Cargando…

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

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....

Descripción completa

Detalles Bibliográficos
Autores principales: Gibbon, Samuel, Attaheri, Adam, Ní Choisdealbha, Áine, Rocha, Sinead, Brusini, Perrine, Mead, Natasha, Boutris, Panagiotis, Olawole-Scott, Helen, Ahmed, Henna, Flanagan, Sheila, Mandke, Kanad, Keshavarzi, Mahmoud, Goswami, Usha
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8358977/
https://www.ncbi.nlm.nih.gov/pubmed/34111684
http://dx.doi.org/10.1016/j.bandl.2021.104968
_version_ 1783737450748706816
author Gibbon, Samuel
Attaheri, Adam
Ní Choisdealbha, Áine
Rocha, Sinead
Brusini, Perrine
Mead, Natasha
Boutris, Panagiotis
Olawole-Scott, Helen
Ahmed, Henna
Flanagan, Sheila
Mandke, Kanad
Keshavarzi, Mahmoud
Goswami, Usha
author_facet Gibbon, Samuel
Attaheri, Adam
Ní Choisdealbha, Áine
Rocha, Sinead
Brusini, Perrine
Mead, Natasha
Boutris, Panagiotis
Olawole-Scott, Helen
Ahmed, Henna
Flanagan, Sheila
Mandke, Kanad
Keshavarzi, Mahmoud
Goswami, Usha
author_sort Gibbon, Samuel
collection PubMed
description 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.
format Online
Article
Text
id pubmed-8358977
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-83589772021-09-01 Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG Gibbon, Samuel Attaheri, Adam Ní Choisdealbha, Áine Rocha, Sinead Brusini, Perrine Mead, Natasha Boutris, Panagiotis Olawole-Scott, Helen Ahmed, Henna Flanagan, Sheila Mandke, Kanad Keshavarzi, Mahmoud Goswami, Usha Brain Lang Article 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. Elsevier 2021-09 /pmc/articles/PMC8358977/ /pubmed/34111684 http://dx.doi.org/10.1016/j.bandl.2021.104968 Text en © 2021 The Authors https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Gibbon, Samuel
Attaheri, Adam
Ní Choisdealbha, Áine
Rocha, Sinead
Brusini, Perrine
Mead, Natasha
Boutris, Panagiotis
Olawole-Scott, Helen
Ahmed, Henna
Flanagan, Sheila
Mandke, Kanad
Keshavarzi, Mahmoud
Goswami, Usha
Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG
title Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG
title_full Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG
title_fullStr Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG
title_full_unstemmed Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG
title_short Machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant EEG
title_sort machine learning accurately classifies neural responses to rhythmic speech vs. non-speech from 8-week-old infant eeg
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8358977/
https://www.ncbi.nlm.nih.gov/pubmed/34111684
http://dx.doi.org/10.1016/j.bandl.2021.104968
work_keys_str_mv AT gibbonsamuel machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT attaheriadam machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT nichoisdealbhaaine machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT rochasinead machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT brusiniperrine machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT meadnatasha machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT boutrispanagiotis machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT olawolescotthelen machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT ahmedhenna machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT flanagansheila machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT mandkekanad machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT keshavarzimahmoud machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg
AT goswamiusha machinelearningaccuratelyclassifiesneuralresponsestorhythmicspeechvsnonspeechfrom8weekoldinfanteeg