Socioeconomic, Nutritional, and Demographic Determinants of Anaemia among Nigerian Women: A Machine Learning Analysis of DHS 2024 Data

Anaemia remains a serious public health problem among women of reproductive age in Nigeria, with significant implications for maternal and population health. This study examined the prevalence, determinants, and predictability of anaemia using descriptive statistics, inferential analyses, and supervised machine-learning models on the data from the 2023–2024 Nigeria Demographic and Health Survey (NDHS). Anaemia status was defined using World Health Organisation haemoglobin thresholds. The results indicate an alarming 78% prevalence of anaemia among Nigerian women across geographic, socioeconomic, and educational strata. Nutritional status, particularly body mass index, together with reproductive factors and contextual characteristics, emerged as the most influential predictors of anaemia. The study highlights the value of combining epidemiological analysis with interpretable machine learning to inform targeted strategies for anaemia prevention and control in Nigeria.

Anaemia; Women of reproductive age; Nigeria Demographic and Health Survey

1. AbioyeA.A., Owopetu C.A., Adamu-Adedipe F.A., Odesanya L.O., and Olofin-Samuel M.A (2024) Anaemia Prevention Among Pregnant Women, International Journal of Nursing, Midwife and Health Related Cases, 10 (2), 1-11 [Google Scholar] [Crossref]

2. Aboagye, R. G., Okyere, J., Seidu, A. A., Ahinkorah, B. O., Budu, E., & Yaya, S. (2023). Relationship between history of hormonal contraceptive use and anaemia status among women in sub-Saharan Africa: A large population-based study. Plos one, 18(6), e0286392. [Google Scholar] [Crossref]

3. Abubakar, H. A., Shahril, M. R., & Mat, S. (2024). Nutritional status and dietary intake among Nigerian adolescent: a systematic review. BMC Public Health, 24(1), 1764. [Google Scholar] [Crossref]

4. Aigbedion, G., Tseng, P. C., & Puthussery, S. (2025). Micronutrient deficiencies and determinants among pregnant women and children in Nigeria: systematic review and meta-analysis. Nutrients, 17(14), 2338. [Google Scholar] [Crossref]

5. Babah, O. A., Sagastume, D., Akinajo, O. R., Scarpa, G., Hanson, C., Larsson, E. C., ... & Beňová, L. (2025). Dietary diversity insufficiently explains differences in prevalence of anaemia in pregnancy across regions in Nigeria: A secondary analysis of Demographic and Health Survey 2018. PLOS Global Public Health, 5(5), e0004540. [Google Scholar] [Crossref]

6. Bello, M., Olarewaju, C. A., & Ayoola, J. I. (2025). Effect of food cultural beliefs on the dietary pattern and food practices of children in Ondo West local area of Ondo state. [Google Scholar] [Crossref]

7. Çetin, V., & Yıldız, O. (2022). A comprehensive review on data preprocessing techniques in data analysis. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 28(2), 299-312. [Google Scholar] [Crossref]

8. Foster, S. D., Lawrence, E., & Hoskins, A. J. (2024). Spatially Clustered Survey Designs. Journal of Agricultural, Biological and Environmental Statistics, 29(1), 130-146. [Google Scholar] [Crossref]

9. Gunarathna, S.P., Wickramasinghe, N.D., Agampodi, T.C., Prasanna, I.R. and Agampodi, S.B., 2024. Assessment of the productivity loss due to leading maternal ill-health conditions: a follow-up study of a prospective pregnancy cohort in rural Sri Lanka. BMJ open, 14(10), p.e082798. [Google Scholar] [Crossref]

10. ICF International (2024) Nigeria Demographic and Health Survey 2023–2024: Key Indicators Report. Rockville, MD: ICF. Available at: https://dhsprogram.com [Google Scholar] [Crossref]

11. Khan, A., Ali, A., Khan, J., Ullah, F., & Faheem, M. (2025). Using Permutation-Based Feature Importance for Improved Machine Learning Model Performance at Reduced Costs. IEEE Access. [Google Scholar] [Crossref]

12. Kinyoki, D., Osgood-Zimmerman, A. E., Bhattacharjee, N. V., Kassebaum, N. J., & Hay, S. I. (2021). Anemia prevalence in women of reproductive age in low-and middle-income countries between 2000 and 2018. Nature medicine, 27(10), 1761-1782. [Google Scholar] [Crossref]

13. Kitaw, B., Asefa, C., & Legese, F. (2024). Leveraging machine learning models for anemia severity detection among pregnant women following ANC: Ethiopian context. BMC public health, 24(1), 3500. https://doi.org/10.1186/s12889-024-21039-x [Google Scholar] [Crossref]

14. Molnar, Christoph, Gunnar König, Bernd Bischl, and Giuseppe Casalicchio. "Model-agnostic feature importance and effects with dependent features: a conditional subgroup approach." Data Mining and Knowledge Discovery 38, no. 5 (2024): 2903-2941. [Google Scholar] [Crossref]

15. National Population Commission (NPC) [Nigeria] and ICF (2024) Nigeria Demographic and Health Survey 2023–2024 Final Report. Abuja and Rockville, MD: NPC and ICF. [Google Scholar] [Crossref]

16. Nigeria Demography and Health Survey, (2024). [Google Scholar] [Crossref]

17. Obeagu, E. I., & Agreen, F. C. (2023). Anaemia among pregnant women: A review of African pregnant teenagers. [Google Scholar] [Crossref]

18. Obi, J. C. (2023). A comparative study of several classification metrics and their performances on data. World Journal of Advanced Engineering Technology and Sciences, 8(1), 308-314. [Google Scholar] [Crossref]

19. Ogbuju, N. E., Anoke, U. R., Olaiya, P. A., Wakama, T., Okoro, L. C., Elebesunu, E. C., ... & Jeremiah, Z. A. (2025). Management of Anaemia during Pregnancy: Insights into Pathophysiology and Public Health Implications in Sub-Saharan Africa. African Journal of Laboratory Haematology and Transfusion Science, 4(1), 58-68. [Google Scholar] [Crossref]

20. Ogunsakin, R. E., Akinyemi, O., Babalola, B. T., & Adetoro, G. (2021). Spatial pattern and determinants of anemia among women of childbearing age in Nigeria. Spatial and Spatio-temporal Epidemiology, 36, 100396. [Google Scholar] [Crossref]

21. Ren, Y., Wu, D., Tong, Y., López-DeFede, A., & Gareau, S. (2023). Issue of data imbalance on low birthweight baby outcomes prediction and associated risk factors identification: establishment of benchmarking key machine learning models with data rebalancing strategies. Journal of medical Internet research, 25, e44081. [Google Scholar] [Crossref]

22. Sanni, S. M. (2025). Nutrition Transition in West Africa: Public Health Challenges, Socioeconomic Impacts, And Regional Policy Interventions. Center of Medicine, 1(1). [Google Scholar] [Crossref]

23. Shatilwe, J. T., Kuupiel, D., & Mashamba-Thompson, T. P. (2021). Evidence on access to healthcare information by women of reproductive age in low-and middle-income countries: scoping review. Plos one, 16(6), e0251633. [Google Scholar] [Crossref]

24. Tilahun, W. M., Gebreegziabher, Z. A., Geremew, H., & Simegn, M. B. (2024). Prevalence and factors associated with anemia among HIV-infected women in sub-saharan Africa: a multilevel analysis of 18 countries. BMC Public Health, 24(1), 2236. [Google Scholar] [Crossref]

25. Tirore, L. L., Areba, A. S., Tamrat, H., Habte, A., & Abame, D. E. (2024). Determinants of severity levels of anemia among pregnant women in Sub-Saharan Africa: multilevel analysis. Frontiers in Global Women's Health, 5, 1367426. [Google Scholar] [Crossref]

26. Wallace, S. M. (2020). Factors affecting dietary intake, dietary change, nutritional status and appetite [Google Scholar] [Crossref]

27. Worku, M. G., Alamneh, T. S., Teshale, A. B., Yeshaw, Y., Alem, A. Z., Ayalew, H. G., ... & Tesema, G. A. (2022). Multilevel analysis of determinants of anemia among young women (15-24) in sub-Sahara Africa. Plos one, 17(5), e0268129. [Google Scholar] [Crossref]

28. World Health Organization (WHO) (2023) Anaemia in Women and Children: Global Estimates and Trends 2000–2022. Geneva: WHO. Available at: https://www.who.int [Google Scholar] [Crossref]

29. Zafar, M. R., & Khan, N. (2021). Deterministic local interpretable model-agnostic explanations for stable explainability. Machine Learning and Knowledge Extraction, 3(3), 525-541. [Google Scholar] [Crossref]

30. Zemariam, A. B., Yimer, A., Abebe, G. K., Wondie, W. T., Abate, B. B., Alamaw, A. W., ... & Ngusie, H. S. (2024). Employing supervised machine learning algorithms for classification and prediction of anemia among youth girls in Ethiopia. Scientific reports, 14(1), 9080. [Google Scholar] [Crossref]

• Tribal Child Nutrition and Health in District of Sundargarh: A Public Health Review of ICDS Intervention
• Knowledge, Attitudes and Practices Towards Prostate Cancer Screening Amongst Men Aged 40-60 Years in The Buea Health District: A Cross-Sectional Study
• Compliance with JCI Protocols: A Focus on Employee Safety
• Influence and Involvement of Teachers in Menstrual Hygiene Management of Female Secondary School Students in Kogi State, Nigeria
• A Critical Evaluation of Ayushman Bharat Pradhan Mantri Jan Arogya Yojana in Bihar