Peer-reviewed article
Predicting childhood anaemia in Ghana with explainable machine learning: A national survey analysis.
Hassan YSA, Omar MA, Karikari JK, Ali AS, Ahmed MM ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001Childhood anaemia affects nearly half of children aged 6-59 months in Ghana, with significant differences between regions and wealth levels. Researchers used machine learning models trained on data from nearly 3,400 children to predict which children are most at risk of anaemia. The best-performing models identified child age, malaria infection, maternal anaemia, region, and household wealth as the strongest predictors. While the models showed moderate ability to identify anaemic children, they missed 28-30% of cases, which should be considered when using them for public health screening.
Key points
- Weighted prevalence of childhood anaemia in Ghana is 48.95% among children aged 6-59 months
- Gradient boosting model achieved best discrimination (AUC = 0.72) but sensitivity of support vector machine and logistic regression (71-73%) means 28-30% of anaemic children would be missed
- Child age, malaria status, maternal anaemia, region, and household wealth were identified as the strongest predictors across models
- Marked regional and socioeconomic disparities in childhood anaemia exist in Ghana
- Study recommends targeted interventions integrating malaria control with nutrition and maternal-child health programmes in high-risk groups
Limitations
This is a predictive modelling study that identifies risk factors but does not evaluate any intervention for reducing anaemia. The moderate predictive performance and high miss-rate means these models cannot yet be reliably applied as standalone screening tools in practice.
Abstract
Introduction Childhood anaemia remains a major public health problem in Ghana, with marked regional and socioeconomic disparities. Conventional regression may not fully capture complex, non-linear relationships among biological, maternal, and household factors. We used supervised machine learning to predict anaemia among children aged 6-59 months using nationally representative survey data. Methods We analysed the 2022 Ghana Demographic and Health Survey, including de facto children aged 6-59 months with valid haemoglobin and complete covariates (weighted N = 3,382). Anaemia was defined as altitude-adjusted haemoglobin <11.0 g/dL. Twenty-one predictors were included. Data were split into training (80%) and testing (20%) sets using stratified sampling. Six models (logistic regression, decision tree, random forest, gradient boosting, support vector machine, and artificial neural network) were tuned via grid search with 10-fold cross-validation. Results The weighted prevalence of childhood anaemia was 48.95% (n = 1,655). Gradient boosting showed the best overall discrimination (AUC = 0.72; F1 = 68.99%; accuracy = 66.27%). Support vector machine and logistic regression achieved the highest sensitivity (recall = 72.73% and 71.74%). Random forest showed overfitting (100% training accuracy; test accuracy = 65.23%). Decision tree and neural network performed poorly (AUC = 0.57 and 0.63). Key predictors across models and SHAP were child age, malaria status, maternal anaemia, region, and household wealth (with feature rankings varying by algorithm). Conclusion Machine learning models achieved moderate predictive performance for childhood anaemia in Ghana. Gradient boosting provided the strongest discrimination, while support vector machine and logistic regression offered higher sensitivity for screening. However, these sensitivities imply that approximately 28-30% of anaemic children may be missed, which should be considered when applying these models in public health screening. Identified determinants support targeted, malaria-integrated nutrition and maternal-child interventions in high-risk groups.