Paper ID:250655S1

Authos: Günet Eroğlu

Title: Early EEG Biomarkers of Dyslexia: An AI-Driven Discovery from First-Session Recordings

​Publisher: Algorithm_Lab.

Conference: ICAITD 2025: The Second International Conference of AI new Technology and open Discussion

Location: Pleasanter Lounge  Nakano, Tokyo Japan

Date: 1-4 june 2025

Editor: Kazuo Ohzeki (Algorithm_Lab.  Professor Emeritus of Shibaura Institute of Technology, Professor of Emeritus of International Professional University of Technology in Tokyo)

Citation: Proceedings: ICAITD  2025  

https://doi.org/10.63211/j.p.25.645311 

​pages:  45-50

​

Abstract:

Using artificial intelligence (AI) and quantitative EEG (qEEG) data, this paper analyses early electrophysiological signs of dyslexia. Drawing from first-session EEG recordings of 208 youngsters labelled as either dyslexic or neurotypical, we found statistically significant variations in particular brainwave characteristics. Analysis aided by machine learning found strong distinction (p < 0.001) for characteristics including beta1 power at O1 (B1_O1), alpha power at O1 (A_O1), and gamma power at P7 (G_P7). These results imply that early screening of dyslexia may be diagnosed even with a single session of EEG and could help future individualised neurofeedback treatments.

​

Keywords: Dyslexia, EEG, quantitative EEG, Artificial Neural Network, machine learning,
biomarkers, single-session screening

Category: Short paper

Review process: Two reviewers

Publication date: July 2nd 2025

First received date: April 14th 2025
Copyright :Author(Full), AlgorithmLab.(First-in-the-world publishing rights granted by the author as the Prceedings of ICAITD 2025)
Licence:Viewer can download and view this review paper, but cannot secondary distribute (redistribute) it. (It is not Creative Commons License, nor MIT Licence) In other words, "Do not distribute" is the License

[] reads