Prediction of salivary cortisol level by electroencephalography features

Behrouz Alizadeh Savareh; Azadeh Bashiri; Mohammad Mehdi Hatef; Boshra Hatef

doi:10.1515/bmt-2020-0005

Article

Prediction of salivary cortisol level by electroencephalography features

Behrouz Alizadeh Savareh , Azadeh Bashiri , Mohammad Mehdi Hatef and Boshra Hatef

Published/Copyright: December 21, 2020

Published by

Become an author with De Gruyter Brill

Submit Manuscript Author Information

From the journal Biomedical Engineering / Biomedizinische Technik Volume 66 Issue 3

Abstract

Change in cortisol affects brain EEG signals. So, the identification of the significant EEG features which are sensitized to cortisol concentration was the aim of the present study. From 468 participated healthy subjects, the salivary samples were taken to test the cortisol concentration and EEG signal recording was done simultaneously. Then, the subjects were categorized into three classes based on the salivary cortisol concentration (<5, 5–15 and >15 nmol/l). Some linear and nonlinear features extracted and finally, in order to investigate the relationship between cortisol level and EEG features, the following steps were taken on features in sequence: Genetic Algorithm, Neighboring Component Analysis, polyfit, artificial neural network and support vector machine classification. Two classifications were considered as following: state 1 categorized the subjects into three groups (three classes) and the second state put them into two groups (group 1: class 1 and 3, group 2: class 2). The best classification was done using ANN in the second state with the accuracy=94.1% while it was 92.7% in the first state. EEG features carefully predicted the cortisol level. This result is applicable to design the intelligence brain computer machines to control stress and brain performance.

Keywords: artificial neural network; EEG; salivary cortisol; support vector machine

Corresponding author: Boshra Hatef, Neuroscience Research Center, Baqiyatallah University of Medical Sciences, Tehran881435916471, Islamic Republic of Iran, E-mail: boshrahatef@bmsu.ac.ir

Acknowledgment

This paper was part of a project in Neuroscience Research Center, Baqiyatallah University of Medical Sciences. It should be noted the ethical code of this study is IR.BMSU.REC.1398.141. Boshra Hatef would like to appreciate the organizations mentioned above and all who helped the research team with doing this research.

Research funding: Authors state no funding involved.
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
Competing interests: No potential conflict of interest relevant to this article was reported.
Informed consent: Informed consent was obtained from all individuals included in this study.
Ethical approval: The ethical consent forms approved by Baqiyatallah University of medical science were signed by participants.

References

1. Spencer, RL, Chun, LE, Hartsock, MJ, Woodruff, ER. Glucocorticoid hormones are both a major circadian signal and major stress signal: how this shared signal contributes to a dynamic relationship between the circadian and stress systems. Front Neuroendocrinol 2018;49:52–71. https://doi.org/10.1016/j.yfrne.2017.12.005.Search in Google Scholar

2. Kino, T. Circadian rhythms of glucocorticoid hormone actions in target tissues. Potential clinical implications. Sci Signal 2012;5:pt4. https://doi.org/10.1126/scisignal.2003333.Search in Google Scholar

3. Nicolaides, NC, Charmandari, E, Chrousos, GP, Kino, T. Circadian endocrine rhythms: the hypothalamic-pituitary-adrenal axis and its actions. Ann NY Acad Sci 2014;1318:71–80. https://doi.org/10.1111/nyas.12464.Search in Google Scholar

4. Urry, HL, Van Reekum, CM, Johnstone, T, Kalin, NH, Thurow, ME, Schaefer, HS, et al.. Amygdala and ventromedial prefrontal cortex are inversely coupled during regulation of negative affect and predict the diurnal pattern of cortisol secretion among older adults. J Neurosci 2006;26:4415–25. https://doi.org/10.1523/jneurosci.3215-05.2006.Search in Google Scholar

5. McEwen, BS, Bowles, NP, Gray, JD, Hill, MN, Hunter, RG, Karatsoreos, IN, et al.. Mechanisms of stress in the brain. Nat Neurosci 2015;18:1353–63. https://doi.org/10.1038/nn.4086.Search in Google Scholar

6. Yaribeygi, H, Panahi, Y, Sahraei, H, Johnston, TP, Sahebkar, A. The impact of stress on body function: a review. EXCLI J 2017;16:1057–72. https://doi.org/10.17179/excli2017-480.Search in Google Scholar

7. McEwen, BS, Bowles, NP, Gray, JD, Hill, MN, Hunter, RG, Karatsoreos, IN. Mechanisms of stress in the brain. Nat Neurosci 2015;18:1353–63. https://doi.org/10.1038/nn.4086.Search in Google Scholar

8. Ghahvehchi-Hosseini, F, Manshadi, E, Mohammadi, A, Jahromi, GP, Hatef, B. Evaluation of the persistence effect acute social stress test on the alpha band power. J Mil Med 2018;20:509–18.Search in Google Scholar

9. Lupien, SJ, Maheu, F, Tu, M, Fiocco, A, Schramek, TE. The effects of stress and stress hormones on human cognition: implications for the field of brain and cognition. Brain Cognit 2007;65:209–37. https://doi.org/10.1016/j.bandc.2007.02.007.Search in Google Scholar

10. von Dawans, B, Kirschbaum, C, Heinrichs, M. The Trier Social Stress Test for Groups (TSST-G): a new research tool for controlled simultaneous social stress exposure in a group format. Psychoneuroendocrinology 2011;36:514–22. https://doi.org/10.1016/j.psyneuen.2010.08.004.Search in Google Scholar

11. Lotfan, S, Shahyad, S, Khosrowabadi, R, Mohammadi, A, Hatef, B. Support vector machine classification of brain states exposed to social stress test using EEG-based brain network measures. Biocybern Biomed Eng 2018;39:199–213. https://doi.org/10.1016/j.bbe.2018.10.008.Search in Google Scholar

12. Rezvani, Z, Hatef, B, Khosrowabadi, R, Meftahi, G-H. Alteration of brain functional network and cortisol level during induction and release of stress: an EEG study in young male adults. Basic Clin Neurosci 2020. https://doi.org/10.32598/bcn.2021.2525.1.10.32598/bcn.2021.2525.1Search in Google Scholar

13. Chapotot, F, Gronfier, C, Jouny, C, Muzet, A, Brandenberger, G. Cortisol secretion is related to electroencephalographic alertness in human subjects during daytime wakefulness. J Clin Endocrinol Metab 1998;83:4263–8. https://doi.org/10.1210/jcem.83.12.5326.Search in Google Scholar

14. Schutter, DJ, Van Honk, E. Salivary cortisol levels and the coupling of midfrontal delta-beta oscillations. Int J Psychophysiol 2005;55:127–9. https://doi.org/10.1016/j.ijpsycho.2004.07.003.Search in Google Scholar

15. Hayes, LD, Grace, FM, Kilgore, JL, Young, JD, Baker, JS. Diurnal variation of cortisol, testosterone, and their ratio in apparently healthy males. Sport Sci Practical Aspect 2012;9:5–13.Search in Google Scholar

16. Lisha, S, Ying, L, Beadle, PJ. Independent component analysis of EEG signals. In: Proceedings of 2005 IEEE international workshop on VLSI design and video technology, 2005; 28–30 May 2005. Suzhou, China: IEEE; 2005:127–9 pp.10.1109/IWVDVT.2005.1504590Search in Google Scholar

17. Stam, CJ. Nonlinear dynamical analysis of EEG and MEG: review of an emerging field. Clin Neurophysiol 2005;116:2266–301. https://doi.org/10.1016/j.clinph.2005.06.011.Search in Google Scholar

18. Ghahvehchi-Hosseini, F, Manshadi, E, Mohammadi, A, Pirzad-Jahromi, J, Hatef, B. Evaluation of the persistence effect acute social stress test on the alpha band power. J Mil Med 2018;20:509–18.Search in Google Scholar

19. Shen, L. Evolutionary Algorithms with Mixed Strategy. Aberystwyth University; 2016.Search in Google Scholar

20. Xie, L, Yuille, A. Genetic cnn. In: Proceedings of the IEEE international conference on computer vision. Venice, Italy; 2017:1388–97 pp.10.1109/ICCV.2017.154Search in Google Scholar

21. Binary genetic algorithm [https://ww2.mathworks.cn/matlabcentral/fileexchange/46961-binary-genetic-algorithm-feature-selection-zip/?s_tid=ILM2FXsub].Search in Google Scholar

22. Yang, W, Wang, K, Zuo, WJJ. Neighborhood component feature selection for high-dimensional data. J Comput 2012;7:161–8. https://doi.org/10.4304/jcp.7.1.161-168.Search in Google Scholar

23. Savareh, BA, Bashiri, A, Behmanesh, A, Meftahi, GH, Hatef, B. Performance comparison of machine learning techniques in sleep scoring based on wavelet features and neighboring component analysis. Peer J 2018;6:e5247. https://doi.org/10.7717/peerj.5247.Search in Google Scholar

24. Polynomial fitting [https://www.mathworks.com/help/matlab/ref/polyfit.html?searchHighlight=polyfit&s_tid=doc_srchtitle].Search in Google Scholar

25. Bashiri, A, Shahmoradi, L, Beigy, H, Savareh, BA, Nosratabadi, M, Kalhori, SRN, et al.. Quantitative EEG features selection in the classification of attention and response control in the children and adolescents with attention deficit hyperactivity disorder. Future Sci OA 2018;4:FSO292. https://doi.org/10.4155/fsoa-2017-0138.Search in Google Scholar

26. Alizadeh, B, Safdari, R, Zolnoori, M, Bashiri, A. Developing an intelligent system for diagnosis of asthma based on artificial neural network. Acta Inf Med 2015;23:220–3. https://doi.org/10.5455/aim.2015.23.220-223.Search in Google Scholar

27. Mohammadfam, I, Soltanzadeh, A, Moghimbeigi, A, Savareh, BA. Use of artificial neural networks (ANNs) for the analysis and modeling of factors that affect occupational injuries in large construction industries. Electron Physician 2015;7:1515–22. https://doi.org/10.19082/1515.Search in Google Scholar

28. Gallagher, JP, Orozco-Cabal, LF, Liu, J, Shinnick-Gallagher, P. Synaptic physiology of central CRH system. Eur J Pharmacol 2008;583:215–25. https://doi.org/10.1016/j.ejphar.2007.11.075.Search in Google Scholar

29. Joëls, M. Corticosteroid effects in the brain. U-shape it. Trends Pharmacol Sci 2006;27:244–50. https://doi.org/10.1016/j.tips.2006.03.007.Search in Google Scholar

30. Mohammadi, A, Emamgoli, A, Shirinkalam, M, Meftahi, GH, Shahyad, S, Yagoobi, K, et al.. The persistent effect of acute psychosocial stress on heart rate variability. EHJ 2019;71:18.10.1186/s43044-019-0009-zSearch in Google Scholar PubMed PubMed Central

31. Lotfan, S, Shahyad, S, Khosrowabadi, R, Mohammadi, A, Hatef, B. Support vector machine classification of brain states exposed to social stress test using EEG-based brain network measures. Biocybern Biomed Eng 2019;39:199–213. https://doi.org/10.1016/j.bbe.2018.10.008.Search in Google Scholar

32. Aardal, E, Holm, A-C. Cortisol in saliva-reference ranges and relation to cortisol in serum. Clin Chem Lab Med 1995;33:927–32. https://doi.org/10.1515/cclm.1995.33.12.927.Search in Google Scholar

33. Echouffo-Tcheugui, JB, Conner, SC, Himali, JJ, Maillard, P, DeCarli, CS, Beiser, AS, et al.. Circulating cortisol and cognitive and structural brain measures: the Framingham heart study. Neurology 2018;91:e1961–70. https://doi.org/10.1212/wnl.0000000000006549.Search in Google Scholar

34. Ouanes, S, Popp, J. High cortisol and the risk of dementia and Alzheimer’s disease: a review of the literature. Front Aging Neurosci 2019;11:43. https://doi.org/10.3389/fnagi.2019.00043.Search in Google Scholar

35. Jentsch, VL, Merz, CJ, Wolf, OT. Restoring emotional stability: cortisol effects on the neural network of cognitive emotion regulation. Behav Brain Res 2019;374:111880. https://doi.org/10.1016/j.bbr.2019.03.049.Search in Google Scholar

Received: 2020-01-12

Accepted: 2020-11-23

Published Online: 2020-12-21

Published in Print: 2021-06-25

You are currently not able to access this content.

Articles in the same Issue

https://doi.org/10.1515/bmt-2020-0005

Keywords for this article

artificial neural network; EEG; salivary cortisol; support vector machine