Probabilistic and explainable modeling of Phase-Phase Cross-Frequency Coupling patterns in EEG. Application to dyslexia diagnosis

• Autorzy: Castillo-Barnes Diego , Gallego-Molina Nicolás J. , Formoso Marco A. , Ortiz Andrés , Figueiredo Patrícia , Luque Juan L.

Identyfikatory

DOI

10.1016/j.bbe.2024.09.003

• Języki publikacji: EN

Abstrakty

EN

This work explores the intricate neural dynamics associated with dyslexia through the lens of Cross-Frequency Coupling (CFC) analysis applied to electroencephalography (EEG) signals evaluated from 48 seven-year-old Spanish readers from the LEEDUCA research platform. The analysis focuses on CFS (Cross-Frequency phase Synchronization) maps, capturing the interaction between different frequency bands during low-level auditory processing stimuli. Then, making use of Gaussian Mixture Models (GMMs), CFS activations are quantified and classified, offering a compressed representation of EEG activation maps. The study unveils promising results specially at the Theta-Gamma coupling (Area Under the Curve = 0.821), demonstrating the method’s sensitivity to dyslexia-related neural patterns and highlighting potential applications in the early identification of dyslexic individuals.

Słowa kluczowe

EN

mixture model; cross frequency coupling; EEG; signal processing; explainable machine learning; dyslexia diagnosis

PL

model mieszany; EEG; przetwarzanie sygnału; uczenie maszynowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2024
• Tom: Vol. 44, no. 4
• Strony: 814--823
• Opis fizyczny: Bibliogr. 58 poz., rys., tab., wykr.

Twórcy

autor

Castillo-Barnes Diego

• Department of Communications Engineering, University of Malaga, Blvd. Louis Pasteur 35, Malaga, 29010, Malaga, Spain
• Institute for Systems and Robotics (Lisboa/LARSyS) and Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, Lisbon, 1049-001, Lisbon, Portugal

autor

Gallego-Molina Nicolás J.

• Department of Communications Engineering, University of Malaga, Blvd. Louis Pasteur 35, Malaga, 29010, Malaga, Spain

autor

Formoso Marco A.

• Department of Communications Engineering, University of Malaga, Blvd. Louis Pasteur 35, Malaga, 29010, Malaga, Spain

autor

Ortiz Andrés

• Department of Communications Engineering, University of Malaga, Blvd. Louis Pasteur 35, Malaga, 29010, Malaga, Spain

autor

Figueiredo Patrícia

• Institute for Systems and Robotics (Lisboa/LARSyS) and Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, Lisbon, 1049-001, Lisbon, Portugal

autor

Luque Juan L.

• Department of Developmental and Educational Psychology, University of Malaga, Dr. Ortiz Ramos 12, Malaga, 29010, Malaga, Spain

Bibliografia

• [1] Reid G. The SAGE handbook of dyslexia. SAGE Publications; 2008.
• [2] Hulme C, Snowling M. Reading disorders and dyslexia. Curr Opin Pediatrics2016;28:731-5.
• [3] McArthur G, Kohnen S, Larsen L, Jones K, et al. Getting to grips with theheterogeneity of developmental dyslexia. Cogn Neuropsychol 2013;30:1-24.
• [4] Pacheco A, Reis A, Araújo S, Inácio F, et al. Dyslexia heterogeneity: cognitive profiling of portuguese children with dyslexia. Read Writ 2014;27:1529-45.
• [5] Zoubrinetzky R, Bielle F, Valdois S. New insights on developmental dyslexia subtypes: Heterogeneity of mixed reading profiles. PLoS One 2014;9:e99337.
• [6] Giraud A, Poeppel D. Cortical oscillations and speech processing: emerging computational principles and operations. Nat Neurosci 2012;15:511-7.
• [7] Soltész F, Szűcs D, Leong V, White S, Goswami U. Differential entrainment of Neuroelectric Delta oscillations in developmental dyslexia. PLoS One2013;8:e76608.
• [8] Gross J, Hoogenboom N, Thut G, Schyns P, et al. Speech rhythms and multiplexed oscillatory sensory coding in the human brain. PLoS Biol2013;11:e1001752.
• [9] Keitel A, Gross J, Kayser C. Perceptually relevant speech tracking in auditory and motor cortex reflects distinct linguistic features. PLoS Biol 2018;16:e2004473.
• [10] Keshavarzi M, Mandke K, Macfarlane A, Parvez L, et al. Atypical beta-band effects in children with dyslexia in response to rhythmic audio-visual speech.Clin Neurophysiol 2024;160:47-55.
• [11] Gallego-Molina N, Formoso M, Ortiz A, Martínez-Murcia F, Luque J. Temporal EigenPAC for dyslexia diagnosis. In: Advances in computational intelligence.2021, p. 45-56.
• [12] Gallego-Molina N, Ortiz A, Martínez-Murcia F, Rodríguez-Rodríguez I. Unraveling dyslexia-related connectivity patterns in EEG signals by Holo-Hilbert spectral analysis. In: Artificial intelligence in neuroscience: affective analysis and health applications. 2022, p. 43-52.
• [13] Formoso M, Ortiz A, Martinez-Murcia F, Gallego N, Luque J. Detecting phase-synchrony connectivity anomalies in EEG signals. Application to dyslexia diagnosis. Sensors 2021;21:7061.
• [14] Gallego-Molina N, Ortiz A, Martínez-Murcia F, Formoso M, Giménez A. Complex network modeling of EEG band coupling in dyslexia: An exploratory analysis of auditory processing and diagnosis. Knowl-Based Syst 2022;240:108098.
• [15] Attaheri A, Ní Choisdealbha Á, Liberto G, Rocha S, et al. Delta- and theta-band cortical tracking and phase-amplitude coupling to sung speech by infants. NeuroImage 2022;247:118698.
• [16] Nadalin J, Martinet L, Blackwood E, Lo M, et al. A statistical framework to assess cross-frequency coupling while accounting for confounding analysis effects. ELife2019;8.
• [17] Hülsemann M, Naumann E, Rasch B. Quantification of phase-amplitude couplingin neuronal oscillations: Comparison of phase-locking value, mean vector length,modulation index, and generalized-linear-modeling-cross-frequency-coupling. Front Neurosci 2019;13.
• [18] Martínez-Cancino R, Heng J, Delorme A, Kreutz-Delgado K, et al. Measuring transient phase-amplitude coupling using local mutual information. NeuroImage2019;185:361-78.
• [19] Duin RPW. Classifiers in almost empty spaces. In: Proceedings 15th International Conference on Pattern Recognition. ICPR-2000. IEEE Comput. Soc; 2000,http://dx.doi.org/10.1109/icpr.2000.906006, ICPR-00.
• [20] Ortiz A, Martinez-Murcia F, Luque J, Giménez A, et al. Dyslexia diagnosis by EEG temporal and spectral descriptors: An anomaly detection approach. Int JNeural Syst 2020;30:2050029.
• [21] Wang G, Teng C, Li K, Zhang Z, Yan X. The removal of EOG artifacts from EEG signals using independent component analysis and multivariate empirical mode decomposition. IEEE J Biomed Health Inf 2016;20:1301-8.
• [22] Biel A, Minarik T, Sauseng P. EEG cross-frequency phase synchronization as an index of memory matching in visual search. NeuroImage 2021;235:117971.
• [23] Jiang X, Bian G, Tian Z. Removal of artifacts from EEG signals: A review. Sensors2019;19:987.
• [24] Li R, Yang D, Fang F, Hong K, et al. Concurrent fNIRS and EEG for brain function investigation: A systematic, methodology-focused review. Sensors 2022;22:5865.
• [25] Palva J, Palva S, Kaila K. Phase synchrony among neuronal oscillations in thehuman cortex. J Neurosci 2005;25:3962-72.
• [26] Scheffer-Teixeira R, Tort A. On cross-frequency phase-phase coupling between theta and gamma oscillations in the hippocampus. ELife 2016;5.
• [27] Rosenblum M, Pikovsky A, Kurths J. Phase synchronization of chaotic oscillators.Phys Rev Lett 1996;76:1804-7.
• [28] Stam C, Nolte G, Daffertshofer A. Phase lag index: Assessment of functional connectivity from multi channel EEG and MEG with diminished bias from common sources. Hum Brain Map 2007;28:1178-93.
• [29] Belluscio M, Mizuseki K, Schmidt R, Kempter R, Buzsáki G. Cross-frequency phase-phase coupling between theta and Gamma oscillations in the hippocampus. J Neurosci 2012;32:423-35.
• [30] Dvorak D, Fenton A. Toward a proper estimation of phase-amplitude couplingin neural oscillations. J Neurosci Methods 2014;225:42-56.
• [31] Liu C, Chen W, Zhang T. Wavelet-Hilbert transform based bidirectional least squares grey transform and modified binary grey wolf optimization for the identification of epileptic EEGs. Biocybern Biomed Eng 2023;43:442-62.
• [32] Bashivan P, Rish I, Yeasin M, Codella N. Learning representations from EEG with deep recurrent-convolutional neural networks. 2015.
• [33] Alfeld P. A trivariate clough - tocher scheme for tetrahedral data. Comput Aided Geom Design 1984;1:169-81.
• [34] Kimppa L, Shtyrov Y, Partanen E, Kujala T. Impaired neural mechanism for online novel word acquisition in dyslexic children. Sci Rep 2018;8.
• [35] Thiede A, Glerean E, Kujala T, Parkkonen L. Atypical MEG inter-subject cor-relation during listening to continuous natural speech in dyslexia. NeuroImage 2020;216:116799.
• [36] Attaheri A, Choisdealbha A, Rocha S, Brusini P, et al. Infant low-frequency EEG cortical power, cortical tracking and phase-amplitude coupling predicts language a year later. Cold Spring Harbor Laboratory; 2022.
• [37] Majkowski A, Oskwarek Ł, Kołodziej M, Rak R. An attempt to localize brain electrical activity sources using EEG with limited number of electrodes. Biocybern Biomed Eng 2016;36:686-96.
• [38] Pizer S, Amburn E, Austin J, Cromartie R, et al. Adaptive histogram equalization and its variations. Comput Vis Graph Image Process 1987;39:355-68.
• [39] Yang C. Image enhancement by modified contrast-stretching manipulation. OptLaser Technol 2006;38:196-201.
• [40] Chaple G, Daruwala R, Gofane M. Comparisions of Robert, Prewitt, Sobel operator based edge detection methods for real time uses on FPGA. In: 2015 international conference on technologies for sustainable development. 2015.
• [41] Li R, Perneczky R, Yakushev I, Förster S, et al. Gaussian mixture models and model selection for [18F] fluorodeoxyglucose positron emission tomography classification in Alzheimer’s disease. PLoS One 2015;10:e0122731.
• [42] Derntl A, Plant C. Clustering techniques for neuroimaging applications. WIREs Data Min Knowl Discov 2015;6:22-36.
• [43] Churchill N, Madsen K, Mørup M. The functional segregation and integration model: Mixture model representations of consistent and variable group-level connectivity in fMRI. Neural Comput 2016;28:2250-90.
• [44] Schwarz G, et al. Estimating the dimension of a model. Ann Statist 1978;6:461-4.
• [45] Akaike H. A new look at the statistical model identification. IEEE Trans Autom Control 1974;19:716-23.
• [46] Castillo-Barnes D, Martinez-Murcia F, Ramírez J, Górriz J, Salas-Gonzalez D.Expectation-maximization algorithm for finite mixture of𝛼-stable distributions. Neurocomputing 2020;413:210-6.
• [47] Chen T, Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016.
• [48] Faraggi D, Reiser B. Estimation of the area under the ROC curve. Stat Med 2002;21:3093-106.
• [49] Brodersen K, Ong C, Stephan K, Buhmann J. The balanced accuracy andits posterior distribution. In: 2010 20th international conference on pattern recognition. 2010.
• [50] Fujii M, Maesawa S, Ishiai S, Iwami K, et al. Neural basis of language: An overview of an evolving model. Neurol Medico-Chirurgica 2016;56:379-86.
• [51] Górriz J, Illán I, Marquina A, Arco J, et al. Computational approaches to explainable artificial intelligence: Advances in theory, applications and trends. Inform Fus 2023;101945.
• [52] Canolty R, Knight R. The functional role of cross-frequency coupling. Trends in Cognitive Sciences 2010;14:506-15.
• [53] Aru J, Aru J, Priesemann V, Wibral M, et al. Untangling cross-frequency coupling in neuroscience. Curr Opin Neurobiol 2015;31:51-61.
• [54] Gialluisi A, Andlauer T, Mirza-Schreiber N, Moll K, et al. Genome-wide association study reveals new insights into the heritability and genetic correlates of developmental dyslexia. Mol Psychiatry 2020;26:3004-17.
• [55] Goswami U. A temporal sampling framework for developmental dyslexia. Trendsin Cognitive Sciences 2011;15:3-10.
• [56] Giraud A, Ramus F. Neurogenetics and auditory processing in developmental dyslexia. Curr Opin Neurobiol 2013;23:37-42.
• [57] Arns M, Peters S, Breteler R, Verhoeven L. Different brain activation patterns in dyslexic children: Evidence from EEG power and coherence patterns for the double-deficit theory of dyslexia. J Integr Neurosci 2007;6:175-90.
• [58] Di Liberto G, Peter V, Kalashnikova M, Goswami U, et al. Atypical cortical entrainment to speech in the right hemisphere underpins phonemic deficits in dyslexia. NeuroImage 2018;175:70-9.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).