Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

valentineghanem-bit/nutrition-sae-ghana-261districts

Domaine:

healthcaregeospatialsocioeconomic

Type de record:

dataset
Créateur:
val
Hôte:
Bayesian spatial ML of stunting anaemia IYCF and diarrhoea across 261 districts of Ghana 2022 GDHS # Small-area Estimation of Childhood Stunting, Anaemia, Infant-Feeding Inadequacy and Diarrhoea Across Ghana's 261 Districts **Author:** Valentine Golden Ghanem | Ghana COCOBOD Cocoa Clinic, Accra, Ghana **ORCID:** 0009-0002-8332-0220 **Affiliation:** Ghana COCOBOD Cocoa Clinic, Accra, Ghana **Reporting standard:** STROBE · RECORD-Spatial · TRIPOD+AI **Date:** May 2026 **Status:** Manuscript in preparation --- ## 1. Abstract **Background.** Ghana's national child-nutrition indicators conceal large regional inequity, but nutrition programmes are planned and budgeted at the district level, where directly-measured estimates are unavailable. This study produces modelled district-level estimates of four child-health outcomes across all 261 districts and identifies their determinants. **Methods.** Outcome data are the 2022 Ghana DHS direct estimates for the 16 administrative regions — the effective inferential unit; district-level covariates (n = 261) are from the 2021 Population and Housing Census. District posteriors for stunting, anaemia (6–59 months), IYCF inadequacy and diarrhoea were obtained by benchmarked Besag–York–Mollié (BYM2) Bayesian small-area estimation. Spatial structure was assessed with Global Moran's I, LISA, bivariate LISA and Getis-Ord Gi*; spatial non-stationarity with geographically weighted regression (GWR); and determinant importance with Random Forest and XGBoost interpreted by SHAP under spatial leave-one-region-out cross-validation. **Results.** Modelled district posterior prevalence spans 7.5–34.6% for stunting, 30.5–74.4% for anaemia, 58.5–91.8% for IYCF inadequacy and 4.2–34.1% for diarrhoea. All four surfaces are strongly spatially clustered (Global Moran's I 0.82–0.96; all p = 0.002). SHAP identifies water and sanitation access, female illiteracy and poverty as the dominant determinants. **Seventeen districts — 14 in Northern and 3 in Savannah Region — are confirmed hotspots for all four outcomes simultaneously.** --- ## 2. Resea …

Visit

github.com

Languages

Ga

Similaires

valentineghanem-bit/nhis-oop-ghana-261districtsvalentineghanem-bit/sti-hiv-syndemic-ghana-261districtsvalentineghanem-bit/wash-child-health-ghana-261districtsvalentineghanem-bit/ghana-health-systems-spatial-261districtsvalentineghanem-bit/hiv-tb-ml-ghana-261districtsvalentineghanem-bit/spatial-ncd-burden-ghana

valentineghanem-bit/nhis-oop-ghana-261districts

Spatial Distribution and Determinants of NHIS Out-of-Pocket Health Expenditure in Ghana: A 261-Distr

valentineghanem-bit/sti-hiv-syndemic-ghana-261districts

STI and HIV syndemic burden: geospatial co-clustering and behavioural determinants in Ghana - 260 he

valentineghanem-bit/wash-child-health-ghana-261districts

Spatial ML mediation analysis: WASH determinants of childhood diarrhoea and under-five mortality acr

valentineghanem-bit/ghana-health-systems-spatial-261districts

Spatial Analysis of Health System Performance and Geographic Equity — Ghana 261 Districts # Spatial

valentineghanem-bit/hiv-tb-ml-ghana-261districts

Ensemble geospatial intelligence for HIV-TB co-infection mapping across 261 Ghana districts # Spati

valentineghanem-bit/spatial-ncd-burden-ghana

Noncommunicable Disease Burden and Determinants in Ghana: National Epidemiological Trends and Distri