A Hybrid Machine Learning – Bayesian Spatial Survival Model of Early Sexual Initiation in Nigeria
DOI:
https://doi.org/10.62054/ijdm/0302.21Abstract
Early sexual initiation remains a major public health concern in Nigeria due to its links with sexually transmitted infections, unintended pregnancies, and unsafe abortions. This study investigated the determinants and spatial distribution of early sexual initiation using a hybrid framework combining machine learning and Bayesian spatial survival modelling. Data were obtained from the 2024 Nigeria Demographic and Health Survey, comprising 39,050 respondents. Time to first sexual intercourse was analysed within a survival framework while accounting for right censoring. A Random Survival Forest model was first used for variable selection, and the selected predictors were incorporated into a Bayesian structured additive spatial Weibull survival model estimated using Integrated Nested Laplace Approximation. Model performance was assessed using the concordance index, AIC, DIC, and WAIC. The hybrid model showed superior predictive performance, with higher time-dependent concordance indices (0.78–0.86) than conventional models. Higher educational attainment and household wealth significantly reduced the hazard of early sexual initiation, whereas urban residence increased risk. A nonlinear age effect showed sharply rising hazards during ages 15–18 years. Spatial analysis revealed higher risks in northern Nigeria and lower risks in southern regions. These findings underscore the need for targeted interventions addressing educational and socioeconomic inequalities in high-risk regions.
References
References (APA 7th Edition)
Adedini, S. A., Odimegwu, C., Imasiku, E. N., & Ononokpono, D. N. (2015). Ethnic differentials in under-five mortality in Nigeria. Ethnicity & Health, 20(2), 145–162. https://doi.org/10.1080/13557858.2014.890013
Akinyemi, A. I., & De Wet, N. (2016). Association between household structure and early sexual debut among adolescents in Nigeria. African Journal of Reproductive Health, 20(3), 94–103.
Besag, J., York, J., & Mollié, A. (1991). Bayesian image restoration, with two applications in spatial statistics. Annals of the Institute of Statistical Mathematics, 43(1), 1–20. https://doi.org/10.1007/BF00116466
Bingenheimer, J. B., & Reed, E. (2014). Risk and protective factors for early sexual initiation among youth in developing countries: A systematic review. Journal of Adolescent Health, 55(3), 291–299. https://doi.org/10.1016/j.jadohealth.2014.01.007
Blangiardo, M., & Cameletti, M. (2015). Spatial and spatio-temporal Bayesian models with R-INLA. Wiley.
Boulesteix, A. L., Janitza, S., Kruppa, J., & König, I. R. (2012). Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2(6), 493–507. https://doi.org/10.1002/widm.1072
Couronné, R., Probst, P., & Boulesteix, A. L. (2018). Random forest versus logistic regression: A large-scale benchmark experiment. BMC Bioinformatics, 19, 270. https://doi.org/10.1186/s12859-018-2264-5
Fahrmeir, L., Kneib, T., Lang, S., & Marx, B. (2013). Regression: Models, methods and applications. Springer.
Harrell, F. E., Lee, K. L., & Mark, D. B. (1996). Multivariable prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Statistics in Medicine, 15(4), 361–387. https://doi.org/10.1002/(SICI)1097- 0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4
Hosmer, D. W., Lemeshow, S., & May, S. (2008). Applied survival analysis: Regression modeling of time-to-event data (2nd ed.). Wiley.
Ishwaran, H., & Kogalur, U. B. (2010). Consistency of random survival forests. Statistics & Probability Letters, 80(13–14), 1056–1064.
Ishwaran, H., Kogalur, U. B., Blackstone, E. H., & Lauer, M. S. (2008). Random survival forests. Annals of Applied Statistics, 2(3), 841–860. https://doi.org/10.1214/08-AOAS169
Kalbfleisch, J. D., & Prentice, R. L. (2002). The statistical analysis of failure time data (2nd ed.). Wiley.
Kassa, G. M., Arowojolu, A. O., Odukogbe, A. A., & Yalew, A. W. (2018). Prevalence and determinants of adolescent pregnancy in Africa: A systematic review and meta-analysis. Reproductive Health, 15, 195. https://doi.org/10.1186/s12978-018-0640-2
Kleinbaum, D. G., & Klein, M. (2012). Survival analysis: A self-learning text (3rd ed.). Springer.
Madise, N. J., Zulu, E. M., & Ciera, J. (2007). Is poverty a driver for risky sexual behaviour? Evidence from national surveys of adolescents in four African countries. African Journal of Reproductive Health, 11(3), 83–98.
Mberu, B. U., & White, M. J. (2011). Internal migration and sexual initiation among never married youths in Nigeria. Social Science & Medicine, 72(8), 1284–1293. https://doi.org/10.1016/j.socscimed.2011.02.012
Mmari, K., & Sabherwal, S. (2013). A review of risk and protective factors for adolescent sexual and reproductive health in developing countries. Journal of Adolescent Health, 52(5), 555–567. https://doi.org/10.1016/j.jadohealth.2012.12.007
Moraga, P. (2023). Spatial statistics for data science: Theory and practice with R. Chapman & Hall/CRC.
National Population Commission (NPC) [Nigeria] & ICF. (2019).
Nigeria demographic and health survey 2024. NPC and ICF.
Nguyen, P. H., Scott, S., Headey, D., Singh, N., & Tran, L. M. (2019). The double burden of malnutrition in India: Trends and inequalities (2006–2016). PLoS ONE, 14(2), e0212218.
Odimegwu, C., & Somefun, O. D. (2017). Ethnicity, gender and risky sexual behaviour among Nigerian youth: An alternative explanation. Reproductive Health, 14, 16.
Pesando, L. M., & Abufhele, A. (2019). Household wealth and adolescent sexual behavior in sub- Saharan Africa. Journal of Biosocial Science, 51(5), 701–718.
Rue, H., & Held, L. (2005). Gaussian Markov random fields: Theory and applications. Chapman & Hall/CRC.
Rue, H., Martino, S., & Chopin, N. (2009). Approximate Bayesian inference for latent Gaussian models using integrated nested Laplace approximations. Journal of the Royal Statistical Society: Series B, 71(2), 319–392. https://doi.org/10.1111/j.1467-9868.2008.00700.x
Sawyer, S. M., Azzopardi, P. S., Wickremarathne, D., & Patton, G. C. (2018). The age of adolescence. The Lancet Child & Adolescent Health, 2(3), 223–228.
Scholes, S., & Bann, D. (2018). Education-related disparities in reported physical activity during leisure-time, active transportation, and work among adults in England. BMC Public Health, 18, 47.
Spiegelhalter, D. J., Best, N. G., Carlin, B. P., & Van Der Linde, A. (2002). Bayesian measures of model complexity and fit. Journal of the Royal Statistical Society: Series B, 64(4), 583–639.
Stephenson, R., Beke, A., & Tshibangu, D. (2006). Community and individual-level influences on adolescent sexual behaviour in sub-Saharan Africa. Studies in Family Planning, 37(2), 91– 110.
UNAIDS. (2022). Global AIDS update 2022. Joint United Nations Programme on HIV/AIDS.
UNFPA. (2022). State of world population report 2022. United Nations Population Fund.
UNICEF. (2021). Adolescent development and participation. United Nations Children’s Fund.
Watanabe, S. (2010). Asymptotic equivalence of Bayes cross validation and widely applicable information criterion. Journal of Machine Learning Research, 11, 3571–3594.
World Bank. (2020). World development report 2020: Trading for development in the age of global value chains. World Bank.
World Health Organization. (2023). Adolescent sexual and reproductive health. WHO.
Yakubu, I., & Salisu, W. J. (2018). Determinants of adolescent pregnancy in sub-Saharan Africa: A systematic review. Reproductive Health, 15, 15. https://doi.org/10.1186/s12978-018-0460-4
Downloads
Published
Data Availability Statement
The study utilized publicly available secondary data from the Nigeria Demographic and Health Survey (NDHS). Ethical approval for the original survey was obtained by the National Population Commission Nigeria and ICF. Permission to use the dataset was obtained through the DHS Program
Issue
Section
License
Copyright (c) 2026 Olopha P. Omoh (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors are solely responsible for obtaining permission to reproduce any copyrighted material contained in the manuscript as submitted. Any instance of possible prior publication in any form must be disclosed at the time the manuscript is submitted and a
copy or link to the publication must be provided.
The Journal articles are open access and are distributed under the terms of the Creative
Commons Attribution-NonCommercial-NoDerivs 4.0 IGO License, which permits use,
distribution, and reproduction in any medium, provided the original work is properly cited.
No modifications or commercial use of the articles are permitted.
