Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors

Artificial neural networks (ANNs) are showing increasing promise as decision support tools in medicine and particularly in neuroscience and neuroimaging. Recently, there has been increasing work on using neural networks to classify individuals with concussion using electroencephalography (EEG) data....

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Karun Thanjavur, Dionissios T. Hristopulos, Arif Babul, Kwang Moo Yi, Naznin Virji-Babul
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/cebee3837ad3469795943d13bfc65f98
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:cebee3837ad3469795943d13bfc65f98
record_format dspace
spelling oai:doaj.org-article:cebee3837ad3469795943d13bfc65f982021-11-30T18:11:46ZDeep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors1662-516110.3389/fnhum.2021.734501https://doaj.org/article/cebee3837ad3469795943d13bfc65f982021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnhum.2021.734501/fullhttps://doaj.org/toc/1662-5161Artificial neural networks (ANNs) are showing increasing promise as decision support tools in medicine and particularly in neuroscience and neuroimaging. Recently, there has been increasing work on using neural networks to classify individuals with concussion using electroencephalography (EEG) data. However, to date the need for research grade equipment has limited the applications to clinical environments. We recently developed a deep learning long short-term memory (LSTM) based recurrent neural network to classify concussion using raw, resting state data using 64 EEG channels and achieved high accuracy in classifying concussion. Here, we report on our efforts to develop a clinically practical system using a minimal subset of EEG sensors. EEG data from 23 athletes who had suffered a sport-related concussion and 35 non-concussed, control athletes were used for this study. We tested and ranked each of the original 64 channels based on its contribution toward the concussion classification performed by the original LSTM network. The top scoring channels were used to train and test a network with the same architecture as the previously trained network. We found that with only six of the top scoring channels the classifier identified concussions with an accuracy of 94%. These results show that it is possible to classify concussion using raw, resting state data from a small number of EEG sensors, constituting a first step toward developing portable, easy to use EEG systems that can be used in a clinical setting.Karun ThanjavurDionissios T. HristopulosArif BabulKwang Moo YiNaznin Virji-BabulNaznin Virji-BabulFrontiers Media S.A.articleconcussionmild traumatic brain injuryresting state EEGadolescentsmachine learningdeep learningNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Human Neuroscience, Vol 15 (2021)
institution DOAJ
collection DOAJ
language EN
topic concussion
mild traumatic brain injury
resting state EEG
adolescents
machine learning
deep learning
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
spellingShingle concussion
mild traumatic brain injury
resting state EEG
adolescents
machine learning
deep learning
Neurosciences. Biological psychiatry. Neuropsychiatry
RC321-571
Karun Thanjavur
Dionissios T. Hristopulos
Arif Babul
Kwang Moo Yi
Naznin Virji-Babul
Naznin Virji-Babul
Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors
description Artificial neural networks (ANNs) are showing increasing promise as decision support tools in medicine and particularly in neuroscience and neuroimaging. Recently, there has been increasing work on using neural networks to classify individuals with concussion using electroencephalography (EEG) data. However, to date the need for research grade equipment has limited the applications to clinical environments. We recently developed a deep learning long short-term memory (LSTM) based recurrent neural network to classify concussion using raw, resting state data using 64 EEG channels and achieved high accuracy in classifying concussion. Here, we report on our efforts to develop a clinically practical system using a minimal subset of EEG sensors. EEG data from 23 athletes who had suffered a sport-related concussion and 35 non-concussed, control athletes were used for this study. We tested and ranked each of the original 64 channels based on its contribution toward the concussion classification performed by the original LSTM network. The top scoring channels were used to train and test a network with the same architecture as the previously trained network. We found that with only six of the top scoring channels the classifier identified concussions with an accuracy of 94%. These results show that it is possible to classify concussion using raw, resting state data from a small number of EEG sensors, constituting a first step toward developing portable, easy to use EEG systems that can be used in a clinical setting.
format article
author Karun Thanjavur
Dionissios T. Hristopulos
Arif Babul
Kwang Moo Yi
Naznin Virji-Babul
Naznin Virji-Babul
author_facet Karun Thanjavur
Dionissios T. Hristopulos
Arif Babul
Kwang Moo Yi
Naznin Virji-Babul
Naznin Virji-Babul
author_sort Karun Thanjavur
title Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors
title_short Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors
title_full Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors
title_fullStr Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors
title_full_unstemmed Deep Learning Recurrent Neural Network for Concussion Classification in Adolescents Using Raw Electroencephalography Signals: Toward a Minimal Number of Sensors
title_sort deep learning recurrent neural network for concussion classification in adolescents using raw electroencephalography signals: toward a minimal number of sensors
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/cebee3837ad3469795943d13bfc65f98
work_keys_str_mv AT karunthanjavur deeplearningrecurrentneuralnetworkforconcussionclassificationinadolescentsusingrawelectroencephalographysignalstowardaminimalnumberofsensors
AT dionissiosthristopulos deeplearningrecurrentneuralnetworkforconcussionclassificationinadolescentsusingrawelectroencephalographysignalstowardaminimalnumberofsensors
AT arifbabul deeplearningrecurrentneuralnetworkforconcussionclassificationinadolescentsusingrawelectroencephalographysignalstowardaminimalnumberofsensors
AT kwangmooyi deeplearningrecurrentneuralnetworkforconcussionclassificationinadolescentsusingrawelectroencephalographysignalstowardaminimalnumberofsensors
AT nazninvirjibabul deeplearningrecurrentneuralnetworkforconcussionclassificationinadolescentsusingrawelectroencephalographysignalstowardaminimalnumberofsensors
AT nazninvirjibabul deeplearningrecurrentneuralnetworkforconcussionclassificationinadolescentsusingrawelectroencephalographysignalstowardaminimalnumberofsensors
_version_ 1718406409900523520