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

被引:4
作者
Thanjavur, Karun [1 ]
Hristopulos, Dionissios T. [2 ]
Babul, Arif [1 ]
Yi, Kwang Moo [3 ]
Virji-Babul, Naznin [4 ,5 ]
机构
[1] Univ Victoria, Dept Phys & Astron, Victoria, BC, Canada
[2] Tech Univ Crete, Sch Elect & Comp Engn, Khania, Greece
[3] Univ British Columbia, Dept Comp Sci, Vancouver, BC, Canada
[4] Univ British Columbia, Djavad Mowafaghian Ctr Brain Hlth, Vancouver, BC, Canada
[5] Univ British Columbia, Fac Med, Dept Phys Therapy, Vancouver, BC, Canada
来源
FRONTIERS IN HUMAN NEUROSCIENCE | 2021年 / 15卷
关键词
concussion; mild traumatic brain injury; resting state EEG; adolescents; machine learning; deep learning; LSTM; concussion classification; SPORTS-RELATED CONCUSSION; TRAUMATIC BRAIN-INJURY; FEATURE-SELECTION; CONNECTIVITY;
D O I
10.3389/fnhum.2021.734501
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
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.
引用
收藏
页数:17
相关论文
共 39 条
  • [1] Immediate Removal From Activity After Sport-Related Concussion Is Associated With Shorter Clinical Recovery and Less Severe Symptoms in Collegiate Student-Athletes
    Asken, Breton M.
    Bauer, Russell M.
    Guskiewicz, Kevin M.
    McCrea, Michael A.
    Schmidt, Julianne D.
    Giza, Christopher C.
    Snyder, Aliyah R.
    Houck, Zachary M.
    Kontos, Anthony P.
    McAllister, Thomas W.
    Broglio, Steven P.
    Clugston, James R.
    [J]. AMERICAN JOURNAL OF SPORTS MEDICINE, 2018, 46 (06) : 1465 - 1474
  • [2] Alterations in Resting-State Brain Networks in Concussed Adolescent Athletes
    Borich, Michael
    Babul, Aliya-Nur
    Yuan, Po Hsiang
    Boyd, Lara
    Virji-Babul, Naznin
    [J]. JOURNAL OF NEUROTRAUMA, 2015, 32 (04) : 265 - 271
  • [3] Combining Whole-Brain Voxel-Wise Analysis with In Vivo Tractography of Diffusion Behavior after Sports-Related Concussion in Adolescents: A Preliminary Report
    Borich, Michael
    Makan, Nadia
    Boyd, Lara
    Virji-Babul, Naznin
    [J]. JOURNAL OF NEUROTRAUMA, 2013, 30 (14) : 1243 - 1249
  • [4] Neurophysiological Correlates of Concussion: Deep Learning for Clinical Assessment
    Boshra, Rober
    Ruiter, Kyle I.
    DeMatteo, Carol
    Reilly, James P.
    Connolly, John F.
    [J]. SCIENTIFIC REPORTS, 2019, 9 (1)
  • [5] Mapping the functional connectome in traumatic brain injury: What can graph metrics tell us?
    Caeyenberghs, Karen
    Verhelst, Helena
    Clemente, Adam
    Wilson, Peter H.
    [J]. NEUROIMAGE, 2017, 160 : 113 - 123
  • [6] Alteration of Cortical Functional Connectivity as a Result of Traumatic Brain Injury Revealed by Graph Theory, ICA, and sLORETA Analyses of EEG Signals
    Cao, C.
    Slobounov, S.
    [J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2010, 18 (01) : 11 - 19
  • [7] Application of a novel measure of EEG non-stationarity as 'Shannon-entropy of the peak frequency shifting' for detecting residual abnormalities in concussed individuals
    Cao, Cheng
    Slobounov, Semyon
    [J]. CLINICAL NEUROPHYSIOLOGY, 2011, 122 (07) : 1314 - 1321
  • [8] Reliability and Validity of the Sport Concussion Assessment Tool-3 (SCAT3) in High School and Collegiate Athletes
    Chin, Esther Y.
    Nelson, Lindsay D.
    Barr, William B.
    McCrory, Paul
    McCrea, Michael A.
    [J]. AMERICAN JOURNAL OF SPORTS MEDICINE, 2016, 44 (09) : 2276 - 2285
  • [9] Cerebrovascular Reactivity After Sport Concussion: From Acute Injury to 1 Year After Medical Clearance
    Churchill, Nathan W.
    Hutchison, Michael G.
    Graham, Simon J.
    Schweizer, Tom A.
    [J]. FRONTIERS IN NEUROLOGY, 2020, 11
  • [10] Mapping brain recovery after concussion From acute injury to 1 year after medical clearance
    Churchill, Nathan W.
    Hutchison, Michael G.
    Graham, Simon J.
    Schweizer, Tom A.
    [J]. NEUROLOGY, 2019, 93 (21) : E1980 - E1992