Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Contextual Microstates: an approach based on word embedding of microstates sequence to identify ADHD patients

Contextual Microstates: an approach based on word embedding of microstates sequence to identify... PurposeSeveral studies have indicated that electroencephalography (EEG) and microstates analysis are promising in the attention-deficit hyperactivity disorder (ADHD) diagnosis. However, these studies are restricted to analyzing the temporal dynamics of microstates; therefore, the syntax of symbolic microstates sequences in ADHD patients has not been explored. To solve this gap, this paper proposes a new methodology for the detection of ADHD using EEG microstate analysis and natural language processing.MethodThis method enables to capture the contextual information of symbolic microstates sequence using Word2vec and model each microstate as a numerical vector. The characteristics derived from these embedding vectors were used to train a neural artificial network to classify patients with ADHD and subtypes.ResultsThe proposed method was able to classify ADHD patients with mean accuracy of 99.06% and was also able to identify ADHD subtypes with mean accuracy of 95.56%. In addition, the proposed approach was able to identify and visualize the most relevant symbolic microstates context becoming a useful tool in ADHD diagnosis.ConclusionThe results indicate that contextual features of symbolic microstates sequence captured by Word2vec achieve better classification results when compared to classical microstates analysis and theta to beta ratio (TBR) frequency analysis. Then, the proposed method is promising to identify ADHD and subtypes. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Research on Biomedical Engineering Springer Journals

Contextual Microstates: an approach based on word embedding of microstates sequence to identify ADHD patients

Download PDF
13 pages

Loading next page...
 
/lp/springer-journals/contextual-microstates-an-approach-based-on-word-embedding-of-R7diU9GgPk
Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to The Brazilian Society of Biomedical Engineering 2022. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
ISSN
2446-4732
eISSN
2446-4740
DOI
10.1007/s42600-022-00245-9
Publisher site
See Article on Publisher Site

Abstract

PurposeSeveral studies have indicated that electroencephalography (EEG) and microstates analysis are promising in the attention-deficit hyperactivity disorder (ADHD) diagnosis. However, these studies are restricted to analyzing the temporal dynamics of microstates; therefore, the syntax of symbolic microstates sequences in ADHD patients has not been explored. To solve this gap, this paper proposes a new methodology for the detection of ADHD using EEG microstate analysis and natural language processing.MethodThis method enables to capture the contextual information of symbolic microstates sequence using Word2vec and model each microstate as a numerical vector. The characteristics derived from these embedding vectors were used to train a neural artificial network to classify patients with ADHD and subtypes.ResultsThe proposed method was able to classify ADHD patients with mean accuracy of 99.06% and was also able to identify ADHD subtypes with mean accuracy of 95.56%. In addition, the proposed approach was able to identify and visualize the most relevant symbolic microstates context becoming a useful tool in ADHD diagnosis.ConclusionThe results indicate that contextual features of symbolic microstates sequence captured by Word2vec achieve better classification results when compared to classical microstates analysis and theta to beta ratio (TBR) frequency analysis. Then, the proposed method is promising to identify ADHD and subtypes.

Journal

Research on Biomedical Engineering – Springer Journals

Published: Mar 1, 2023

Keywords: ADHD; EEG; Microstates analysis; Word embedding; Machine learning

References

  • Neurocognitive profile of children with attention deficit hyperactivity disorders (ADHD): a comparison between subtypes
    Ahmadi, N; Mohammadi, MR; Araghi, SM; Zarafshan, H
  • ADHD history of the concept: the case of the continuous performance test
    Albrecht, B; Uebel-von Sandersleben, H; Wiedmann, K; Rothenberger, A
  • Part 1: simple definition and calculation of accuracy, sensitivity and specificity
    Baratloo, A; Hosseini, M; Negida, A; El Ashal, G
  • Effects of noise letters upon the identification of a target letter in a nonsearch task
    Eriksen, BA; Eriksen, CW
  • Overlap of ADHD and oppositional defiant disorder DSM-IV derived criteria
    Ghanizadeh, A
  • A systematic literature review on word embedding
    Gutiérrez, L; Keith, B; Mejia, J; Muñoz, M; Rocha, Á; Peña, A; Pérez-Cisneros, M
  • Automated and ERP-based diagnosis of attention-deficit hyperactivity disorder in children
    Jahanshahloo, HR; Shamsi, M; Ghasemi, E; Kouhi, A
  • No evidence of associations between ADHD and event-related brain potentials from a continuous performance task in a population-based sample of adolescent twins
    Lau-Zhu, A; Tye, C; Rijsdijk, F; McLoughlin, G
  • Multimodal analysis of resting state cortical activity: what does fMRI add to our knowledge of microstates in resting state EEG activity?: Commentary to the papers by Britz et al. and Musso et al. in the current issue of NeuroImage
    Lehmann, D
  • EEG alpha map series: brain micro-states by space-oriented adaptive segmentation
    Lehmann, D; Ozaki, H; Pal, I
  • Functional MRI reveals different response inhibition between adults and children with ADHD
    Lei, D; Du, M; Wu, M; Chen, T; Huang, X; Du, X; Bi, F; Kemp, GJ; Gong, Q
  • Rotation-invariant similarity in time series using bag-of-patterns representation
    Lin, J; Khade, R; Li, Y
  • Visualizing data using t-SNE
    Maaten, LvD; Hinton, G
  • On a test of whether one of two random variables is stochastically larger than the other
    Mann, HB; Whitney, DR
  • Biomarkers for ADHD: the present and future directions
    Mehta, T; Mannem, N; Yarasi, NK; Bollu, PC
  • Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG
    Moghaddari, M; Lighvan, MZ; Danishvar, S
  • The development of a quantitative electroencephalographic scanning process for attention deficit–hyperactivity disorder: reliability and validity studies
    Monastra, VJ; Lubar, JF; Linden, M
  • Segmentation of brain electrical activity into microstates: model estimation and validation
    Pascual-Marqui, RD; Michel, CM; Lehmann, D
  • 15 years of microstate research in schizophrenia – where are we?
    Rieger, K; Diaz Hernandez, L; Baenninger, A; Koenig, T
  • A meta-analysis of quantitative EEG power associated with attention-deficit hyperactivity disorder
    Snyder, SM; Hall, JR
  • Prevalence of attention-deficit/hyperactivity disorder: a systematic review and meta-analysis
    Thomas, R; Sanders, S; Doust, J; Beller, E; Glasziou, P
  • Deep learning based on event-related EEG differentiates children with ADHD from healthy controls
    Vahid, A; Bluschke, A; Roessner, V; Stober, S; Beste, C
  • Adaptive segmentation of spontaneous EEG map series into spatially defined microstates
    Wackermann, J; Lehmann, D; Michel, C; Strik, W
  • Bag-of-words representation for biomedical time series classification
    Wang, J; Liu, P; She, MF; Nahavandi, S; Kouzani, A
  • Information-theoretical analysis of resting state EEG microstate sequences - non-Markovianity, non-stationarity and periodicities
    von Wegner, F; Tagliazucchi, E; Laufs, H