A neural network model for recognizing indicators of presuicidal risk in adolescents in the digital educational environment

Relevance. The digitalization of education enables the application of machine learning methods and neural network models to monitoring and decision support in the educational environment. One of the most socially significant tasks is the early automated identification of adolescents’ presuicidal risk, the effectiveness of which critically depends on a well-grounded set of model input features.
The aims of the study presented in the article are to develop the architecture of a neural network model for recognizing indicators of adolescents’ presuicidal risk in the digital educational environment and to empirically substantiate its set of input features based on self-attitude indicators and the riskogenity of the educational environment.

Materials and methods. The empirical basis for feature selection consisted of data from 599 students aged 13–17 years (M = 14.34; SD = 0.83). The Self-Attitude Inventory by S. R. Pantileev, the Piers—Harris Self-Concept Scale, the inventory of the propensity for victim behavior, the personal differential and the “Index of sociocultural safety of a schoolchild” were used. Feature selection and validation were performed using correlation analysis, Student’s t-test and one-way analysis of variance (ANOVA); a fully connected neural network architecture with a three-class output was proposed.
Results. A compact, empirically substantiated set of input features was formed: self-worth, self-acceptance, withdrawal, self-blame, behavior, family and the riskogenity of the educational environment. A high level of propensity for self-injurious and self-destructive behavior, corresponding to the target high-risk class, was found in 29 % of adolescents.
Conclusions. The proposed neural network model with an empirically grounded feature set can be integrated into the digital educational environment as a tool for scalable early identification of presuicidal risk, subject to ethical constraints and confirmation by a specialist.

1. Karakozov S. D., Samokhvalova E. A., Ryzhova N. I. Implementation of artificial intelligence essentials in the secondary general education informatics course: The practiceoriented aspect. Informatics and Education. 2024;39(5):6-20. (In Russian.) DOI: 10.32517/0234-0453-2024-39-5-6-20. EDN: EJGPIY.]

2. Walsh C. G., Ribeiro J. D., Franklin J. C. Predicting risk of suicide attempts over time through machine learning. Clinical Psychological Science. 2017;5(3):457–469. DOI: 10.1177/2167702617691560.

3. Jung Jun Su, Park Sung Jin, Kim Eun Young, Na Kyoung-Sae, Kim Young Jae, Kim Kwang Gi. Prediction models for high risk of suicide in Korean adolescents using machine learning techniques. PLOS ONE. 2019;14(6):e0217639. DOI: 10.1371/journal.pone.0217639.

4. Walsh C. G., Ribeiro J. D., Franklin J. C. Predicting suicide attempts in adolescents with longitudinal clinical data and machine learning. The Journal of Child Psychology and Psychiatry. 2018;59(12):1261–1270. DOI: 10.1111/jcpp.12916.

5. Lyubov E. B., Zotov P. B., Bannikov G. S. Self-harming behavior of adolescents: Definitions, epidemiology, risk factors and protective factors. The message I. Suicidology. 2019;10(4(37)):16–46. (In Russian.) DOI: 10.32878/suiciderus.19-10-04(37)-16-46. EDN: QZCFZQ.

6. Klonsky E. D. The functions of deliberate self-injury: A review of the evidence. Clinical Psychology Review. 2007;27(2):226–239. DOI: 10.1016/j.cpr.2006.08.002.

7. Whitlock J., Muehlenkamp J., Eckenrode J., Purington A., Baral Abrams G., Barreira P., Kress V. Nonsuicidal self-injury as a gateway to suicide in young adults. Journal of Adolescent Health. 2013;52(4):486–492. DOI: 10.1016/j.jadohealth.2012.09.010.

8. Syrokvashina K. V., Dozortseva E. G. Psychological factors of risk of suicidal behavior in adolescents. Counseling Psychology and Psychotherapy. 2016;24(3(92)):8–24. (In Russian.) DOI: 10.17759/cpp.2016240302. EDN: WMJCLX.

9. Kholmogorova A. B. Suicidal behavior: Theoretic model and practical implications in cognitive-behavioral therapy. Counseling Psychology and Psychotherapy. 2016;24(3(92)):144–163. (In Russian.) DOI: 10.17759/cpp.2016240309. EDN: WMJCOP.

10. Polskaya N. A. Risk factors and approaches to preventing self-injurious behavior in adolescents. Clinical Psychology and Special Education. 2018;7(2):1–20. (In Russian.) DOI: 10.17759/cpse.2018070201. EDN: XWQWOT.]

11. Bannikov G. S., Fedunina N. Yu., Pavlova T. S., Vikhristyuk O. V., Letova A. V., Bazhenova M. D. Mechanisms of self-harm behavior in non-clinical adolescent population: The results of monitoring in Moscow schools. Counseling Psychology and Psychotherapy. 2016;24(3(92)):42–68. (In Russian.) DOI: 10.17759/cpp.2016240304. EDN: WMJCMR.

12. Polskaya N. A., Vlasova N. V. Self-destructive behavior in adolescence and youth. Counseling Psychology and Psychotherapy. 2015;23(4(88)):176–190. (In Russian.) DOI: 10.17759/cpp.2015230411. EDN: VHSQOX.

13. Polskaya N. A. Emotional dysregulation in the structure of self-injurious behavior. Counseling Psychology and Psychotherapy. 2018;26(4(102)):65–82. (In Russian.) DOI: 10.17759/cpp.2018260405. EDN: YQHLOX.

14. Polskaya N. A., Yakubovskaya D. K. The impact of social media platforms on self-injurious behavior in adolescents. Counseling Psychology and Psychotherapy. 2019;27(3(105)):156–174. (In Russian.) DOI: 10.17759/cpp.2019270310. EDN: TJMBWB.

15. Polskaya N. A. The reasons of self-injurious behavior in youth (based on a self-report scale). Counseling Psychology and Psychotherapy. 2014;22(2(81)):140–152. (In Russian.) EDN: SJUUMP.

16. Stolin V. V. Self-consciousness of the personality. Moscow, Moscow University Press; 1983. 284 p. (In Russian.)

17. Sardzhveladze N. I. Personality and its interaction with the social environment. Tbilisi, Metsniereba; 1989. 206 p. (In Russian.)

18. Baeva I. A. Mental health of adolescents. How to support it? Psychological Science and Education. 2012;17(4):11–17. (In Russian.) EDN: PYRBYX.

19. Gilemkhanova E. N. Technique “Adolescence sociocultural safety index”. Moscow University Psychology Bulletin. 2019;(2):164–183. (In Russian.) DOI: 10.11621/vsp.2019.02.164. EDN: VSKGLN.

20. Gilemkhanova E. N. Diseased subjectness as an indicator of security problems of the “subject-context” system of the educational environment. The World of Science, Culture and Education. 2022;(4(95)):103–113. (In Russian.) DOI: 10.24412/1029-3388-2022-4-103-113. EDN: DLPJNX.

21. Andronnikova O. O. Methodology for studying the propensity for victim behavior: a study guide. Novosibirsk, NSPU; 2015. 105 p. (In Russian.)

22. Prikhozhan A. M. Diagnostics of personal development of adolescent children. Moscow, ANO “PEB”; 2007. 56 p. (In Russian.)

23. Pantileev S. R. Methodology for the study of self-attitude. Moscow, Smysl; 1993. 32 p. (In Russian.)

24. Bazhin E. F., Etkind A. M. Personal differential: Methodological recommendations. Leningrad, V. M. Bekhterev Institute; 1983. 12 p. (In Russian.)

25. Kapranova L. D. Digital transformation of society and the standard of living of the population. Economics, Taxes & Law. 2025;18(3):81–91. (In Russian.) DOI: 10.26794/1999-849X-2025-18-3-81-91. EDN: GDXTGU.

26. Maksimova M. V., Frolova O. V., Etuev Kh. Kh., Aleksandrova L. D. Adaptive personalized learning: Implementation of emerging technologies in higher education. Informatics and Education. 2023;38(4):14–27. (In Russian.) DOI: 10.32517/0234-0453-2023-38-4-14-27. EDN: ZXOKFV.

27. Ilyina I. Yu. Formation of competitive strategies for teachers of Russian universities in the context of digitalization of education. Economics, Taxes & Law. 2024;17(4):92-101. (In Russian.) DOI: 10.26794/1999-849X-2024-17-4-92-101. EDN: BQXUXU.

28. Kashirsky D. V., Sabelnikova N. V. Personality predictors of the attitude to the digitalization of education among Russian students. Psychological Science and Education. 2024;29(4):44–62. (In Russian.) DOI: 10.17759/pse.2024290404. EDN: RTJGOP.

29. Barabash D. A., Panov P. M. Creating a software prototype of the face recognition system for educational institutions on the “1C:Enterprise” platform. Informatics and Education. 2023;38(6):52–58. (In Russian.) DOI: 10.32517/0234-0453-2023-38-6-52-58. EDN: INQART.

30. Markina O. S., Molchanov S. V. The relationship between the perception of emotionally significant events in one’s life and world assumptions of the student youth during the period of transitive changes. Psychological-Educational Studies. 2023;15(2):3–17. (In Russian.) DOI: 10.17759/psyedu.2023150201. EDN: JHUEIZ.