Detection of anxiety with non-linear EEG dynamics

Yıl 2024, , 558 - 567, 15.04.2024

Elif Uğurgöl , Turgay Batbat , Demet Yesilbas , Miray Altınkaynak , Ayşegül Güven , Esra Demirci , Nazan Dolu

https://doi.org/10.28948/ngumuh.1359809

Öz

Anxiety is a psychiatric disorder characterized by excessive worry frequently encountered within society. Given the prevalence of anxiety and the limitations of current subjective assessment methods, the quantitative determination of this disorder gains significance. In pursuit of this objective, the study employed the 4-point likert-type Beck Anxiety Scale alongside essential clinical evaluations. As a result of the assessment, two participant groups were formed: one consisting of individuals with anxiety disorder and the other serving as the control group. Electroencephalography (EEG) recordings were obtained from the participants during resting states, followed by the computation of entropy and Hjorth (mobility, complexity) parameters from the EEG signals. The computed features were then classified using machine learning algorithms, namely K-Nearest Neighbor (kNN), Multi-Layer Perceptron (MLP), and Random Forest (RF), for classification purposes. The k-Nearest Neighbor (kNN) model, which yielded the most successful outcome among these classifiers, was able to reach an accuracy level of 88.4%. Furthermore, the combined utilization of diverse parameters was observed to lead to an increase in the success rate across all three algorithms.

Anahtar Kelimeler

EEG, Anxiety Disorder, Resting State, Machine Learning

Etik Beyan

Valid ethical documents regarding the method and participants used in the study have been uploaded as an additional file.

Destekleyen Kurum

TUBITAK

Proje Numarası

121E502

Doğrusal olmayan EEG dinamikleri ile anksiyete tespiti

Öz

Anksiyete, toplum içerisinde sıklıkla rastlanılan ve aşırı kaygı ile karakterize edilen psikiyatrik bir bozukluktur. Mevcut subjektif yöntemler düşünüldüğünde bu bozukluğun kantitatif yöntemlerle tespiti önem kazanmaktadır. Bu amaçla yapılan çalışmada 4’lü likert tipli Beck Anksiyete Ölçeği kullanılıp gerekli klinik değerlendirmeler yapılmıştır. Değerlendirme sonucunda anksiyete bozukluğu bulunan grup ve kontrol grubu şeklinde iki katılımcı grubu belirlenmiştir. Katılımcılardan dinlenim durumunda Elektroensefalografi (EEG) kayıtları alınmış daha sonra EEG sinyallerinden entropi ve Hjorth (karmaşıklık, hareketlilik) parametreleri hesaplanmıştır. Hesaplanan öznitelikler makine öğrenmesinde K -En Yakın Komşu (K-Nearest Neighbor, kNN), Çok Katmanlı Algılayıcı (Multi-Layer Perceptron, MLP) ve Rastgele Orman (Random Forest, RF) sınıflandırma algoritmalarıyla sınıflandırılmışlardır. Bu sınıflandırıcılardan en başarılı sonuç veren model olan kNN %88.4 değerine kadar ulaşabilmiştir. Ayrıca farklı parametrelerin bir arada kullanımının başarı oranında 3 algoritma için yükselişe sebep olduğu gözlenmiştir. Bu sonuçlar makineli öğrenme tekniklerinin anksiyetenin tanı süreçlerinde kullanımına uygun olduğunu gösteren çalışmaları desteklemektedir.

Anahtar Kelimeler

EEG, Anksiyete Bozukluğu, Dinlenim Durumu, Makineli Öğrenme

Etik Beyan

Çalışmada kullanılan yöntem ve katılımcılarla ilgili geçerli etik belgeler ek dosya olarka yüklenmiştir.

Destekleyen Kurum

TÜBİTAK

Proje Numarası

121E502

Kaynakça

• American Psychiatric Association, Diagnostic and Statistical Manual of Mental Disorders, American Psychiatric Association Publishing, 2022. https://doi.org/10.1176/appi.books.9780890425787.
• R.C. Kessler, M. Petukhova, N.A. Sampson, A.M. Zaslavsky, H.U. Wittchen, Twelve-month and lifetime prevalence and lifetime morbid risk of anxiety and mood disorders in the United States. The International Journal of Methods in Psychiatric Research, 21, 169–184, 2012. https://doi.org/10. 1002/mpr.1359.
• X. Yang, Y. Fang, H. Chen, T. Zhang, X. Yin, J. Man, L. Yang, M. Lu, Global, regional and national burden of anxiety disorders from 1990 to 2019: results from the Global Burden of Disease Study 2019, Epidemiology and Psychiatric Sciences, 30, e36, 2021.
• B.J. Casey, F.S. Lee, Optimizing treatments for anxiety by age and genetics. Annals of the New York Academy of Sciences, 1345, 16–24, 2015. https://doi.org/10.1111/nyas.12746.
• T. Allison, Recording and interpreting event-related potentials, in: E. Donchin (Ed.). Cogn. Psychophysiol. Event-Related Potensials Study Hum. Cogn., Laurence Erlbaum Associates, Hillsdale NJ, 1986.
• Ü.İ. Alkaç, Beyin Araştırmaları Tarihinde Bir Gezinti : Elektronörofizyoloji. Klinik gelişim, 3, 14–19, 2009.
• S. Aliakbaryhosseinabadi, E.N. Kamavuako, N. Jiang, D. Farina, N. Mrachacz-Kersting, Classification of EEG signals to identify variations in attention during motor task execution. Journal of Neuroscience Methods, 284, 27–34, 2017. https://doi.org/10.1016/j.jneumeth.2017.04.00 8.
• S.M. Snyder, T.A. Rugino, M. Hornig, M.A. Stein, Integration of an EEG biomarker with a clinician’s ADHD evaluation. Brain and Behavior, 5, 1–17, 2015. https://doi.org/10.1002/brb3.330.
• J.S. Damoiseaux, S.A.R.B. Rombouts, F. Barkhof, P. Scheltens, C.J. Stam, S.M. Smith, C.F. Beckmann, Consistent resting-state networks across healthy subjects. Proceedings of the National Academy of Sciences of the United States of America, 103, 13848–13853, 2006. https://doi.org/10.1073/pnas.06014171 03.
• D. Mantini, M.G. Perrucci, C. Del Gratta, G.L. Romani, M. Corbetta, Electrophysiological signatures of resting state networks in the human brain. Proceedings of the National Academy of Sciences of the United States of America, 104, 13170–13175, 2007. https://doi.org/ 10.1073/pnas.0700668104.
• F. Li, L. Jiang, Y. Liao, Y. Si, C. Yi, Y. Zhang, X. Zhu, Z. Yang, D. Yao, Z. Cao, P. Xu, Brain variability in dynamic resting-state networks identified by fuzzy entropy: A scalp EEG study. Journal of neural engineering, 18, 46097, 2021. https://doi.org/10.1088/1741-2552/ac0d41.
• O. Al Zoubi, A. Mayeli, A. Tsuchiyagaito, M. Misaki, V. Zotev, H. Refai, M. Paulus, J. Bodurka, R.L. Aupperle, S.S. Khalsa, J.S. Feinstein, J. Savitz, Y.H. Cha, R. Kuplicki, T.A. Victor, EEG microstates temporal dynamics differentiate individuals with mood and anxiety disorders from healthy subjects. Frontiers in Human Neuroscience, 13, 1–10, 2019. https://doi.org/10.33 89/fnhum.2019.00056.
• A. Al-Ezzi, N. Kamel, I. Faye, E. Gunaseli, Analysis of default mode network in social anxiety disorder: Eeg resting-state effective connectivity study. Sensors, 21, 1–19, 2021. https://doi.org/10.3390/s21124098.
• S.M. Pincus, Approximate entropy as a measure of irregularity for psychiatric serial metrics. Bipolar Disorders, 8, 430–440, 2006. https://doi.org/10.1111/j.13 99-5618.2006.00375.x.
• N. Kannathal, M.L. Choo, U.R. Acharya, P.K. Sadasivan, Entropies for detection of epilepsy in EEG. Computer Methods and Programs in Biomedicine, 80, 187–194, 2005. https://doi.org/10.1016/j.cmpb.2005.06.012.
• T. Batbat, A. Güven, N. Dolu, Evaluation of divided attention using different stimulation models in event-related potentials. Medical & Biological Engineering & Computing, 57, 2069–2079, 2019. https://doi.org/10.1007/s11517-019-0201 3-x.
• S.-H. Oh, Y.-R. Lee, H.-N. Kim, A Novel EEG Feature Extraction Method Using Hjorth Parameter. International Journal of Electronics and Electrical Engineering, 2, 106–110, 2014. https://doi. org/10.12720/ijeee.2.2.106-110.
• T. Elbert, W. Lutzenberger, B. Rockstroh, P. Berg, R. Cohen, Physical aspects of the EEG in schizophrenics. Biological psychiatry, 32, 595–606, 1992. https://doi.org/ 10.1016/0006-3223(92)90072-8.
• X.T. Li, The distribution of left and right handedness in Chinese people. Acta Psychologica Sinica, 3, 268–276, 1983.
• M. Altınkaynak, Dikkat Eksikliği Ve Hiperaktivitesi Olan Hastalarda Kognitif Fonksiyonların Uyarılmış Potansiyel Ve Fonksiyonel Yakın Kızıl Ötesi Spektroskopisi Yöntemleriyle İncelenmesi. Doktora Tezi, Erciyes Üniversitesi Fen Bilimleri Enstitüsü, Türkiye, 2021.
• L. Guo, Y. Wu, L. Zhao, T. Cao, W. Yan, X. Shen, Classification of mental task from EEG signals using immune feature weighted support vector machines. IEEE Transactions on Magnetics, 47, 866–869, 2011. https://doi.org/ 10.1109/TMAG.2010.2072775.
• Q. Meng, W. Zhou, Y. Chen, J. Zhou, Feature analysis of epileptic EEG using nonlinear prediction method. 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, Soc. EMBC’10, pp. 3998–4001, IEEE, 2010. https://doi.org/ 10.1109/IEMBS.2010.5628001.
• Y. Li, Y. Fan, C. Qian, EEG nonlinear feature detection in brain-computation interface. 2009 3rd International Conference on Bioinformatics and Biomedical Engineering, pp. 1–4, IEEE, 2009. https://doi.org/10.1109/ICBBE.2009.516268 1.
• W.X. He, X.G. Yan, X.P. Chen, H. Liu, Nonlinear feature extraction of sleeping EEG signals. 2005 IEEE engineering in medicine and biology 27th annual conference, pp. 4614–4617, IEEE, 2005. https://doi.org/10.1109/iembs.2005.1 615498.
• X.W. Wang, D. Nie, B.L. Lu, Emotional state classification from EEG data using machine learning approach. Neurocomputing, 129, 94–106, 2014. https://doi.org/10.1016/j.neucom.2013.06.046.
• M. Čukić, V. López, J. Pavón, Classification of depression through resting-state electroencephalogram as a novel practice in psychiatry: review. Journal of Medıcal Internet Research, 22, e19548, 2020. https://doi.org/10. 2196/19548.
• D. Librenza-Garcia, B.J. Kotzian, J. Yang, B. Mwangi, B. Cao, L.N. Pereira Lima, M.B. Bermudez, M.V. Boeira, F. Kapczinski, I.C. Passos, The impact of machine learning techniques in the study of bipolar disorder: A systematic review. Neuroscience & Biobehavioral Reviews, 80, 538–554, 2017. https://doi.org/10.1016/j.neu biorev.2017.07.004.
• H. Cai, J. Han, Y. Chen, X. Sha, Z. Wang, B. Hu, J. Yang, L. Feng, Z. Ding, Y. Chen, J. Gutknecht, A Pervasive Approach to EEG-Based Depression Detection. Complexity, 2018, 1–13, 2018. https://doi. org/10.1155/2018/5238028.
• D. Şayık, D. Yiğit, A. Açıkgöz, E. Çolak, Ö. Mumcu, Koronavirüs anksiyete ölçeğinin Türkçe geçerliliği ve güvenirliği. Eskisehir Medical Journal, J. 2, 16–22, 2021.
• F. Yıldırım, İ.Ö. İlhan, Genel öz yeterlilik ölçeği Türkçe formunun geçerlilik ve güvenilirlik çalışması. Türk Psikiyatri Dergisi, 21, 301–308, 2010.
• M. Ulusoy, N. H. Sahin, & H. Erkmen, Turkish version of the Beck Anxiety Inventory: psychometric properties. Journal of cognitive psychotherapy, 12(2), 163, 1998.
• A. T. Beck, N. Epstein, G. Brown & Steer,R., Beck anxiety inventory. Journal of consulting and clinical psychology, 7(3), 195-205, 1993.
• A. Babayiğit, & E. Erdem, Şanlıurfa Örnekleminde Depresif Belirtiler ve Anksiyete Yaygınlığının COVİD-19 ve Psikolojik Dayanıklılık ile İlişkisinin İncelenmesi. Kıbrıs Türk Psikiyatri ve Psikoloji Dergisi, 5(3), 239-249, 2023.
• L. A. Schmidt, K. L. Poole, R. Hassan, T. Willoughby, Frontal EEG alpha-delta ratio and social anxiety across early adolescence. International Journal of Psychophysiology, 175, 1-7, 2022. https://doi.org/10.1016/j.ijpsycho .2021.12.011.
• Ü. Işık, A. Güven, T. Batbat, Evaluation of Emotions from Brain Signals on 3D VAD Space via Artificial Intelligence Techniques. Diagnostics, 13, 2141, 2023. https://doi.org/10.3390/diagnostics13132141.
• H.U. Amin, A.S. Malik, R.F. Ahmad, N. Badruddin, N. Kamel, M. Hussain, W.T. Chooi, Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques. Australasian Physical & Engineering Sciences in Medicine, 38, 139–149, 2015. https://doi.org/10.1007/s13246-015-0333-x.
• O. Bahadır, H. Türkmençalıkoğlu, Bilgi Kuramında Shannon Entropisi ve Uygulamaları. The European Journal of Science and Technology, 491–497, 2022. https://doi.org/10.31590/ejosat.1039771.
• T. Batbat, İşitsel ve görsel uyaranlar ile elde edilen uyarılmış potansiyel sinyallerinden farklı dikkat durumlarının değerlendirilmesi. Doktora Tezi, Erciyes Üniversitesi Fen Bilimleri Enstitüsü, Türkiye, 2020.
• R.M. Mehmood, H.J. Lee, A novel feature extraction method based on late positive potential for emotion recognition in human brain signal patterns. Computers & Electrical Engineering, 53, 444-457, 2016. https://doi.org/10. 1016/j.compeleceng.2016.04.009.
• R. Jenke, A. Peer, M. Buss, Feature extraction and selection for emotion recognition from EEG. IEEE Transactions on Affective computing. 5, 327–339, 2014. https://doi. org/10.1109/TAFFC.2014.2339834.
• Z. Li, X. Wu, X. Xu, H. Wang, Z. Guo, Z. Zhan, L. Yao, The Recognition of Multiple Anxiety Levels Based on Electroencephalograph. IEEE Transactions on Affective Computing, 13, 519–529, 2022. https://doi.org/10.1109 /TAFFC.2019.2936198.
• P. Bhuvaneswari, J.S. Kumar, Influence of linear features in nonlinear electroencephalography (EEG) signals. Procedia Computer Science, 47, 229–236, 2015. https://doi.org/10.1016/j.procs.2015.03.202.
• N.S. Altman, An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46, 175–185, 1992. https://doi.org/10.1080/00031305.19 92.10475879.
• S. Ibrahim, R. Djemal, A. Alsuwailem, S. Gannouni, Electroencephalography (EEG)-based epileptic seizure prediction using entropy and K-nearest neighbor (KNN). Communications in Science and Technology, 2,6–10, 2017. https://doi.org/10.21924/cst.2.1.2017.44.
• M.N.A.H. Sha’abani, N. Fuad, N. Jamal, M.F. Ismail, kNN and SVM Classification for EEG: A Review. Lect. Notes Electr. Eng., pp. 555–565, Springer, 2020. https://doi.org/10.1007/978-981-15-2317-5_47.
• F. Murtagh, Multilayer perceptrons for classification and regression. Neurocomputing, 2, 183–197, 1991. https://doi.org/10.1016/0925-2312(91)90023-5.
• R. Chatterjee, T. Bandyopadhyay, EEG Based Motor Imagery Classification Using SVM and MLP. Proceedings of the 5th International Conference on Electrical, Control & Computer Engineering, 29th July 2019, pp. 84–89, Kuantan, Pahang, Malaysia, IEEE, 2016. https://doi.org/10.1109/CINE.2016.22.
• L. Breiman, Random forests. Machine Learning, 45, 5–32, 2001.
• M. Koçyiğit, A. Güven, F. Çam, Beyin Bilgisayar Arayüzünün Geliştirilmesi İçin Hayali Motor Görüntü Tabanlı Yakın Kızılötesi Spektroskopi Sinyallerinin Sınıflandırılması. Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 9, 1–8, 2020. https://doi.org/10.28948/ngumuh.606507.
• W. Chen, Y. Wang, G. Cao, G. Chen, Q. Gu, A random forest model based classification scheme for neonatal amplitude-integrated EEG. Biomedical engineering online, 13, 1–13, 2014. https://doi.org/10.1186/1475-925X-13-S2-S4.
• A. Arsalan, M. Majid, A study on multi-class anxiety detection using wearable EEG headband. J. Journal of Ambient Intelligence and Humanized Computing, 13, 5739–5749, 2022. https://doi.org/10.1007/s12652-021-03249-y.
• S.I. Dimitriadis, C.I. Salis, D. Liparas, An automatic sleep disorder detection based on EEG cross-frequency coupling and random forest model. Journal of Neural Engineering, 18, 46064, 2021. https://doi.org/10.1088/1741-2552/abf 773.
• C. Kamarajan, B.A. Ardekani, A.K. Pandey, D.B. Chorlian, S. Kinreich, G. Pandey, J.L. Meyers, J. Zhang, W. Kuang, A.T. Stimus, B. Porjesz, Random forest classification of alcohol use disorder using EEG source functional connectivity, neuropsychological functioning, and impulsivity measures. Behavioral Sciences, 10, 62, 2020. https://doi.org/10.3390/bs1 0030062.
• A. Tharwat, Classification assessment methods. Applied computing and informatics, 17, 168–192, 2018. https://doi. org/10.1016/j.aci.2018.08.003.
• Ž. Vujović, Classification Model Evaluation Metrics. International Journal of Advanced Computer Science and applications, 12, 599–606, 2021. https://doi.org/10.14569/IJACSA.2021.0120670.
• T. Saito, M. Rehmsmeier, The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One, 10, e0118432, 2015. https://doi.org/10.1371/journal. pone.0118432.
• A. Zugman, L. Jett, C. Antonacci, A. M. Winkler, & D. S. Pine, A Systematic Review and Meta-Analysis of Resting-state fMRI in Anxiety Disorders: Need for Data Sharing to Move the Field Forward. Journal of Anxiety Disorders, 102773, 2023.
• S. Mizzi, M. Pedersen, V. Lorenzetti, M. Heinrichs, & I. Labuschagne, Resting-state neuroimaging in social anxiety disorder: a systematic review. Molecular Psychiatry, 27(1), 164-179, 2022.
• ND. Woodward, CJ. Cascio. Resting-State Functional Connectivity in Psychiatric Disorders. JAMA Psychiatry, 72(8), 743-4. 2015. https://doi.org/10.1001/jam apsychiatry.2015.0484.
• L.S. Mokatren, R. Ansari, A.E. Cetin, A.D. Leow, O. Ajilore, H. Klumpp, F.T.Y. Vural, EEG Classification based on Image Configuration in Social Anxiety Disorder. International IEEE/EMBS Conference on Neural Engineering (NER), pp. 577–580, IEEE, 2019. https://doi.org/10.1109/NE R.2019.8717152.
• A. Al-Ezzi, A.A. Al-Shargabi, F. Al-Shargie, A.T. Zahary, Complexity Analysis of EEG in Patients With Social Anxiety Disorder Using Fuzzy Entropy and Machine Learning Techniques. IEEE Access, 10, 39926–39938, 2022. https://doi.org/10.1109/ACCES S.2022.3165199.
• J.W.G. Tiller, Depression and anxiety. The Medical Journal of Australia, 199, 28–31, 2013. https://doi.org/10.5694/mja12.1 0628.
• H. Türkçapar, Anksiyete Bozukluğu ve Depresyonun Tanısal İlişkileri. Klinik Psikiyatri, 4, 12–16, 2004.
• O. Karamustafalıoğlu, H. Yumrukçal, Depresyon ve anksiyete bozuklukları. Şişli Etfal Hastanesi Tıp Bülteni, 45, 65–74, 2011.