Predicting Adolescent Suicide Risk in Smart Cities: An AI-Driven, Privacy-Preserving Architecture
Downloads
This study aims to improve the accuracy, speed, and safety of suicide risk assessment among adolescents in the digital ecosystems of smart cities. To achieve this goal, an integrated system architecture was developed that combines natural language processing methods, transformer models, and privacy-preserving computation. The methodological part includes large-scale textual data analysis, distributed processing in Apache Spark and Hadoop environments, and the use of federated learning, which allows models to be trained without transferring sensitive source information. The evaluation was conducted on open mental health datasets and supplemented by a series of experiments simulating the system's operation in real time, as well as surveys of specialists – psychologists, educators, and IT experts. The analysis showed that transformer models, particularly BERT, significantly outperform classical algorithms, achieving an AUC-ROC of 0.96 and an F1 score of 0.92 with an average response time of 2.4 seconds. Survey participants noted the importance of transparency and data protection, and the proposed architecture received high marks for reducing the risk of information leaks and providing robust audit mechanisms. The novelty of the work lies in the combination of predictive analytics, federated learning, differential privacy, and blockchain traceability in a single application-oriented system. The results show that ethically sound and rapid suicide risk detection can be implemented in schools, medical institutions, and municipal services, providing both practical benefits and contributing to methodological advancements.
Downloads
[1] Dean, J., & Ghemawat, S. (2008). MapReduce: Simplified data processing on large clusters. Communications of the ACM, 51(1), 107–113. doi:10.1145/1327452.1327492.
[2] Dayalan, M. (2018). MapReduce: simplified data processing on large cluster. International Journal of Research and Engineering, 5(5), 399-403.
[3] Zaharia, M., Chowdhury, M., Franklin, M. J., Shenker, S., & Stoica, I. (2010). Spark: Cluster computing with working sets. 2nd USENIX Workshop on Hot Topics in Cloud Computing, HotCloud 2010, 1-10.
[4] Zabala-Vargas, S., Jaimes-Quintanilla, M., & Jimenez-Barrera, M. H. (2023). Big Data, Data Science, and Artificial Intelligence for Project Management in the Architecture, Engineering, and Construction Industry: A Systematic Review. Buildings, 13(12), 2944. doi:10.3390/buildings13122944.
[5] Bernert, R. A., Hilberg, A. M., Melia, R., Kim, J. P., Shah, N. H., & Abnousi, F. (2020). Artificial intelligence and suicide prevention: A systematic review of machine learning investigations. International Journal of Environmental Research and Public Health, 17(16), 1–25. doi:10.3390/ijerph17165929.
[6] Hawton, K., Hill, N. T. M., Gould, M., John, A., Lascelles, K., & Robinson, J. (2020). Clustering of suicides in children and adolescents. The Lancet Child and Adolescent Health, 4(1), 58–67. doi:10.1016/S2352-4642(19)30335-9.
[7] Kim, H., Son, Y., Lee, H., Kang, J., Hammoodi, A., Choi, Y., Kim, H. J., Lee, H., Fond, G., Boyer, L., Kwon, R., Woo, S., & Yon, D. K. (2024). Machine Learning-Based Prediction of Suicidal Thinking in Adolescents by Derivation and Validation in 3 Independent Worldwide Cohorts: Algorithm Development and Validation Study. Journal of Medical Internet Research, 26(1), 55913. doi:10.2196/55913.
[8] Méndez-Bustos, P., Fuster-Villaseca, J., Lopez-Castroman, J., Jiménez-Solomon, O., Olivari, C., & Baca-Garcia, E. (2022). Longitudinal trajectories of suicidal ideation and attempts in adolescents with psychiatric disorders in Chile: study protocol. BMJ Open, 12(2), 51749. doi:10.1136/bmjopen-2021-051749.
[9] Saduakassova, K., Zhanuzakov, M., Kassenova, G., & Serbin, V. (2024). Artificial Intelligence as a Tool to Prevent Autoaggressive Destructive Behavior among Children and Adolescents: A Brief Overview. Journal of Clinical Medicine of Kazakhstan, 21(6), 24–29. doi:10.23950/jcmk/15716.
[10] Rodway, C., Tham, S.-G., Ibrahim, S., Turnbull, P., Kapur, N., & Appleby, L. (2020). Children and young people who die by suicide: childhood-related antecedents, gender differences and service contact. BJPsych Open, 6(3), 49. doi:10.1192/bjo.2020.33.
[11] Jach, T., Magiera, E., & Froelich, W. (2015). Application of Hadoop to store and process big data gathered from an urban water distribution system. Procedia Engineering, 119(1), 1375–1380. doi:10.1016/j.proeng.2015.08.988.
[12] Lee, J., & Pak, T. Y. (2022). Machine learning prediction of suicidal ideation, planning, and attempt among Korean adults: A population-based study. SSM - Population Health, 19. doi:10.1016/j.ssmph.2022.101231.
[13] Merceedi, K. J., & Sabry, N. A. (2021). A Comprehensive Survey for Hadoop Distributed File System. Asian Journal of Research in Computer Science, 11(2), 46–57. doi:10.9734/ajrcos/2021/v11i230260.
[14] Assefi, M., Behravesh, E., Liu, G., & Tafti, A. P. (2017). Big data machine learning using apache spark MLlib. Proceedings - IEEE International Conference on Big Data, Big Data 2017, 2018-January, 3492–3498. doi:10.1109/BigData.2017.8258338.
[15] Armbrust, M., Xin, R. S., Lian, C., Huai, Y., Liu, D., Bradley, J. K., Meng, X., Kaftan, T., Frankliny, M. J., Ghodsi, A., & Zaharia, M. (2015). Spark SQL: Relational data processing in spark. Proceedings of the ACM SIGMOD International Conference on Management of Data, 2015-May, 1383–1394. doi:10.1145/2723372.2742797.
[16] Gonzalez, J. E., Xin, R. S., Dave, A., Crankshaw, D., Franklin, M. J., & Stoica, I. (2014). GraphX: Graph processing in a distributed dataflow framework. Proceedings of the 11th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2014, 599–613.
[17] Ali, A. A., & Logofatu, D. (2022). An Analysis on Graph-Processing Frameworks: Neo4j and Spark GraphX. IFIP Advances in Information and Communication Technology, 646 IFIP, 461–470. doi:10.1007/978-3-031-08333-4_37.
[18] Bohaterewicz, B., Sobczak, A. M., Podolak, I., Wójcik, B., Mȩtel, D., Chrobak, A. A., Fa̧frowicz, M., Siwek, M., Dudek, D., & Marek, T. (2021). Machine Learning-Based Identification of Suicidal Risk in Patients with Schizophrenia Using Multi-Level Resting-State fMRI Features. Frontiers in Neuroscience, 14, 605697. doi:10.3389/fnins.2020.605697.
[19] Su, C., Aseltine, R., Doshi, R., Chen, K., Rogers, S. C., & Wang, F. (2020). Machine learning for suicide risk prediction in children and adolescents with electronic health records. Translational Psychiatry, 10(1), 413. doi:10.1038/s41398-020-01100-0.
[20] Parsapoor, M., Koudys, J. W., & Ruocco, A. C. (2023). Suicide risk detection using artificial intelligence: the promise of creating a benchmark dataset for research on the detection of suicide risk. Frontiers in Psychiatry, 14. doi:10.3389/fpsyt.2023.1186569.
[21] Khosravi, H., Ahmed, I., & Choudhury, A. (2024). Predicting Suicidal Ideation, Planning, and Attempts among the Adolescent Population of the United States. Healthcare (Switzerland), 12(13), 1262. doi:10.3390/healthcare12131262.
[22] Bekmurat, O., Razaque, A., Khan, M. A., & Amanzholova, S. (2025). Prediction of Suicidal Tendencies in Adolescents Using Machine Learning Models and Artificial Intelligence. 2025 IEEE 1st Secure and Trustworthy Cyberinfrastructure for IoT and Microelectronics, SATC 2025 - Conference Proceedings, 1–5. doi:10.1109/SATC65530.2025.11136830.
[23] Marjit, U., Sharma, K., & Mandal, P. (2015). Data Transfers in Hadoop: A Comparative Study. Open Journal of Big Data, 1(2), 34–46.
[24] Hashem, I. A. T., Anuar, N. B., Gani, A., Yaqoob, I., Xia, F., & Khan, S. U. (2016). MapReduce: Review and open challenges. Scientometrics, 109(1), 389–422. doi:10.1007/s11192-016-1945-y.
[25] Batty, M., Axhausen, K. W., Giannotti, F., Pozdnoukhov, A., Bazzani, A., Wachowicz, M., Ouzounis, G., & Portugali, Y. (2012). Smart cities of the future. European Physical Journal: Special Topics, 214(1), 481–518. doi:10.1140/epjst/e2012-01703-3.
[26] Vitulyova, Y., Babenko, T., Kolesnikova, K., Kiktev, N., & Abramkina, O. (2025). A Hybrid Approach Using Graph Neural Networks and LSTM for Attack Vector Reconstruction. Computers, 14(8), 301. doi:10.3390/computers14080301.
[27] Chen, M., Mao, S., & Liu, Y. (2014). Big data: A survey. Mobile Networks and Applications, 19(2), 171–209. doi:10.1007/s11036-013-0489-0.
[28] Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R., D’Oliveira, R. G. L., Eichner, H., El Rouayheb, S., Evans, D., Gardner, J., Garrett, Z., Gascón, A., Ghazi, B., Gibbons, P. B., … Zhao, S. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1–2), 1–210. doi:10.1561/2200000083.
[29] Loh, H. W., Ooi, C. P., Seoni, S., Barua, P. D., Molinari, F., & Acharya, U. R. (2022). Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011–2022). Computer Methods and Programs in Biomedicine, 226. doi:10.1016/j.cmpb.2022.107161.
[30] Saba Raoof, S., & Durai, M. A. S. (2022). A Comprehensive Review on Smart Health Care: Applications, Paradigms, and Challenges with Case Studies. Contrast Media and Molecular Imaging, 4822235. doi:10.1155/2022/4822235.
[31] Liu, B., Gu, J., & Wang, C. (2024). Research on smart city public health detection system and improvement technology based on intelligent multi-objective. Frontiers in Public Health, 12. doi:10.3389/fpubh.2024.1347586.
[32] Sarinova, A., Bekbayeva, A., Dunayev, P., Sarsikeyev, Y., & Sansyzbay, K. (2021). Hyperspectral Image Compression Algorithms for Phytosanitary Inspection of Agricultural Crops in Aerospace Photography. Journal of Theoretical and Applied Information Technology, 99(24), 6280–6290.
[33] Peponi, A., & Morgado, P. (2020). Smart and regenerative urban growth: A literature network analysis. International Journal of Environmental Research and Public Health, 17(7), 2463. doi:10.3390/ijerph17072463.
[34] Mohammadzadeh, Z., Saeidnia, H. R., Lotfata, A., Hassanzadeh, M., & Ghiasi, N. (2023). Smart city healthcare delivery innovations: a systematic review of essential technologies and indicators for developing nations. BMC Health Services Research, 23(1), 1180. doi:10.1186/s12913-023-10200-8.
[35] Fan, M., Sun, J., Zhou, B., & Chen, M. (2016). The Smart Health Initiative in China: The Case of Wuhan, Hubei Province. Journal of Medical Systems, 40(3), 1–17. doi:10.1007/s10916-015-0416-y.
[36] Alkina, A., Mekhtiyev, A., Neshina, Y., Serikov, T., Madi, P., Sansyzbay, K., & Yurchenko, A. (2022). Studying Additional Losses of Standard G.652 Optical Fiber with Protective Cladding during Multiple Bending To Develop Weight Control Sensor. Journal of Theoretical and Applied Information Technology, 100(7), 1983–1995.
[37] Alnasir, J. J., & Shanahan, H. P. (2018). The application of Hadoop in structural bioinformatics. Briefings in Bioinformatics, 21(1), 96–105. doi:10.1093/bib/bby106.
[38] Chen, Y., Alspaugh, S., & Katz, R. (2012). Interactive analytical processing in big data systems: A crossindustry study of mapreduce workloads. Proceedings of the VLDB Endowment, 5(12), 1802–1813. doi:10.14778/2367502.2367519.
[39] Zaharia, M., Das, T., Li, H., Hunter, T., Shenker, S., & Stoica, I. (2013). Discretized streams: Fault-tolerant streaming computation at scale. SOSP 2013 - Proceedings of the 24th ACM Symposium on Operating Systems Principles, 423–438. doi:10.1145/2517349.2522737.
[40] Essaidi, A., & Bellafkih, M. (2023). A New Big Data Architecture for Analysis: The Challenges on Social Media. International Journal of Advanced Computer Science and Applications, 14(3), 634–639. doi:10.14569/IJACSA.2023.0140373.
[41] Shvachko, K., Kuang, H., Radia, S., & Chansler, R. (2010). The Hadoop distributed file system. 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies, MSST2010, 1-10. doi:10.1109/MSST.2010.5496972.
[42] Bazrafshan, M., & Sayehmiri, K. (2024). Predicting suicidal behavior outcomes: an analysis of key factors and machine learning models. BMC Psychiatry, 24(1), 841. doi:10.1186/s12888-024-06273-2.
[43] Ehtemam, H., Sadeghi Esfahlani, S., Sanaei, A., Ghaemi, M. M., Hajesmaeel-Gohari, S., Rahimisadegh, R., Bahaadinbeigy, K., Ghasemian, F., & Shirvani, H. (2024). Role of machine learning algorithms in suicide risk prediction: a systematic review-meta analysis of clinical studies. BMC Medical Informatics and Decision Making, 24(1), 138. doi:10.1186/s12911-024-02524-0.
[44] Zhu, X. (2021). Sample size calculation for Mann-Whitney U test with five methods. International Journal of Clinical Trials, 8(3), 184. doi:10.18203/2349-3259.ijct20212840.
[45] Aslam, M., & Smarandache, F. (2023). Chi-square test for imprecise data in consistency table. Frontiers in Applied Mathematics and Statistics, 9. doi:10.3389/fams.2023.1279638.
[46] Rashed, A. E. E., Atwa, A. E. M., Ahmed, A., Badawy, M., Elhosseini, M. A., & Bahgat, W. M. (2024). Facial image analysis for automated suicide risk detection with deep neural networks. Artificial Intelligence Review, 57(10), 274. doi:10.1007/s10462-024-10882-4.
[47] Morales, M., Dey, P., Theisen, T., Belitz, D., & Chernova, N. (2019). An Investigation of Deep Learning Systems for Suicide Risk Assessment. Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology, 177–181. doi:10.18653/v1/w19-3023.
[48] Akuma, S., Lubem, T., & Adom, I. T. (2022). Comparing Bag of Words and TF-IDF with different models for hate speech detection from live tweets. International Journal of Information Technology (Singapore), 14(7), 3629–3635. doi:10.1007/s41870-022-01096-4.
[49] Yadav, V., Verma, P., & Katiyar, V. (2023). Long short-term memory (LSTM) model for sentiment analysis in social data for e-commerce products reviews in Hindi languages. International Journal of Information Technology (Singapore), 15(2), 759–772. doi:10.1007/s41870-022-01010-y.
[50] Glenn, C. R., Kleiman, E. M., Kellerman, J., Pollak, O., Cha, C. B., Esposito, E. C., Porter, A. C., Wyman, P. A., & Boatman, A. E. (2020). Annual Research Review: A meta-analytic review of worldwide suicide rates in adolescents. Journal of Child Psychology and Psychiatry and Allied Disciplines, 61(3), 294–308. doi:10.1111/jcpp.13106.
[51] Hughes, J. L., Horowitz, L. M., Ackerman, J. P., Adrian, M. C., Campo, J. V., & Bridge, J. A. (2023). Suicide in young people: screening, risk assessment, and intervention. Bmj, 381, 70630. doi:10.1136/bmj-2022-070630.
[52] Rappai, S., & Ramasamy, G. (2024). Navigating the emotional maze: Understanding Adolescent suicidal ideation using CNN-LSTM model. Intelligent Decision Technologies, 18(3), 1797–1811. doi:10.3233/IDT-240790.
[53] Banik, T., Asgar, S., Hosen, M. H., Uddin, A., Nawar, S., & Saha, A. (2024). From Social Media to Mental Health Insights: A Hybrid CNN-LSTM Model for Depression Detection in Bangladesh. 2024 IEEE Conference on Computing Applications and Systems, COMPAS 2024. doi:10.1109/COMPAS60761.2024.10797102.
[54] Sansyzbay, K. M., Bakhtiyarova, Y. A., Iliev, T., Patokin, G. S., Tasbolatova, L. T., & Sagmedinov, D. B. (2024). Development of an Algorithm for a National Microprocessor-Based Centralization System with a Modular Architecture KZ-MPC-MA Featuring Advanced Intelligent Control Functions. IEEE Access, 12, 193229–193240. doi:10.1109/ACCESS.2024.3521219.
[55] Goel, R., & Digalwar, M. (2024). Suicidal Thought Detection using Max Voting Ensemble Technique. Procedia Computer Science, 235, 2587–2598. doi:10.1016/j.procs.2024.04.244.
[56] Young, J., Bishop, S., Humphrey, C., & Pavlacic, J. M. (2023). A review of natural language processing in the identification of suicidal behavior. Journal of Affective Disorders Reports, 12. doi:10.1016/j.jadr.2023.100507.
[57] Feroze, S. A., Feroze, S. B., & Abbasi, U. (2024). The Unveiling Distress: Harnessing NLP and Deep Learning to Identify Suicidal Signals in Tweets. International Journal of Technology, Innovation and Management, 4(1), 20–31. doi:10.54489/ymy5bp91.
[58] Ji, S. (2022). Towards Intention Understanding in Suicidal Risk Assessment with Natural Language Processing. In Findings of the Association for Computational Linguistics: EMNLP 2022, 4057–4067. EMNLP. doi:10.18653/v1/2022.findings-emnlp.297.
[59] Bialer, A., Izmaylov, D., Segal, A., Tsur, O., Levi-Belz, Y., & Gal, K. (2022). Detecting Suicide Risk in Online Counseling Services: A Study in a Low-Resource Language. Proceedings - International Conference on Computational Linguistics, COLING, 29(1), 4241–4250. doi:10.48550/arXiv.2209.04830.
[60] Cliffe, C., Seyedsalehi, A., Vardavoulia, K., Bittar, A., Velupillai, S., Shetty, H., Schmidt, U., & Dutta, R. (2021). Using natural language processing to extract self-harm and suicidality data from a clinical sample of patients with eating disorders: A retrospective cohort study. BMJ Open, 11(12), e053808. doi:10.1136/bmjopen-2021-053808.
- This work (including HTML and PDF Files) is licensed under a Creative Commons Attribution 4.0 International License.
