Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG Article

Gibbon, S, Attaheri, A, Ní Choisdealbha, Á et al. (2021). Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG . BRAIN AND LANGUAGE, 220 10.1016/j.bandl.2021.104968

cited authors

  • Gibbon, S; Attaheri, A; Ní Choisdealbha, Á; Rocha, S; Brusini, P; Mead, N; Boutris, P; Olawole-Scott, H; Ahmed, H; Flanagan, S; Mandke, K; Keshavarzi, M; Goswami, U

abstract

  • Currently there are no reliable means of identifying infants at-risk for later language disorders. Infant neural responses to rhythmic stimuli may offer a solution, as neural tracking of rhythm is atypical in children with developmental language disorders. However, infant brain recordings are noisy. As a first step to developing accurate neural biomarkers, we investigate whether infant brain responses to rhythmic stimuli can be classified reliably using EEG from 95 eight-week-old infants listening to natural stimuli (repeated syllables or drumbeats). Both Convolutional Neural Network (CNN) and Support Vector Machine (SVM) approaches were employed. Applied to one infant at a time, the CNN discriminated syllables from drumbeats with a mean AUC of 0.87, against two levels of noise. The SVM classified with AUC 0.95 and 0.86 respectively, showing reduced performance as noise increased. Our proof-of-concept modelling opens the way to the development of clinical biomarkers for language disorders related to rhythmic entrainment.

publication date

  • September 1, 2021

published in

Digital Object Identifier (DOI)

volume

  • 220