Early malaria risk screening in Nigerian minors using AutoML and cluster-based analysis of non-clinical survey data
- 1Department of Industrial and Production Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, Bangladesh
Abstract
Malaria remains a major public health challenge in sub-Saharan Africa, with Nigeria accounting for a substantial proportion of the global malaria burden, particularly among children under five years of age. Although rapid diagnostic tests (RDTs) enable timely screening, false-negative results and delays in confirmatory microscopy can hinder early treatment in resource-limited settings. This study developed and evaluated an automated machine learning (AutoML)-based framework for early malaria risk prediction using demographic, household, and socioeconomic data from the nationally representative Nigeria Malaria Indicator Survey (MIS) 2021. Initially, 43 candidate variables were selected and subsequently reduced to 13 statistically significant predictors through preprocessing and statistical dependency testing. Five machine learning models, namely Logistic Regression (LR), Decision Tree (DT), Support Vector Classifier (SVC), Extreme Gradient Boosting (XGBoost), and H2O AutoML, were developed and evaluated using stratified train–test splitting and 10-fold cross-validation. To reduce the influence of regional information, Agglomerative Hierarchical Clustering (AHC) was performed using the eight most important predictors after excluding regional identifiers, yielding two optimal population subgroups (Silhouette Score = 0.3939). For the overall dataset, H2O AutoML Generalized Linear Model (GLM) achieved the highest F2-score (79.38%) with a recall of 83.08%, whereas XGBoost achieved the highest test accuracy (75.54%). Cluster-specific analyses demonstrated that H2O GLM provided the best recall-oriented performance in Cluster 1 (F2-score = 83.31%), while XGBoost performed best in Cluster 2 (F2-score = 83.25%). These findings demonstrate that H2O AutoML provides a robust and automated framework for malaria risk prediction, while cluster-specific modeling further improves predictive performance by accounting for population heterogeneity. The proposed framework has the potential to support early malaria risk assessment and complement conventional diagnostic strategies in resource-limited public health settings. Author summary: Effective malaria control depends on the timely identification of children at risk so that appropriate treatment can be initiated before severe disease develops. In Nigeria, rapid diagnostic tests may produce false-negative results, while delays in confirmatory laboratory testing can hinder timely clinical decision-making, particularly in resource-limited settings. In this study, we developed an automated machine learning framework using routinely available demographic, household, and socioeconomic information from the 2021 Nigeria Malaria Indicator Survey to support early malaria risk prediction. To reduce the influence of regional information on model development, agglomerative hierarchical clustering was performed after excluding regional identifiers, enabling the identification of population subgroups with distinct risk profiles. H2O AutoML demonstrated strong recall-oriented performance and produced competitive predictive models across both the overall population and cluster-specific analyses. These findings suggest that combining non-clinical data, automated machine learning, and subgroup-specific modeling can support scalable and more targeted malaria risk assessment, complementing existing diagnostic strategies in resource-limited settings.
Related
- Cluster-Based Dimensionality Reduction by Nonparametric Distributional Screening
- Strong isometric path complexity of graphs: Asymptotic minors, restricted holes, and graph operations
- Prime and Cohen-Macaulay ideals of 2-minors with linear resolution
- Ideals of 2-minors of nearly determinantal matrices
- Extremal function for rooted K5 minors
BibTeX
@article{khan2026early,
title = {{Early malaria risk screening in Nigerian minors using AutoML and cluster-based analysis of non-clinical survey data}},
author = {Ashiqur Rahman Khan and Nafisa Mahbub and Ridwan Al Aziz and Mahamudul Hassan Siddique and Zahidul Islam Sayeem},
journal = {PLOS Digital Health},
year = {2026},
month = sep,
doi = {10.1371/journal.pdig.0001736},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001736},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Early malaria risk screening in Nigerian minors using AutoML and cluster-based analysis of non-clinical survey data
AU - Ashiqur Rahman Khan
AU - Nafisa Mahbub
AU - Ridwan Al Aziz
AU - Mahamudul Hassan Siddique
AU - Zahidul Islam Sayeem
PY - 2026
DA - 2026/09/23
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0001736
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001736
AB - Malaria remains a major public health challenge in sub-Saharan Africa, with Nigeria accounting for a substantial proportion of the global malaria burden, particularly among children under five years of age. Although rapid diagnostic tests (RDTs) enable timely screening, false-negative results and delays in confirmatory microscopy can hinder early treatment in resource-limited settings. This study developed and evaluated an automated machine learning (AutoML)-based framework for early malaria risk prediction using demographic, household, and socioeconomic data from the nationally representative Nigeria Malaria Indicator Survey (MIS) 2021. Initially, 43 candidate variables were selected and subsequently reduced to 13 statistically significant predictors through preprocessing and statistical dependency testing. Five machine learning models, namely Logistic Regression (LR), Decision Tree (DT), Support Vector Classifier (SVC), Extreme Gradient Boosting (XGBoost), and H2O AutoML, were developed and evaluated using stratified train–test splitting and 10-fold cross-validation. To reduce the influence of regional information, Agglomerative Hierarchical Clustering (AHC) was performed using the eight most important predictors after excluding regional identifiers, yielding two optimal population subgroups (Silhouette Score = 0.3939). For the overall dataset, H2O AutoML Generalized Linear Model (GLM) achieved the highest F2-score (79.38%) with a recall of 83.08%, whereas XGBoost achieved the highest test accuracy (75.54%). Cluster-specific analyses demonstrated that H2O GLM provided the best recall-oriented performance in Cluster 1 (F2-score = 83.31%), while XGBoost performed best in Cluster 2 (F2-score = 83.25%). These findings demonstrate that H2O AutoML provides a robust and automated framework for malaria risk prediction, while cluster-specific modeling further improves predictive performance by accounting for population heterogeneity. The proposed framework has the potential to support early malaria risk assessment and complement conventional diagnostic strategies in resource-limited public health settings. Author summary: Effective malaria control depends on the timely identification of children at risk so that appropriate treatment can be initiated before severe disease develops. In Nigeria, rapid diagnostic tests may produce false-negative results, while delays in confirmatory laboratory testing can hinder timely clinical decision-making, particularly in resource-limited settings. In this study, we developed an automated machine learning framework using routinely available demographic, household, and socioeconomic information from the 2021 Nigeria Malaria Indicator Survey to support early malaria risk prediction. To reduce the influence of regional information on model development, agglomerative hierarchical clustering was performed after excluding regional identifiers, enabling the identification of population subgroups with distinct risk profiles. H2O AutoML demonstrated strong recall-oriented performance and produced competitive predictive models across both the overall population and cluster-specific analyses. These findings suggest that combining non-clinical data, automated machine learning, and subgroup-specific modeling can support scalable and more targeted malaria risk assessment, complementing existing diagnostic strategies in resource-limited settings.
SN - 2767-3170
ER -