Explainable Machine Learning for Multiclass Classification of Concurrent Child Undernutrition in Ethiopia
DOI:
https://doi.org/10.4108/eetismla.11185Keywords:
supervised machine learning, child anthropometric status, Ethiopia, multiclass classification, concurrent undernutritionAbstract
Child undernutrition remains a major public-health challenge in Ethiopia, often occurring in concurrent forms that are clinically more severe than single deficits. We develop a supervised machine-learning framework to classify children into concurrent nutritional states using World Health Organization anthropometric indicators. Using baseline data from the Young Lives Cohort Study, we model seven observed nutritional categories under substantial class imbalance. Models were evaluated using imbalance-aware metrics, including Macro-F1, Balanced Accuracy, and ROC-AUC. Random Forest achieved the strongest overall performance and provided improved discrimination for concurrent undernutrition cate-gories. Explainability analysis using SHAP highlighted the importance of house-hold and caregiver-related factors. These findings demonstrate the potential of explainable machine-learning approaches for modeling concurrent undernutrition and provide a foundation for future longitudinal and multi-label extensions.
Downloads
References
[1] Fenta, H.M., et al., Determinants of stunting among under-five years children in Ethiopia from the 2016 Ethiopia demographic and Health Survey: Application of ordinal logistic regression model using complex sampling designs. Clinical Epidemiology and Global Health, 2020. 8(2): p. 404–413.
[2] Kasaye, H.K., et al., Poor nutrition for under-five children from poor households in Ethiopia: Evidence from 2016 Demographic and Health Survey. PloS one, 2019. 14(12): p. e0225996.
[3] Kassie, G.W. and D.L. Workie, Determinants of under-nutrition among children under five years of age in Ethiopia. BMC Public Health, 2020. 20: p. 1–11.
[4] Toma, T.M., et al., Factors associated with wasting and stunting among children aged 06–59 months in South Ari District, Southern Ethiopia: a community-based cross-sectional study. BMC nutrition, 2023. 9(1): p. 34.
[5] Woldeamanuel, B.T. and T.T. Tesfaye, Risk factors associated with Under‐Five stunting, wasting, and underweight based on Ethiopian demographic health survey datasets in Tigray Region, Ethiopia. Journal of nutrition and metabolism, 2019. 2019(1): p. 6967170.
[6] Bitew, F.H., C.S. Sparks, and S.H. Nyarko, Machine learning algorithms for predicting undernutrition among under-five children in Ethiopia. Public health nutrition, 2022. 25(2): p. 269–280.
[7] Shahriar, M.M., et al. A Deep Learning Approach to Predict Malnutrition Status of 0-59 Month's Older Children in Bangladesh. in 2019 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT). 2019. IEEE.
[8] Rahman, S.J., et al., Investigate the risk factors of stunting, wasting, and underweight among under-five Bangladeshi children and its prediction based on machine learning approach. Plos one, 2021. 16(6): p. e0253172.
[9] Talukder, A. and B. Ahammed, Machine learning algorithms for predicting malnutrition among under-five children in Bangladesh. Nutrition, 2020. 78: p. 110861.
[10] Kawo, M.A., et al., PREDICTING UNDERNUTRITION RISK FACTORS USING MACHINE LEARNING TECHNIQUES IN NIGERIAN UNDER FIVE CHILDREN. 2024.
[11] Jain, S., et al. Efficient Machine Learning for Malnutrition Prediction among under-five children in India. in 2022 IEEE Delhi Section Conference (DELCON). 2022. IEEE.
[12] Khare, S., et al., Investigation of nutritional status of children based on machine learning techniques using Indian demographic and health survey data. Procedia computer science, 2017. 115: p. 338–349.
[13] Vasu, S.R., et al. Features Explaining Malnutrition in India: A Machine Learning Approach to Demographic and Health Survey Data. in Advanced Computing: 10th International Conference, IACC 2020, Panaji, Goa, India, December 5–6, 2020, Revised Selected Papers, Part I 10. 2021. Springer.
[14] Von Grafenstein, L., Mapping Real-Time Child Malnutrition in India Using Machine Learning. 2023.
[15] Anku, E.K. and H.O. Duah, Predicting and identifying factors associated with undernutrition among children under five years in Ghana using machine learning algorithms. Plos one, 2024. 19(2): p. e0296625.
[16] Fenta, H.M., T. Zewotir, and E.K. Muluneh, A machine learning classifier approach for identifying the determinants of under-five child undernutrition in Ethiopian administrative zones. BMC Medical Informatics and Decision Making, 2021. 21: p. 1–12.
[17] Kebede Kassaw, A., et al., The application of machine learning approaches to determine the predictors of anemia among under five children in Ethiopia. Scientific Reports, 2023. 13(1): p. 22919.
[18] Van, V.T.S., et al., Predicting undernutrition among elementary schoolchildren in the Philippines using machine learning algorithms. Nutrition, 2022. 96: p. 111571.
[19] Shen, H., H. Zhao, and Y. Jiang, Machine learning algorithms for predicting stunting among under-five children in Papua New Guinea. Children, 2023. 10(10): p. 1638.
[20] Chilyabanyama, O.N., et al., Performance of machine learning classifiers in classifying stunting among under-five children in Zambia. Children, 2022. 9(7): p. 1082.
[21] Khan, J.R., J.H. Tomal, and E. Raheem, Model and variable selection using machine learning methods with applications to childhood stunting in Bangladesh. Informatics for Health and Social Care, 2021. 46(4): p. 425–442.
[22] Ndagijimana, S., et al., Prediction of stunting among under-5 children in Rwanda using machine learning techniques. Journal of Preventive Medicine and Public Health, 2023. 56(1): p. 41.
[23] Begum, N., M.M. Rahman, and M. Omar Faruk, Machine learning prediction of nutritional status among pregnant women in Bangladesh: Evidence from Bangladesh demographic and health survey 2017–18. Plos one, 2024. 19(5): p. e0304389.
[24] Oxford, A Guide to Young Lives Research. , Y. Lives, Editor. 2017.
[25] Begashaw, G.B., T. Zewotir, and H.M. Fenta, Multistate Markov chain modeling for child undernutrition transitions in Ethiopia: a longitudinal data analysis, 2002–2016. BMC Medical Research Methodology, 2024. 24(1): p. 283.
[26] Genuer, R., J.-M. Poggi, and C. Tuleau-Malot, Variable selection using random forests. Pattern recognition letters, 2010. 31(14): p. 2225–2236.
[27] Janitza, S., G. Tutz, and A.-L. Boulesteix, Random forest for ordinal responses: prediction and variable selection. Computational Statistics & Data Analysis, 2016. 96: p. 57–73.
[28] Rodriguez-Galiano, V.F., et al., An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS journal of photogrammetry and remote sensing, 2012. 67: p. 93–104.
[29] Breiman, L., Random forests. Machine learning, 2001. 45: p. 5–32.
[30] Fenta, H.M., et al., Factors of acute respiratory infection among under-five children across sub-Saharan African countries using machine learning approaches. Scientific Reports, 2024. 14(1): p. 15801.
[31] Yuliansyah, H., et al., Comparison and analysis of classification algorithm performance for nutritional status data. International Journal of Computer Applications, 2020. 176(20): p. 14–20.
[32] Khudri, M.M., et al., Predicting nutritional status for women of childbearing age from their economic, health, and demographic features: A supervised machine learning approach. PloS one, 2023. 18(5): p. e0277738.
[33] Fatmawati, M., B.A. Herlambang, and N.Q. Nada, Random Forest Algorithm for Toddler Nutritional Status Classification Website. Journal of Applied Informatics and Computing, 2024. 8(2): p. 428–433.
[34] Selemani, B., D. Machuve, and N. Mduma, Machine learning model for predicting fetal nutritional status. Computational Ecology and Software, 2024. 14(1): p. 68.
[35] Turjo, E.A. and M.H. Rahman, Assessing risk factors for malnutrition among women in Bangladesh and forecasting malnutrition using machine learning approaches. BMC nutrition, 2024. 10(1): p. 22.
[36] Begashaw, G.B., T. Zewotir, and H.M. Fenta, A deep learning approach for classifying and predicting children's nutritional status in Ethiopia using LSTM-FC neural networks. BioData Mining, 2025. 18(1): p. 11.
[37] Begashaw, G.B., T. Zewotir, and H.M. Fenta, Dynamic Bayesian network modeling for longitudinal data on child undernutrition in Ethiopia (2002–2016). Frontiers in Public Health, 2024. 12: p. 1399094.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Getnet Begashaw, Temesgen Zewotir, Haile Fenta, Mulu Asmamaw, Abebe Legass
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
