Abstract
Adolescent depression is a significant public health concern in low- and middle-income countries, including Kenya, where limited screening capacity contributes to under diagnosis. This study developed and validated a Bayesian Neural Network for predicting depression risk among adolescents, leveraging probabilistic inference to capture predictive uncertainty and complex nonlinear relationships. Secondary data for 2,192 adolescents aged 12-18 years were obtained from the Open Science Framework, incorporating psychosocial, demographic, and mental health measures. Significant predictors were identified using chi-square tests and point-biserial correlations, followed by forward feature selection. The proposed Bayesian Neural Network employed a three-hidden-layer feedforward architecture with ReLU and sigmoid activations, Gaussian priors on weights, and Bayes-by-Backprop Variational inference. Model performance was benchmarked against a Random Forest classifier using cross-validation. Results indicate that anxiety, loneliness, perceived social support, gratitude, positive youth development, academic self-perception, gender, academic form, financial status, parental education, and age are significant predictors of depression. The model achieved superior performance, with an accuracy of 80.13%, F1 score of 0.876, recall of 0.965, ROC-AUC of 0.813, and PR-AUC of 0.913, outperforming the Random Forest in most metrics except precision. Calibration analysis yielded a low Brier score (0.0693), indicating well-calibrated probabilistic predictions. These findings demonstrate the suitability of Bayesian Neural Networks for adolescent depression risk screening in resource-constrained settings, where uncertainty-aware decision support is critical.
References
Anderson, S. F., Salk, R. H., & Hyde, J. S. (2015). Stress in romantic relationships and adolescent depressive symptoms: Influence of parental support. Journal of Family Psychology, 29(3), 339.
Bandeira, M., Graham, M. A., & Ebersöhn, L. (2023). The significance of feeling safe for resilience of adolescents in sub-Saharan Africa. Frontiers in Psychology, 14, 1183748.
Barendse, M. E. A., Cosme, D., Flournoy, J. C., Vijayakumar, N., Cheng, T. W., Allen, N. B., & Pfeifer, J. H. (2023). Neural correlates of adolescent stress and mental health. Nature Reviews Psychology, 2(6), 370–384.
Blundell, C., Cornebise, J., Kavukcuoglu, K., & Wierstra, D. (2015). Weight uncertainty in neural network. In International Conference on Machine Learning (pp. 1613–1622).
Buntine, W. L. (1994). Operations for learning with graphical models. Journal of Artificial Intelligence Research, 2, 159–225.
Cai, H., Xie, X.-M., Zhang, Q., Cui, X., Lin, J.-X., Sim, K., Ungvari, G. S., Zhang, L., & Xiang, Y.-T. (2021). Prevalence of suicidality in major depressive disorder: A systematic review and meta-analysis of comparative studies. Frontiers in Psychiatry, 12, 690130. https://doi.org/10.3389/fpsyt.2021.690130
Dobson, E. T., Croarkin, P. E., Schroeder, H. K., Varney, S. T., Mossman, S. A., Cecil, K., & Strawn, J. R. (2021). Bridging anxiety and depression: A network approach in anxious adolescents. Journal of Affective Disorders, 280, 305–314.
Evans, D., Borriello, G. A., & Field, A. P. (2018). A review of the academic and psychological impact of the transition to secondary education. Frontiers in Psychology, 9, 391751.
Fara, S., Hickey, O., Georgescu, A., Goria, S., Molimpakis, E., & Cummins, N. (2022). Bayesian networks for the robust and unbiased prediction of depression and its symptoms utilizing speech and multimodal data. arXiv preprint arXiv:2211.04924.
Hankin, B. L. (2015). Depression from childhood through adolescence: Risk mechanisms across multiple systems and levels of analysis. Current Opinion in Psychology, 4, 13–20.
Heek, J., & Kalchbrenner, N. (2019). Bayesian inference for large scale image classification. arXiv preprint arXiv:1908.03491.
Jospin, L. V., Laga, H., Boussaid, F., Buntine, W., & Bennamoun, M. (2022). Hands-on Bayesian neural networks—A tutorial for deep learning users. IEEE Computational Intelligence Magazine, 17(2), 29–48.
Lin, F.-G., Chou, Y.-C., Wu, C.-H., & Lin, J.-D. (2014). Short-term and long-term influences of family arguments and gender difference on developing psychological well-being in Taiwanese adolescents. Research in Developmental Disabilities, 35(11), 2735–2743.
McElroy, E., Fearon, P., Belsky, J., Fonagy, P., & Patalay, P. (2018). Networks of depression and anxiety symptoms across development. Journal of the American Academy of Child & Adolescent Psychiatry, 57(12), 964–973.
Myers, B., Bantjes, J., Lochner, C., Mortier, P., Kessler, R. C., & Stein, D. J. (2021). Prevalence, correlates, and predictors of adolescent depression in LMICs. Journal of Adolescent Health, 69(3), 413–422.
Putwain, D. W., Symes, W., & Remedios, R. (2023). Academic self-concept, stress, and adolescent mental health. Educational Psychology Review, 35, 57.
Shridhar, K., Laumann, F., & Liwicki, M. (2018). Uncertainty estimations by softplus normalization in Bayesian convolutional neural networks with variational inference. arXiv preprint arXiv:1806.05978.
Silvestro, D., & Andermann, T. (2020). Prior choice affects ability of Bayesian neural networks to identify unknowns. arXiv preprint arXiv:2005.04987.
Sodi, T., Quarshie, E. N.-B., Oppong Asante, K., et al. (2022). Mental health literacy of school-going adolescents in sub-Saharan Africa: A regional systematic review protocol. BMJ Open, 12, e063687.
Thapar, A., Eyre, O., Patel, V., & Brent, D. (2022). Depression in young people. The Lancet, 400(10352), 617–631.
Vreeman, R. C., McCoy, B. M., & Lee, S. (2017). Mental health challenges among adolescents living with HIV. Journal of the International AIDS Society, 20, 21497.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 Edwin Kagereki, Thomas Mageto, Anthony Wanjoya