Household-level spatial modelling of child height-for-age in Northern Province, Rwanda: comparison of geographically weighted and neural network weighted regression models
Geospatial Health · 2026
DOI: 10.4081/gh.2026.1491 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Geospatial Health, 2026. Verfasst von Clarisse Kagoyire und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Earth and Environmental Sciences, Lund University, Lund, Sweden; Centre for GIS and Remote Sensing, College of Science and Technology, …. Hauptthemen laut MEDLINE: Body Height, Growth Disorders, Family Characteristics, Neural Networks, Computer. Die Arbeit nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Childhood stunting remains a major public health concern in low- and middle-income countries, with persistent sub-national disparities. This study examined spatially varying associations between Height-for-Age z-scores (HAZ) and selected child, maternal, and household factors, and compared Geographically Weighted Regression (GWR), Multi-scale GWR (MGWR) and Geographically Neural Network Weighted Regression (GNNWR) in their ability to capture spatial heterogeneity and non-linearity. We analysed data from a cross-sectional survey conducted in December 2021 in the Northern Province of Rwanda. The survey covered 615 households, with analyses performed for 601 children aged 1–36 months. After imputation, multicollinearity screening, and feature selection, HAZ was modelled using Ordinary Least Squares (OLS), GWR, MGWR and GNNWR. Model performance was assessed using coefficient of determination (R2), Root Mean Square Error (RMSE), Akaike Information Criterion/AIC Corrected (AIC/AICc), and Moran’s I of residuals. Overall stunting prevalence was 27.1%. Spatially varying associations were observed for child age, sex, birthweight, underweight status, selected childcare practices, maternal support, and household living conditions. GNNWR achieved the best training performance (R2 = 0.66; RMSE=0.74) followed by MGWR (R2 =0.51; RMSE=0.88) and GWR (R2 =0.43; RMSE=0.95). Validation performance declined for all models, although GNNWR retained a higher validation (R2=0.28) with negligible residual spatial autocorrelation (Moran’s I = −0.005). GNNWR provided the strongest overall fit among the compared models and highlighted local spatial variation in associations with HAZ. However, the modest validation performance indicates that the findings should be interpreted cautiously. The workflow offers a portable framework for analysing DHS-like geocoded household datasets, but broader applicability should be assessed using spatial cross-validation, and sensitivity analyses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Earth and Environmental Sciences, Lund University, Lund, Sweden; Centre for GIS and Remote Sensing, College of Science and Technology, University of Rwanda, Kigali.
- Department of Earth and Environmental Sciences, Lund University, Lund, Sweden; Department of Civil, Environmental and Geomatics Engineering, College of Science and Technology, University of Rwanda, Kigali.
- Department of Earth and Environmental Sciences, Lund University, Lund.
- Department of Spatial Planning, School of Architecture and Built Environment, College of Science and Technology, University of Rwanda, Kigali.
- Lund University, Lund, Sweden.
Zitieren
APA
Kagoyire, C., Nduwayezu, G., Oucheikh, R., Bizimana, J. P., Pilesjö, P., & Mansourian, A. (2026). Household-level spatial modelling of child height-for-age in Northern Province, Rwanda: comparison of geographically weighted and neural network weighted regression models. Geospatial Health. https://doi.org/10.4081/gh.2026.1491
Vancouver
Kagoyire C, Nduwayezu G, Oucheikh R, Bizimana JP, Pilesjö P, Mansourian A. Household-level spatial modelling of child height-for-age in Northern Province, Rwanda: comparison of geographically weighted and neural network weighted regression models. Geospatial Health. 2026. doi:10.4081/gh.2026.1491
BibTeX
@article{Kagoyire2026,
author = {Kagoyire, Clarisse and Nduwayezu, Gilbert and Oucheikh, Rachid and Bizimana, Jean Pierre and Pilesjö, Petter and Mansourian, Ali},
title = {Household-level spatial modelling of child height-for-age in Northern Province, Rwanda: comparison of geographically weighted and neural network weighted regression models},
journal = {Geospatial Health},
year = {2026},
doi = {10.4081/gh.2026.1491}
}
EUVIMED