Academic Journal
An ensemble machine learning approach for predicting anemia among under-five children in malaria-endemic sub-Saharan African countries.
| Title: | An ensemble machine learning approach for predicting anemia among under-five children in malaria-endemic sub-Saharan African countries. |
|---|---|
| Authors: | Tekeba B; Department of Pediatrics and Child Health Nursing, School of Nursing, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia. berishboss7@gmail.com., Baykemagn ND; Department of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia., Mengesha AT; Department of Information Science, College of Informatics, University of Gondar, Gondar, Ethiopia., Mengstie MA; Department of Information Science, College of Informatics, University of Gondar, Gondar, Ethiopia. |
| Source: | Infectious diseases of poverty [Infect Dis Poverty] 2026 Jul 13; Vol. 15 (1). Date of Electronic Publication: 2026 Jul 13. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: BioMed Central Country of Publication: England NLM ID: 101606645 Publication Model: Electronic Cited Medium: Internet ISSN: 2049-9957 (Electronic) Linking ISSN: 20499957 NLM ISO Abbreviation: Infect Dis Poverty Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central, 2012- |
| MeSH Terms: | Anemia*/epidemiology , Anemia*/diagnosis , Anemia*/etiology , Malaria*/epidemiology , Malaria*/complications , Boosting Machine Learning Algorithms*, Africa South of the Sahara/epidemiology ; Child, Preschool ; Female ; Humans ; Infant ; Male ; Classification Algorithms ; Cross-Sectional Studies ; Predictive Learning Models ; Random Forest |
| Abstract: | Background: Worldwide, anemia in children under-five is a major public health issue, particularly in sub-Saharan Africa. Sub-Saharan Africa also has the highest burden of malaria. This study aimed to develop an ensemble machine learning model to estimate anemia burden and potential predictors in under-five children in malaria-endemic sub-Saharan African countries. Method: A cross-sectional study was conducted using Demographic and Health Survey data from sub-Saharan African countries. Samples were selected through a two-stage stratified cluster sampling method. Data analysis was performed using Python 3.8, with a total weighted sample of 21,249. The dataset was split into 80% for training and 20% for testing and validation purposes. To address class imbalance, a hybrid data balancing approach combining SMOTE (Synthetic Minority Over-sampling Technique) and Tomek Links was applied. Four machine learning algorithms were developed and evaluated using standard performance metrics. Recursive Feature Elimination with a Random Forest classifier was used to identify potential predictors of anemia among children under five living in malaria-endemic SSA countries. Result: In this study, XGBoost showed the best performance, achieving an accuracy of 83.69%, a precision of 85.81%, and an F1 score of 83.19%. Additionally, XGBoost attained the highest ROC AUC of 90.1 and Precision Recall AUC of 90.0. According to Recursive Feature Elimination with a Random Forest classifier, region, birth order, child age, wealth index, and number of mosquito nets were identified as the associated factors of anemia among under-five children in malaria-endemic SSA countries. Conclusion: To reduce anemia among under-five children in malaria-endemic regions of sub-Saharan Africa, interventions should prioritize implementing geographically targeted programs, focus on younger children and those with high birth orders by integrating anemia screening into routine check-ups. In addition, enhancing economic support for low-income families and distributing and educating families on the proper use of mosquito nets are essential. (© 2026. The Author(s).) |
| Competing Interests: | Declarations. Ethics approval and consent to participate: This study is a secondary analysis of data from the Demographic and Health Surveys Program, which obtained ethical approval before data collection. The analysis used publicly available, anonymized, and de-identified data, selecting only variables and records relevant to the study. Access to the datasets was granted following the submission and approval of a formal data request. As the data contain no personal identifiers, no additional ethical approval was required for this analysis. All data were kept confidential and handled in an anonymous manner. According to the DHS Program, all participant information was anonymized during survey collection. More details regarding DHS data and ethical standards are available online at http://www.dhsprogram.com . Human ethics and consent to participate: The study was conducted under the principles of the Declaration of Helsinki and the International Ethical Guidelines. No patient was involved in developing the research question, outcome measure, or design of the study. The public was also not involved in the design, conduct, or choice of our outcome measures and recruitments for the study. The public and patients were not involved in the dissemination of the research. The ethical approval committee, or Institutional Review Board, was not necessary for this study, as the study utilized publicly available secondary data. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests. |
| References: | Pediatrics. 2010 Jul;126(1):e140-9. (PMID: 20547647) Am J Trop Med Hyg. 2001 Jan-Feb;64(1-2 Suppl):57-67. (PMID: 11425178) PLoS One. 2020 Oct 6;15(10):e0239409. (PMID: 33021981) Sci Rep. 2019 Nov 12;9(1):16540. (PMID: 31719548) BMJ Glob Health. 2023 Jan;8(1):. (PMID: 36653068) Anemia. 2011;2011:260380. (PMID: 21738863) J Infect Dis. 2006 Jul 1;194(1):108-14. (PMID: 16741889) PLoS One. 2020 Jan 30;15(1):e0228258. (PMID: 31999737) Med Microbiol Immunol. 2012 Nov;201(4):593-8. (PMID: 22965173) PLoS One. 2024 Apr 11;19(4):e0300172. (PMID: 38603735) Hematology Am Soc Hematol Educ Program. 2009;:87-93. (PMID: 20008186) Ethiop J Health Sci. 2019 Sep;29(5):613-622. (PMID: 31666783) Malar J. 2023 Jun 26;22(1):196. (PMID: 37365602) PLoS One. 2021 Apr 23;16(4):e0249978. (PMID: 33891603) Parasitol Res. 2007 Nov;101(6):1463-9. (PMID: 17874326) Pediatric Health Med Ther. 2021 Mar 29;12:161-175. (PMID: 33824615) Anemia. 2018 Jun 03;2018:3087354. (PMID: 29973986) Sci Rep. 2023 Dec 21;13(1):22919. (PMID: 38129535) SAGE Open Nurs. 2026 Feb 25;12:23779608251408899. (PMID: 41767848) PLoS Med. 2011 Dec;8(12):e1001142. (PMID: 22205883) Health Sci Rep. 2023 Oct 22;6(10):e1643. (PMID: 37916141) Front Parasitol. 2024 Aug 01;3:1438218. (PMID: 39817171) J Nutr. 2001 Feb;131(2S-2):697S-700S; discussion 700S-701S. (PMID: 11160600) BMC Pediatr. 2016 Jan 11;16:3. (PMID: 26754288) Epidemiol Infect. 2009 May;137(5):654-61. (PMID: 18840319) Afr J Reprod Health. 2013 Sep;17(3):110-8. (PMID: 24069773) Nutr J. 2013 May 28;12:69. (PMID: 23714275) Prev Med. 1999 Sep;29(3):152-6. (PMID: 10479602) Lancet. 2011 Dec 17;378(9809):2123-35. (PMID: 21813172) Blood. 2014 Jan 30;123(5):615-24. (PMID: 24297872) Int J Environ Res Public Health. 2017 Jun 17;14(6):. (PMID: 28629151) PLoS One. 2022 May 9;17(5):e0268129. (PMID: 35533194) |
| Contributed Indexing: | Keywords: Anemia; Machine-learning; Malaria; Malaria endemic; Predictors; Sub-Saharan Africa |
| Entry Date(s): | Date Created: 20260712 Date Completed: 20260712 Latest Revision: 20260813 |
| Update Code: | 20260814 |
| PubMed Central ID: | PMC13360475 |
| DOI: | 10.1186/s40249-026-01461-6 |
| PMID: | 42437942 |
| Database: | MEDLINE |
| ISSN: | 2049-9957 |
|---|---|
| DOI: | 10.1186/s40249-026-01461-6 |