Detection of Schizophrenia from EEG Signals by Permutation Entropy-Based Complexity Analysis

Year 2022, , 2085 - 2096, 01.12.2022

Hasan Polat

https://doi.org/10.21597/jist.1122315

Abstract

Early diagnosis of schizophrenia (SZ) can improve the quality of life by allowing patients to receive more effective treatment. The complexity and heterogeneity of symptoms related to the disease hinder early clinical diagnosis. In this context, electroencephalogram (EEG) is used as an alternative diagnostic tool for the probable SZ. Due to the high temporal resolution of the EEG technique, the reflections of cognitive and behavioral processes on cortical activities can be successfully investigated. In this study, it is aimed to classify and evaluate SZ anomalies by permutation entropy (PE) based complexity analysis of EEG signals. PE analyzes were performed on EEG recordings from 45 adolescents with symptoms of SZ and 39 healthy participants. For feature extraction, PE values are computed for all sub-bands in the EEG as delta, theta, alpha, beta, and gamma waves. A multilayer perceptron neural network (MLPNN) is used as a classifier model. The classification process was performed separately for each scalp electrode. Thus, comprehensive statistical analyzes of the PE distributions related to the efficient channels were performed. The results demonstrate that SZ can be detected efficiently from the P4 and T6 electrode locations. The classification accuracy of 87.2% and 86.8% is obtained for P4 and T6 channels, respectively. Moreover, statistical results of PE distributions showed that complex neurobehavioral features significantly decrease in the case of SZ patients for gamma activities.

Keywords

Schizophrenia, EEG, permutation entropy, complexity, classification, Şizofreni, permütasyon entropi, karmaşıklık, sınıflandırma

Permütasyon Entropi Tabanlı Karmaşıklık Analizi ile EEG İşaretlerinden Şizofreni Tespiti

Abstract

Şizofreninin (SZ) erken tanısı hastaların daha etkili tedavi görmelerine olanak sağlayarak, yaşam kalitelerini artırır. Ancak, hastalığın karmaşık ve heterojen bulguları erken klinik tanıları sekteye uğratmaktadır. Bu bağlamda elektroansefalogram (EEG), olası SZ için alternatif bir tanı aracı olarak kullanılmaktadır. EEG tekniğinin yüksek temporal çözünürlük sunmasından dolayı, bilişsel ve davranışsal süreçlerin kortikal aktivitelere yansımaları başarılı bir şekilde irdelenebilir. Bu çalışmada, EEG işaretlerinin permütasyon entropi (PE) tabanlı karmaşıklık analizi ile SZ anomalilerin sınıflandırılması ve değerlendirilmesi amaçlanmıştır. PE analizleri, SZ semptomları sergileyen 45 adölesan birey ile 39 sağlıklı katılımcıdan alınan EEG kayıtları üzerinde uygulanmıştır. Özellik çıkarımı için delta, teta, alfa, beta ve gama dalgaları olmak üzere tüm alt bantların PE değerleri hesaplanmıştır. Sınıflandırıcı model olarak ise çok katmanlı perseptron sinir ağları (MLPNN) kullanılmıştır. Sınıflandırma işlemi her bir elektrot için ayrı bir şekilde yürütülmüştür. Böylelikle, SZ tespitinde etkin kanallar belirlenmiş ve bu kanallara ilişkin kapsamlı istatistiksel analizler uygulanmıştır. Bulgular, SZ tespitinin P4 ve T6 elektrot konumlarından etkin bir şekilde yapılabileceğini göstermiştir. Sınıflandırma doğrulukları P4 ve T6 kanalları için sırasıyla %87.2 ve %86.8 olarak elde edilmiştir. Ayrıca, PE dağılımlarının istatistiksel sonuçları, gama aktiviteleri için SZ hastalarında karmaşık nörodavranışsal özelliklerin önemli ölçüde azaldığını göstermiştir.

Keywords

Şizofreni, permütasyon entropi, karmaşıklık, sınıflandırma

References

• Bandt C, Pompe B, 2002. Permutation Entropy: A Natural Complexity Measure for Time Series. Physical Review Letters, 88(17), 4. https://doi.org/10.1103/PhysRevLett.88.174102
• Barros C, Silva CA, Pinheiro AP, 2021. Advanced EEG-based learning approaches to predict schizophrenia: Promises and pitfalls. Artificial Intelligence in Medicine, 114(December 2020), 102039. https://doi.org/10.1016/j.artmed.2021.102039
• Biagetti G, Crippa P, Falaschetti L, LuzziS, Turchetti C, 2021. Classification of Alzheimer’s disease from EEG signal using robust-PCA feature extraction. Procedia Computer Science, 192(2019), 3114–3122. https://doi.org/10.1016/j.procs.2021.09.084
• Boostani R, Sabeti M, 2018. Optimising brain map for the diagnosis of Schizophrenia. International Journal of Biomedical Engineering and Technology, 28(2), 105–119. https://doi.org/10.1504/IJBET.2018.094728
• Boostani R, Sadatnezhad K, Sabeti M, 2009. An efficient classifier to diagnose of schizophrenia based on the EEG signals. Expert Systems with Applications, 36(3 PART 2), 6492–6499. https://doi.org/10.1016/j.eswa.2008.07.037
• Buettner R, Hirschmiller M, Schlosser K, Rossle M, Fernandes M, Timm IJ, 2019. High-performance exclusion of schizophrenia using a novel machine learning method on EEG data. 2019 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2019, 39–44. https://doi.org/10.1109/HealthCom46333.2019.9009437
• Cao Y, Tung W, wen, Gao JB, Protopopescu VA, Hively LM, 2004. Detecting dynamical changes in time series using the permutation entropy. Physical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics, 70(4), 7. https://doi.org/10.1103/PhysRevE.70.046217
• Das K, Pachori RB, 2021. Schizophrenia detection technique using multivariate iterative filtering and multichannel EEG signals. Biomedical Signal Processing and Control, 67(January), 102525. https://doi.org/10.1016/j.bspc.2021.102525
• Dvey-Aharon Z, Fogelson N, Peled A, Intrator N, 2015. Schizophrenia detection and classification by advanced analysis of EEG recordings using a single electrode approach. PLoS ONE, 10(4), 1–12. https://doi.org/10.1371/journal.pone.0123033
• Faust O, Acharya UR, Adeli H, Adeli A, 2015. Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis. Seizure, 26, 56–64. https://doi.org/10.1016/j.seizure.2015.01.012
• Goshvarpour A, Goshvarpour A, 2020. Schizophrenia diagnosis using innovative EEG feature-level fusion schemes. Australasian Physical and Engineering Sciences in Medicine, 43(1), 227–238. https://doi.org/10.1007/s13246-019-00839-1
• Haykin SS, 2009. Neural networks and learning machines, 3rd Edition. https://doi.org/10987654321
• Kang J, Chen H, Li X, Li X, 2019. EEG entropy analysis in autistic children. Journal of Clinical Neuroscience, 62, 199–206. https://doi.org/10.1016/j.jocn.2018.11.027
• Kim JW, Lee YS, Han DH, Min KJ, Lee J, Lee K, 2015. Diagnostic utility of quantitative EEG in un-medicated schizophrenia. Neuroscience Letters, 589, 126–131. https://doi.org/10.1016/j.neulet.2014.12.064
• Larson MK, Walker EF, Compton MT, 2010. Early signs, diagnosis and therapeutics of the prodromal phase of schizophrenia and related psychotic disorders. Expert Review of Neurotherapeutics, 10(8), 1347–1359. https://doi.org/10.1586/ern.10.93
• Lee S, Hussein R, Ward R, Jane Wang Z, McKeown MJ, 2021. A convolutional-recurrent neural network approach to resting-state EEG classification in Parkinson’s disease. Journal of Neuroscience Methods, 361(June), 109282. https://doi.org/10.1016/j.jneumeth.2021.109282
• Liu H, Zhang T, Ye Y, Pan C, Yang G, Wang J, Qiu RC, 2017. A Data Driven Approach for Resting-state EEG signal Classification of Schizophrenia with Control Participants using Random Matrix Theory. 1–9. http://arxiv.org/abs/1712.05289
• Naira CAT, Del Alamo CJL, 2019. Classification of people who suffer schizophrenia and healthy people by EEG signals using deep learning. International Journal of Advanced Computer Science and Applications, 10(10), 511–516. https://doi.org/10.14569/ijacsa.2019.0101067
• Oh SL, Vicnesh J, Ciaccio EJ, Yuvaraj R, Acharya UR, 2019. Deep convolutional neural network model for automated diagnosis of Schizophrenia using EEG signals. Applied Sciences (Switzerland), 9(14). https://doi.org/10.3390/app9142870
• Phang CR, Noman F, Hussain H, Ting CM, Ombao H, 2020. A Multi-Domain Connectome Convolutional Neural Network for Identifying Schizophrenia from EEG Connectivity Patterns. IEEE Journal of Biomedical and Health Informatics, 24(5), 1333–1343. https://doi.org/10.1109/JBHI.2019.2941222
• Piryatinska A, Darkhovsky B, Kaplan A, 2017. Binary classification of multichannel-EEG records based on the ϵ-complexity of continuous vector functions. Computer Methods and Programs in Biomedicine, 152, 131–139. https://doi.org/10.1016/j.cmpb.2017.09.001
• Sabeti M, Katebi S, Boostani R, 2009. Entropy and complexity measures for EEG signal classification of schizophrenic and control participants. Artificial Intelligence in Medicine, 47(3), 263–274. https://doi.org/10.1016/j.artmed.2009.03.003
• Santos-Mayo L, San-Jose-Revuelta LM, Arribas JI, 2017. A computer-aided diagnosis system with EEG based on the p3b wave during an auditory odd-ball task in schizophrenia. IEEE Transactions on Biomedical Engineering, 64(2), 395–407. https://doi.org/10.1109/TBME.2016.2558824
• Yasin S, Hussain SA, Aslan S, Raza I, Muzammel M, Othmani A, 2021. EEG based Major Depressive disorder and Bipolar disorder detection using Neural Networks:A review. Computer Methods and Programs in Biomedicine, 202. https://doi.org/10.1016/j.cmpb.2021.106007