ANC4+GEEMachine Learning
ANC4+ Prediction & Determinants
Predicting completion of 4+ antenatal care visits among 6,893 women across 794 clusters, with GEE analysis of key determinants.
Using the EDHS 2024-25 Individual Recode (6,893 women, 794 clusters), built classification models achieving a cross-validated AUC of 0.799 with both logistic regression and XGBoost. Weighted ANC4+ prevalence was 46.9%. A generalized estimating equations (GEE) analysis identified wealth, maternal education, family planning knowledge, rural residence, and region as the strongest determinants. Produced a full publication-ready manuscript.