in specific frequency bands that differentiate between controls and DD subjects. The proposed method showed relatively high sensitivity above 0.6, and up to 0.9 in some of the experiments.

The Use of Neuronal Response Signals as Early Biomarkers of Dyslexia

“…The ability to use high temporal (EEG) and spatial (fMRI) resolution during experimental paradigms make these techniques excellent tools for the identification of physiological correlates of reading processes (Carter et al, 2019;Duffy et al, 1980). It has been demonstrated that these tools can be useful in the evaluation of reading impairments (Gallego-Molina et al, 2022;Ortiz et al, 2020). Importantly, these studies have demonstrated that assessment of reading processes using neuro-imaging tools can lower the age of diagnosis for children with dyslexia (Chyl et al, 2021;Ortiz et al, 2020) and identify abnormal neural activation patterns prior to formal literacy instruction (Schiavone et al, 2014;Wilkinson et al, 2020).…”

“…It has been demonstrated that these tools can be useful in the evaluation of reading impairments (Gallego-Molina et al, 2022;Ortiz et al, 2020). Importantly, these studies have demonstrated that assessment of reading processes using neuro-imaging tools can lower the age of diagnosis for children with dyslexia (Chyl et al, 2021;Ortiz et al, 2020) and identify abnormal neural activation patterns prior to formal literacy instruction (Schiavone et al, 2014;Wilkinson et al, 2020). The purported reduction in the age of diagnosis using physiological markers introduces the possibility of a foundational improvement in the effectiveness of reading intervention outcomes.…”

Temporal EigenPAC for dyslexia diagnosis

“…The EEG data used in this work was provided by the Leeduca Study Group at the University of Málaga [6]. EEG signals were recorded using the Brainvision acticHamp Plus with 32 active electrodes (actiCAP, Brain Products GmbH, Germany) at a sampling rate of 500 Hz during 15 minutes sessions, while presenting an auditory stimulus to the subject.…”

Modelling Brain Connectivity Networks by Graph Embedding for Dyslexia Diagnosis

“…EEG data used in this work was provided by the Leeduca Reserch Group at the University of Málaga [10]. EEG signals were recorded using the Brainvision acticHamp Plus with 32 active electrodes (actiCAP, Brain Products GmbH, Germany) at a sampling rate of 500 Hz during 15 minute sessions, while presenting an auditory stimulus to the subject.…”