EEG-Based Effective Connectivity Analysis for Attention Deficit Hyperactivity Disorder Detection Using Color-Coded Granger-Causality Images and Custom Convolutional Neural Network
International Clinical Neuroscience Journal,
Vol. 10 No. 1 (2023),
15 January 2023
,
Page e12
Abstract
Background: Attention deficit hyperactivity disorder (ADHD) is prevalent worldwide, affecting approximately 8-12% of children. Early detection and effective treatment of ADHD are crucial for improving academic, social, and emotional outcomes. Despite numerous studies on ADHD detection, existing models still lack accuracy distinguishing between ADHD and healthy control (HC) children.
Methods: This study introduces an innovative methodology that utilizes granger causality (GC), a well-established brain connectivity analysis technique, to reduce the required EEG electrodes. We computed GC indexes (GCI) for the entire brain and specific brain regions, known as regional GCI, across different frequency bands. Subsequently, these GCIs were transformed into color-coded images and fed into a custom-developed 11-layer convolutional neural network.
Results: The proposed model is evaluated through a five-fold cross-validation, achieving the highest accuracy of 99.80% in the gamma frequency band for the entire brain and an accuracy of 98.50% in distinguishing the theta frequency band of the right hemisphere of ADHD and HC children by only using eight electrodes.
Conclusion: The proposed framework provides a powerful automated tool for accurately classifying ADHD and HC children. The study’s outcome demonstrates that the innovative proposed methodology utilizing GCI and a custom-developed convolutional neural network can significantly improve ADHD detection accuracy, improving affected children’s overall quality of life.
- ADHD; Electroencephalography; Effective connectivity; Granger Causality; Convolutional Neural Network.
How to Cite
References
2. Vashishtha S. Attention deficit hyperactivity disorder (ADHD): Introduction, mental health concerns, and treatment. New Developments in Diagnosing, Assessing, and Treating ADHD. 2021;23–42. doi: 10.4018/978-1-7998-5495-1.CH002.
3. Feil EG, Small JW, Seeley JR, Walker HM, Golly A, Frey A, et al. Early intervention for preschoolers at risk for attention-deficit/hyperactivity disorder: Preschool first step to success. Behav Disord. 2016;41(2):95–106. doi: 10.17988/0198-7429-41.2.95.
4. Rohr CS, Bray SL, Dewey DM. Functional connectivity based brain signatures of behavioral regulation in children with ADHD, DCD, and ADHD-DCD. Dev Psychopathol. 2023;35(1). doi: 10.1017/S0954579421001449.
5. Hamedi N, Khadem A, Delrobaei M, Babajani-Feremi A. Detecting ADHD based on brain functional connectivity using resting-state MEG signals. Front biome. technol. 2022;9(2):110–8. doi: 10.18502/FBT.V9I2.8850.
6. Aydın S, Çetin FH, Uytun MÇ, Babadag̃í Z, Güven AS, Işık Y. Comparison of domain specific connectivity metrics for estimation brain network indices in boys with ADHD-C. Biomed Signal Process Control. 2022;76:103626. doi: 10.1016/j.bspc.2022.103626.
7. Hearne L, Lin HY, Sanz-Leon P, Tseng W, Gau S, Roberts JA, et al. ADHD symptoms map onto noise-driven structure-function decoupling between hub and peripheral brain regions. Mol. Psychiatry. 2021;26:4036–45. doi: 10.1038/s41380-019-0554-6.
8. Kiiski H, Rueda-Delgado LM, Bennett M, Knight R, Rai L, Roddy D, et al. Functional EEG connectivity is a neuromarker for adult attention deficit hyperactivity disorder symptoms. Clin Neurophysiol. 2020;131(1):330–42. doi: 10.1016/j.clinph.2019.08.010.
9. Chen C, Yang H, Du Y, Zhai G, Xiong H, Yao D, et al. Altered functional connectivity in children with ADHD revealed by scalp EEG: An ERP study. Neural Plast. 2021;2021. doi: 10.1155/2021/6615384.
10. Ekhlasi A, Nasrabadi AM, Mohammadi MR. Direction of information flow between brain regions in ADHD and healthy children based on EEG by using directed phase transfer entropy. Cogn Neurodyn. 2021;15(6):975–86. doi: 10.1007/S11571-021-09680-3/METRICS.
11. Ekhlasi A, Motie Nasrabadi A, Mohammadi M. Classification of the children with ADHD and healthy children based on the directed phase transfer entropy of EEG signals. Front biome. technol. 2021;8(2). doi: 10.18502/fbt.v8i2.6515.
12. Abbas AK, Azemi G, Amiri S, Ravanshadi S, Omidvarnia A. Effective connectivity in brain networks estimated using EEG signals is altered in children with ADHD. Comput Biol Med. 2021;134:104515. doi: 10.1016/J.COMPBIOMED.2021.104515.
13. Ekhlasi A, Nasrabadi AM, Mohammadi M. Analysis of EEG brain connectivity of children with ADHD using graph theory and directional information transfer. Biomed Tech (Berl). 2022. doi: 10.1515/bmt-2022-0100.
14. Moqadam R, Loghmani N, Moghaddam AK, Allahverdy A. Differentiating brain connectivity networks in ADHD and normal children using EEG. 30th Int Conf Electr Eng (ICEE). 2022;231–5. doi: 10.1109/ICEE55646.2022.9827093.
15. Coelli S, Calcagno A, Iascone E, Gaspari L, Canevini MP, Bianchi AM. Sustained attention task-related changes of functional connectivity in children with ADHD. IEEE MELECON 2022 Conf. 2022;585–9. doi: 10.1109/MELECON53508.2022.9842899.
16. Talebi N, Motie Nasrabadi A. Investigating the discrimination of linear and nonlinear effective connectivity patterns of EEG signals in children with Attention-Deficit/Hyperactivity Disorder and Typically Developing children. Comput Biol Med. 2022;148:105791. doi: 10.1016/J.COMPBIOMED.2022.105791.
17. Moghaddari M, Lighvan MZ, Danishvar S. Diagnose ADHD disorder in children using convolutional neural network based on continuous mental task EEG. Comput Methods Programs Biomed. 2020;197:105738. doi: 10.1016/J.CMPB.2020.105738.
18. Bakhtyari M, Mirzaei S. ADHD detection using dynamic connectivity patterns of EEG data and ConvLSTM with attention framework. Biomed Signal Process Control. 2022;76:103708. doi: 10.1016/J.BSPC.2022.103708.
19. Granger CWJ. Investigating causal relations by econometric models and cross-spectral methods. Econometrica. 1969;37(3):424. doi: 10.2307/1912791.
20. Ali Motie Nasrabadi, Armin Allahverdy, Mehdi Samavati MRM. EEG data for ADHD / Control children | IEEE DataPort. 2020. Available from: https://ieee-dataport.org/open-access/eeg-data-adhd-control-children.
21. Delorme A, Makeig S. EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods. 2004;134(1):9–21. doi: 10.1016/j.jneumeth.2003.10.009.
22. Delorme A. Clean Raw Data plugin. Available from: https://github.com/sccn/clean_rawdata.
23. Pion-Tonachini L, Kreutz-Delgado K, Makeig S. ICLabel: An automated electroencephalographic independent component classifier, dataset, and website. Neuroimage. 2019;198:181–97. doi: 10.1016/j.neuroimage.2019.05.026.
24. Seth AK, Barrett AB, Barnett L. Granger causality analysis in neuroscience and neuroimaging. J Neurosci. 2015;35(8):3293–7. doi: 10.1523/JNEUROSCI.4399-14.2015.
25. Schmidt C, Pester B, Schmid-Hertel N, Witte H, Wismuller A, Leistritz L. A Multivariate Granger causality concept towards full brain functional connectivity. PLoS One. 2016;11(4):e0153105. doi: 10.1371/JOURNAL.PONE.0153105.
26. Wismüller A, Dsouza AM, Vosoughi MA, Abidin A. Large-scale nonlinear Granger causality for inferring directed dependence from short multivariate time-series data. Sci Rep. 2021;11(1). doi: 10.1038/S41598-021-87316-6.
27. Wang S, Zhang D, Fang B, Liu X, Yan G, Sui G, et al. A study on resting EEG effective connectivity difference before and after neurofeedback for children with ADHD. Neuroscience. 2021;457:103–13. doi: 10.1016/J.NEUROSCIENCE.2020.12.038.
- Abstract Viewed: 395 times
- PDF Downloaded: 239 times