Schizophrenia detection using Multivariate Empirical Mode Decomposition and entropy measures from multichannel EEG signal

• Autorzy: Krishnan Palani Thanaraj , Joseph Raj Alex Noel , Balasubramanian Parvathavarthini , Chen Yuanzhu

Identyfikatory

DOI

10.1016/j.bbe.2020.05.008

• Języki publikacji: EN

Abstrakty

EN

Multivariate analysis of the EEG signal for the detection of Schizophrenia condition is proposed here. Multivariate Empirical Mode Decomposition (MEMD) is used to decompose the EEG signal into Intrinsic Mode Functions (IMF) signal. The randomness measure of the IMF signal is determined by computing the entropy of the signal. Five entropy measures such as Approximate entropy, Sample entropy, Permutation entropy, Spectral entropy, and Singular Value Decomposition entropy are measured from the IMF signal. These entropy measures showed a significant difference ( p < 0.01) between the healthy controls (HC) and Schizophrenia (SZ) subjects. Many state-of-the-art (SoA) machine learning classifiers are trained on the feature matrix obtained from entropy values of the IMF signal, amongst them Support Vector Machine based on Radial Basis Function (SVM-RBF) provided the highest accuracy and F1-score of 93% for the 95 features. The area under the curve (AUC) value of 0.9831 was obtained using this classifier. These performance metrics suggests that computation of randomness measure such as entropy in the multivariate IMF domain provided better discriminating power in detection of Schizophrenia condition from the multichannel EEG signal.

Słowa kluczowe

EN

EEG signal; multivariate empirical mode decomposition; intrinsic mode function; entropy features; multivariate signal; signal classification; machine learning classifier

PL

sygnał EEG; funkcja trybu wewnętrznego; wybór cech; sygnał wielowymiarowy

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 3
• Strony: 1124--1139
• Opis fizyczny: Bibliogr. 55 poz., rys., tab., wykr.

Twórcy

autor

Krishnan Palani Thanaraj

• Department of Electronics & Instrumentation Engineering, St. Joseph's College of Engineering, Chennai, India

autor

Joseph Raj Alex Noel

• Department of Electronic & Information Engineering, Shantou University, China

autor

Balasubramanian Parvathavarthini

• Department of Computer Science & Engineering, St. Joseph's College of Engineering, Chennai, India

autor

Chen Yuanzhu

• Department of Computer Science, Memorial University of Newfoundland, Canada

Bibliografia

• [1] Chong HY, Teoh SL, Wu DBC, Kotirum S, Chiou CF, Chaiyakunapruk N. Global economic burden of schizophrenia: a systematic review; 2016. http://dx.doi.org/10.2147/NDT.S96649.
• [2] Sabeti M, Katebi S, Boostani R. Entropy and complexity measures for EEG signal classification of schizophrenic and control participants. Artif Intell Med 2009;47(3):263–74. http://dx.doi.org/10.1016/j.artmed.2009.03.003.
• [3] Greenberger C, Serper MR. Examination of clinical and cognitive insight in acute Schizophrenia patients. J Nerv Mental Dis 2010;198(7):465–9. http://dx.doi.org/10.1097/NMD.0b013e3181e4f35d.
• [4] Gejman PV, Sanders AR, Duan J. The role of genetics in the etiology of schizophrenia 2010. http://dx.doi.org/10.1016/j.psc.2009.12.003.
• [5] Damaraju E, Allen EA, Belger A, Ford JM, McEwen S, Mathalon DH, et al. Dynamic functional connectivity analysis reveals transient states of dysconnectivity in schizophrenia. NeuroImage: Clin 2014;5:298–308. http://dx.doi.org/10.1016/j.nicl.2014.07.003.
• [6] Schlögl A, Lee F, Bischof H, Pfurtscheller G. Characterization of four-class motor imagery EEG data for the BCI-competition 2005. J Neural Eng 2005;2(4):L14–22. http://dx.doi.org/10.1088/1741-2560/2/4/L02.
• [7] Liu Y, Zhang H, Zhao Q, Zhang L. Common spatial-spectral boosting pattern for brain-computer interface. Frontiers in artificial intelligence and applications, vol. 263. IOS Press; 2014. p. 537–42. http://dx.doi.org/10.3233/978-1-61499-419-0-537.
• [8] Maziero D, Sturzbecher M, Velasco TR, Rondinoni C, Castellanos AL, Carmichael DW, et al. A comparison of independent component analysis (ICA) of fMRI and electrical source imaging (ESI) in focal epilepsy reveals misclassification using a classifier. Brain Topogr 2015;28(6):813–31. http://dx.doi.org/10.1007/s10548-015-0436-4.
• [9] Sweeney-Reed CM, Nasuto SJ. A novel approach to the detection of synchronisation in EEG based on empirical mode decomposition. J Comput Neurosci 2007;23(1):79–111. http://dx.doi.org/10.1007/s10827-007-0020-3.
• [10] Kim JW, Lee YS, Han DH, Min KJ, Lee J, Lee K. Diagnostic utility of quantitative EEG in un-medicated schizophrenia. Neurosci Lett 2015;589:126–31. http://dx.doi.org/10.1016/j.neulet.2014.12.064.
• [11] Dvey-Aharon Z, Fogelson N, Peled A, Intrator N. Schizophrenia detection and classification by advanced analysis of EEG recordings using a single electrode approach. PLOS ONE 2015;10(4):e0123033. http://dx.doi.org/10.1371/journal.pone.0123033.
• [12] Johannesen JK, Bi J, Jiang R, Kenney JG, Chen C-MA. Machine learning identification of EEG features predicting working memory performance in schizophrenia and healthy adults. Neuropsychiatr Electrophysiol 2 (1). doi:10.1186/s40810-016-0017-0.
• [13] Akar SA, Kara S, Latifoglu F, Bilgiç V. Analysis of the complexity measures in the EEG of schizophrenia patients. Int J Neural Syst 2016;26(02):1650008. http://dx.doi.org/10.1142/S0129065716500088.
• [14] Götz T, Stadler L, Fraunhofer G, Tomé AM, Hausner H, Lang EW. A combined cICA-EEMD analysis of EEG recordings from depressed or schizophrenic patients during olfactory stimulation. J Neural Eng 2017;14(1):016011. http://dx.doi.org/10.1088/1741-2552/14/1/016011.
• [15] Santos-Mayo L, San-Jose-Revuelta LM, Arribas JI. A computer-aided diagnosis system with EEG based on the p3b wave during an auditory odd-ball task in schizophrenia. IEEE Trans Biomed Eng 2017;64(2):395–407. http://dx.doi.org/10.1109/TBME.2016.2558824.
• [16] Thilakvathi B, Shenbaga Devi S, Bhanu K, Malaippan M. EEG signal complexity analysis for schizophrenia during rest and mental activity. Biomed Res 2017;28(1):1–9, http://www.alliedacademies.org/articles/eeg-signal-complexianalysis-for-schizophrenia-during-rest-and-mental-activity.html.
• [17] Olejarczyk E, Jernajczyk W. Graph-based analysis of brain connectivity in schizophrenia. PLOS ONE 2017;12(11): e0188629. http://dx.doi.org/10.1371/journal.pone.0188629.
• [18] Lyu I, Kang H, Woodward ND, Landman BA. Sulcal depth-based cortical shape analysis in normal healthy control and schizophrenia groups. Proceedings of SPIE—The International Society for Optical Engineering, vol. 10574. SPIE-Intl Soc Optical Eng; 2018. p. 1.
• [19] Ibá nez-Molina AJ, Lozano V, Soriano MF, Aznarte JI, Gómez-Ariza CJ, Bajo MT. EEG multiscale complexity in schizophrenia during picture naming. Front Physiol 2018;9 (SEP):1213. http://dx.doi.org/10.3389/fphys.2018.01213.
• [20] Devia C, Mayol-Troncoso R, Parrini J, Orellana G, Ruiz A, Maldonado PE, et al. EEG classification during scene free-viewing for schizophrenia detection. IEEE Trans Neural Syst Rehabil Eng 2019;27(6):1193–9. http://dx.doi.org/10.1109/TNSRE.2019.2913799.
• [21] Xiang J, Tian C, Niu Y, Yan T, Li D, Cao R, et al. Abnormal entropy modulation of the EEG signal in patients with schizophrenia during the auditory paired-stimulus paradigm. Front Neuroinform 2019;13:4. http://dx.doi.org/10.3389/fninf.2019.00004.
• [22] Phang C-R, Ting C-M, Noman F, Ombao H. Classification of EEG-based brain connectivity networks in schizophrenia using a multi-domain connectome convolutional neural network. arXiv:1903.08858.
• [23] Oh SL, Vicnesh J, Ciaccio EJ, Yuvaraj R, Acharya UR. Deep convolutional neural network model for automated diagnosis of schizophrenia using EEG signals. Appl Sci 2019;9(14):2870. http://dx.doi.org/10.3390/app9142870.
• [24] Kutepov IE, Dobriyan VV, Zhigalov MV, Stepanov MF, Krysko AV, Yakovleva TV, et al. EEG analysis in patients with schizophrenia based on Lyapunov exponents. Inform Med Unlocked 2020;18:100289. http://dx.doi.org/10.1016/j.imu.2020.100289.
• [25] Harmah DJ, Li C, Li F, Liao Y, Wang J, Ayedh WMA, et al. Measuring the non-linear directed information flow in schizophrenia by multivariate transfer entropy. Front Comput Neurosci 2020;13:85. http://dx.doi.org/10.3389/fncom.2019.00085.
• [26] Olejarczyk E, Jernajczyk W. EEG in schizophrenia; 2017. http://dx.doi.org/10.18150/repod.0107441.
• [27] Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond Ser A: Math Phys Eng Sci 1998;454 (1971):903–95. http://dx.doi.org/10.1098/rspa.1998.0193.
• [28] Fleureau J, Kachenoura A, Albera L, Nunes J-C, Senhadji L. Multivariate empirical mode decomposition and application to multichannel filtering. Signal Process 2011;91 (12):2783–92. http://dx.doi.org/10.1016/j.sigpro.2011.01.018.
• [29] Bajaj V, Pachori RB. Classification of seizure and nonseizure EEG signals using empirical mode decomposition. IEEE Trans Inf Technol Biomed 2012;16(6):1135–42. http://dx.doi.org/10.1109/TITB.2011.2181403.
• [30] Acharya UR, Molinari F, Sree SV, Chattopadhyay S, Ng K-H, Suri JS. Automated diagnosis of epileptic EEG using entropies. Biomed Signal Process Control 2012;7(4):401–8. http://dx.doi.org/10.1016/j.bspc.2011.07.007.
• [31] Sharma R, Pachori R, Acharya U. Application of entropy measures on intrinsic mode functions for the automated identification of focal electroencephalogram signals. Entropy 2015;17(2):669–91. http://dx.doi.org/10.3390/e17020669.
• [32] Rilling G, Flandrin P, Goncalves P, Lilly JM. Bivariate empirical mode decomposition. IEEE Signal Process Lett 2007;14(12):936–9. http://dx.doi.org/10.1109/LSP.2007.904710.
• [33] ur Rehman N, Mandic D. Empirical mode decomposition for trivariate signals. IEEE Trans Signal Process 2010;58 (3):1059–68. http://dx.doi.org/10.1109/TSP.2009.2033730.
• [34] Sweeney-Reed CM, Nasuto SJ, Vieira MF, Andrade AO. Empirical mode decomposition and its extensions applied to EEG analysis: a review. Adv Data Sci Adapt Anal 2018;10 (02):1840001. http://dx.doi.org/10.1142/S2424922X18400016.
• [35] Rehman N, Mandic DP. Multivariate empirical mode decomposition. Proc R Soc A: Math Phys Eng Sci 2010;466 (2117):1291–302. http://dx.doi.org/10.1098/rspa.2009.0502.
• [36] Mandic DP, ur Rehman N, Wu Z, Huang NE. Empirical mode decomposition-based time-frequency analysis of multivariate signals: the power of adaptive data analysis. IEEE Signal Process Mag 2013;30(6):74–86. http://dx.doi.org/10.1109/MSP.2013.2267931.
• [37] Park C, Looney D, ur Rehman N, Ahrabian A, Mandic DP. Classification of motor imagery BCI using multivariate empirical mode decomposition. IEEE Trans Neural Syst Rehabil Eng 2013;21(1):10–22. http://dx.doi.org/10.1109/TNSRE.2012.2229296.
• [38] Zahra A, Kanwal N, ur Rehman N, Ehsan S, McDonald-Maier KD. Seizure detection from EEG signals using multivariate empirical mode decomposition. Comput Biol Med 2017;88:132–41. http://dx.doi.org/10.1016/j.compbiomed.2017.07.010.
• [39] Kannathal N, Choo ML, Acharya UR, Sadasivan P. Entropies for detection of epilepsy in EEG. Comput Methods Progr Biomed 2005;80(3):187–94. http://dx.doi.org/10.1016/j.cmpb.2005.06.012.
• [40] Abásolo D, Hornero R, Espino P, Álvarez D, Poza J. Entropy analysis of the EEG background activity in Alzheimer's disease patients. Physiol Meas 2006;27(3):241–53. http://dx.doi.org/10.1088/0967-3334/27/3/003.
• [41] Liang Z, Wang Y, Sun X, Li D, Voss LJ, Sleigh JW, Hagihira S, Li X. EEG entropy measures in anesthesia. Front Comput Neurosci 9. doi:10.3389/fncom.2015.00016.
• [42] Krysko VA, Papkova IV, Saltykova OA, Yakovleva TV, Pavlov SP, Zhigalov MV, et al. Visualization of amplitude- frequency characteristics of EEG of pathological and cognitive functions of the brain from a position of nonlinear dynamics. J Phys: Conf Ser 2019;1260:072010. http://dx.doi.org/10.1088/1742-6596/1260/7/072010.
• [43] Yakovleva TV, Kutepov IE, Karas AY, Yakovlev NM, Dobriyan VV, Papkova IV, et al. EEG analysis in structural focal epilepsy using the methods of nonlinear dynamics (Lyapunov exponents, Lempel-Ziv complexity, and multiscale entropy). Sci World J 2020. http://dx.doi.org/10.1155/2020/8407872.
• [44] Patidar S, Panigrahi T. Detection of epileptic seizure using Kraskov entropy applied on tunable-Q wavelet transform of EEG signals. Biomed Signal Process Control 2017;34:74–80. http://dx.doi.org/10.1016/j.bspc.2017.01.001.
• [45] Tian P, Hu J, Qi J, Ye X, Che D, Ding Y, et al. A hierarchical classification method for automatic sleep scoring using multiscale entropy features and proportion information of sleep architecture. Biocybern Biomed Eng 2017;37(2):263–71. http://dx.doi.org/10.1016/j.bbe.2017.01.005.
• [46] Raghu S, Sriraam N, Kumar GP, Hegde AS. A novel approach for real-time recognition of epileptic seizures using minimum variance modified fuzzy entropy. IEEE Trans Biomed Eng 2018;65(11):2612–21. http://dx.doi.org/10.1109/TBME.2018.2810942.
• [47] Li P, Karmakar C, Yearwood J, Venkatesh S, Palaniswami M, Liu C. Detection of epileptic seizure based on entropy analysis of short-term EEG. PLOS ONE 2018;13(3):e0193691. http://dx.doi.org/10.1371/journal.pone.0193691.
• [48] Zhang T, Chen W, Li M. Fuzzy distribution entropy and its application in automated seizure detection technique. Biomed Signal Process Control 2018;39:360–77. http://dx.doi.org/10.1016/j.bspc.2017.08.013.
• [49] Pincus SM. Approximate entropy as a measure of system complexity. Proc Natl Acad Sci 1991;88(6):2297–301. http://dx.doi.org/10.1073/pnas.88.6.2297.
• [50] Richman JS, Lake DE, Moorman J. Sample entropy. Methods in enzymology, vol. 384. Elsevier; 2004. p. 172–84. http://dx.doi.org/10.1016/S0076-6879(04)84011-4.
• [51] Delgado-Bonal A, Marshak A. Approximate entropy and sample entropy: a comprehensive tutorial. Entropy 2019;21 (6):541. http://dx.doi.org/10.3390/e21060541.
• [52] Yang Y, Zhou M, Niu Y, Li C, Cao R, Wang B, Yan P, Ma Y, Xiang J. Epileptic seizure prediction based on permutation entropy. Front Comput Neurosci 12. doi:10.3389/fncom.2018.00055.
• [53] Anagnoste S, Caraiani P. The impact of financial and macroeconomic shocks on the entropy of financial markets. Entropy 2019;21(3):316. http://dx.doi.org/10.3390/e21030316.
• [54] Parvez MZ, Paul M. Seizure prediction using undulated global and local features. IEEE Trans Biomed Eng 2017;64(1):208–17. http://dx.doi.org/10.1109/TBME.2016.2553131.
• [55] Mursalin M, Zhang Y, Chen Y, Chawla NV. Automated epileptic seizure detection using improved correlation- based feature selection with random forest classifier. Neurocomputing 2017;241:204–14. http://dx.doi.org/10.1016/j.neucom.2017.02.053.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).