Single-trial FRPs: A Machine Learning Approach Towards the Study of the Neural Underpinning of Reading Disorders

Understanding the neural underpinning of reading disorders, such as dyslexia, is a fundamental question in developmental neuroscience. However, identifying and isolating informative components elicited during free-naming paradigms (i.e. unprompted unconstrained naming tasks) has proven challenging methodological task. These barriers have hindered study underpinnings disorders. In this paper, we proposed machine learning approach for detecting free-naming, overcoming much current challenges. We propose new neural-based metric to differentiate groups children with dyslexia (DYS) their chronological age controls (CAC) Our combines electroencephalography (EEG) eye-tracking measures generate single-trial fixation-related potentials (sFRPs) formulate an optimization problem extract naming-related components, group differences. validated on real dataset involving CAC performing Rapid-Automatized Naming (RAN) results demonstrate validity indicator markers Importantly, our framework provides novel that can facilitate correlates disorders under methods are unable to.