Exploring machine learning insights into long-acting reversible family planning usage in Ethiopia: analysis of the PMA 2023 dataset

INTRODUCTION: Ethiopia faces challenges in Long-Acting Reversible Family Planning (LARFP) adoption despite its efficacy. Traditional statistical methods have a limited capacity to capture nonlinear determinants. This study leverages machine learning (ML) to identify predictors of LARFP use using the 2021–2023 Performance Monitoring for Action (PMA) Ethiopia dataset. METHODS: Twenty-four predictors across geographic, socioeconomic, healthcare access, and behavioral domains were analyzed using seven machine learning models evaluated via stratified 5-fold cross-validation. RESULTS: Decision Tree outperformed other models (cross-validated accuracy: 99.45%, F1: 99.55%), identifying method duration (importance = 0.35), provider type (0.25), and region (0.15) as top predictors. These findings indicate that ML methods, particularly tree-based models, outperform traditional approaches in predicting contraceptive behavior. Regional disparities were stark (SNNP: 30.59% LARFP use vs. Amhara: 15.58%). Key reasons for method choice included fewer side effects (32.3%) and long duration (15.5%). CONCLUSION: Tree-based ML models effectively captured complex determinants of LARFP use. Targeted interventions addressing regional disparities, provider training, and client-centered care (e.g., reducing side effects) are critical for improving uptake. These insights provide evidence for tailored, data-driven family planning policies that address regional and provider-level disparities.