Detection of personal and situational anxiety based on electroencephalography using machine learning

The purpose of research. Nowadays electroencephalography is successfully used for diagnostics and rehabilitation of psychological and cognitive disorders. At the same time, practical healthcare meets with the difficulties related to the weakness  in objective assessment of  the severity of anxiety  states and  the  requirement  to  consider  the  individual characteristics of patients. These features are difficult to formalize, but can be taken into account when implementing machine learning methods. The purpose of the study is to evaluate the possibility of using machine learning technolo- gies to identify the level of anxiety correlated with the Spielberger-Khanin method, according to electroencephalography data. 
Methods. To identify anxiety in the main and control groups, the Spielberger-Khanin method was used, which allows for differential measurement of anxiety as a personal trait. Alpha rhythms were recorded using 6-channel electroen- cephalography. The CatBoost library, which implements a gradient boosting algorithm with loss function minimization, was used as a machine learning tool. 
Results. The experiment involved 92 respondents, divided into three groups based on the testing results. Before test- ing, all subjects were in a state of rest for 1.5 minutes with the EEG recording turned on. Then they were asked to take a test to determine personal anxiety with synchronous recording of alpha rhythm parameters. Based on the results of testing, respondents were divided into three groups in accordance with the level of a certain anxiety. The study revealed a relationship between different levels of anxiety according to the Spielberger-Khanin scale and the type of electroen- cephalogram in subjects, which makes it possible to move from testing patients to recording and interpreting EEG. 
Conclusion. The study revealed a positive relationship between different levels of personal anxiety according to the Spielberger-Khanin scale and the type of electroencephalogram in subjects with an accuracy of up to 14%. It is shown that when determining anxiety, it is possible to replace the test based on the Spielberger-Khanin method for determining anxiety by EEG using machine learning technology. 

1. Beauducel A., Brocke B., Leue A. Energetical bases of extraversion: effort, arousal, EEG, and performance. Int J. Psychophysiol. 2006;(62):212–223.

2. Frankel M.A., Lehmkuhle M.J., Spitz M.C., Newman B.J., Richards S.V., Arain A.M. Wearable reduced-channel EEG system for remote seizure monitoring. Front. Neurol. 2021;(12):728484. https://doi.org/10.3389/fneur.2021.728484. EDN OFZUVS

3. Zhuravlev D.V. Equipment for electroencephalographic research. Voronezh: Voronezh State Technical University; 2021. 259 p. (In Russ.)

4. Novikova S.I. EEG rhythms and cognitive processes. Psikhologicheskaya nauka i obra- zovanie = Psychological Science and Education. 2015;4(1):91–108. (In Russ.) EDN TZJDZX

5. Stankova E.P., Myshkin I.Yu. The influence of individual EEG characteristics and psychophysiological

6. features on reaction time. Nauchnoe obozrenie. Biologicheskie nauki = Sci-entific Review. Biological Sciences. 2015;(1):151–152. (In Russ.) EDN SBKXCZ

7. Kurbako A.V., Khramkov A.N., Borovkova E.I., Dubinkina E.S., Ishbulatov Yu.M., Ponomarenko V.I., Karavaev A.S., Prokhorov M.D. Hardware and software complex for diagnosing the psychophysiological state of a person in the process of solving cognitive problems. Izvestiya Saratovskogo universiteta. Novaya seriya. Seriya: Fizika = Proceedings of the Saratov University. A New Family. Series: Physics. 2024;4(1):19–29. (In Russ.) https://doi.org/10.18500/1817-3020-2024-24-1-19-29. EDN UFAMDM

8. Murodov V., Halimova F.T., Shumilina O.V. Comparative characteristics of the electrical activity of the brain and the degree of anxiety. Meditsinskii vestnik Natsional'noi akade- mii nauk Tadzhikistana = Medical Bulletin of the National Academy of Sciences of Tajikistan. 2022;12(4):34–39. (In Russ.) EDN LBVXGE

9. Kulikov V.Yu., Antropova L.K. Features of beta rhythm with closed and open eyes in moderately and highly anxious individuals. Sibirskii meditsinskii vestnik = Siberian Medical Bulletin. 2021;(3):37–43. (In Russ.) https://doi.org/10.31549/2541-8289-2021-3-37-43. EDN RFULKS

10. Gazenkampf K.A., Schneider N.A., Dmitrenko D.V., Karnaukhov V.E., Firsova D.A. Correlation of the power of the main EEG rhythms and the coherence coefficient with the level of anxiety and depression in adolescence. Vestnik klinicheskoi neirofiziologii = Bulletin of Clinical Neurophysiology. 2018;(S):38–39. (In Russ.) EDN FJQDGG

11. Cheremushkin E.A., Petrenko N.E., Alipov N.N., Sergeeva O.V. Changes in the power characteristics of the alpha rhythm in students with different levels of anxiety in conditions of normal sleep and partial deprivation when solving the GO/NOGO problem. Fizi-ologiya cheloveka = Human Physiology. 2022;48(2):79–85. (In Russ.) https://doi.org/10.31857/S0131164622020047. EDN TPRRDS

12. Astashchenko A.P., Gorbatenko N.P., Dorokhov E.V., Varvarova S.I., Zyablova P.V. The influence of anxiety associated with exam stress on the movement of visual attention and electrical activity of the frontal areas of the brain. Ul'yanovskii mediko-biologicheskii zhurnal = Ulyanovsk Medical and Biological Journal. 2020;(2):100–111. (In Russ.) https://doi.org/10.34014/2227-1848-2020-2-100-111. EDN PGHPGQ

13. Popova T.V., Koryukalov Yu.I., Kourova O.G. Determination of the risk of maladaptation by electroencephalogram for the prevention of mental overexertion. Zhurnal nevrologii i psikhiatrii im. S.S. Korsakova = Journal of Neurology and Psychiatry named after S.S. Kor-sakov. 2024;124(8):97–102. (In Russ.) https://doi.org/10.17116/jnevro202412408197. EDN NAXNJY

14. Karatygin N.A., Korobeynikova I.I., Venerina Ya.A., Biryukova E.V. The relationship of personal anxiety with the spectrally coherent characteristics of the Α1 rhythm of the human electroencephalogram. Mezhdunarodnyi zhurnal prikladnykh i fundamental'nykh issle-dovanii = International Journal of Applied and Fundamental Research. 2018;(9):91–97. (In Russ.) EDN PEQDPV

15. Dzhebrailova T.D., Korobeynikova I.I., Karatygin N.A., Biryukova E.V., Venerina Ya.A. Dynamics of spectral EEG characteristics in individuals with different personal needs during cognitive activity. Fiziologiya cheloveka = Human Physiology. 2021;47(1):20–30. (In Russ.) https://doi.org/10.31857/S0131164621010033. EDN AEIHVY

16. Venerina Ya.A., Dzhebrailova T.D., Karatygin N.A., Budnikov M.Y. Spectral characteristics of the EEG and the concentration of hormones in saliva in individuals with different personality anxiety during cognitive activity. Psikhicheskoe zdorov'e = Mental Health. 2021;(8):3–12. (In Russ.) https://doi.org/10.25557/2074-014X.2021.08.3-12. EDN XXCVSH

17. Galkin S.A. The relationship between the EEG profile and the clinical and psychopathological characteristics of patients with depressive disorders. Psikhicheskoe zdorov'e = Mental Health. 2021;(7):43–48. (In Russ.) EDN ZWOUFJ

18. Galkin S.A., Tkacheva G.D., Oshkina T.A., Vasilyeva S.N., Roshchina O.V., Ivanova S.A., Bohan N.A. The connection of bioelectric brain activity with the clinical features of the course of depressive disorders. Psikhicheskoe zdorov'e = Mental Health. 2020;(8):16–21. (In Russ.) https://doi.org/10.25557/2074-014X.2020.08.16-21. EDN PWDHMD

19. Spiel-berger C.D., Gorsuch R., Lushene R.E., Vagg P.R. Manual for the State-Trait Anxiety Inventory (Form Y1 – Y2). CA: Consulting Psychologists Press; 1983. 19. Khanin Yu.L. A brief guide to the scale of reactive and personal anxiety by C.D. Spielberger. Leningrad; 1976. 18 p. (In Russ.)

20. NEUROPLAY-6C. Universal 6-channel neural headset with neural games. (In Russ.) Available at: https://neuroplay.ru/catalog/neuroplay-6c/ (accessed 17.03.2025).

21. Prokhorenkova L., Gusev G., Vorobev A., et al. Catboost: Unbiased boosting with categorical features. Advances in Neural Information Processing Systems. Available at: https://arxiv.org/pdf/1706.09516 (accessed 17.03.2025).