Leveraging machine learning to identify determinants of zero utilization of maternal continuum of care in Ethiopia: Insights from SHAP analysis and the 2019 mini DHS

Abstract

Ensuring complete utilization of maternal continuum of care is essential for reducing maternal and neonatal mortality. In Ethiopia, significant gaps remain in maternal healthcare utilization, particularly among women who do not engage in any stage of the maternal care continuum. This study aims to identify the determinants of zero utilization in the maternal continuum of care among Ethiopian women using machine learning techniques, with insights provided by SHAP (SHapley Additive exPlanations) analysis. This study analyzed data from the 2019 Ethiopian Mini Demographic and Health Survey, using a cross-sectional design. The dataset was preprocessed and modeled using various machine learning algorithms through the PyCaret library, with lightGBM emerging as the best model after various models trained and evaluated based on classification performance metrics. S Synthetic Minority Over-sampling Technique was applied to address class imbalance. SHAP analysis was used to interpret model predictions and identify key predictors. lightGBM demonstrated robust performance with an accuracy of 84.47%, an AUC of 0.93, a recall of 0.80, a precision of 0.95, and an F1-score of 0.87 on test data. SHAP analysis revealed that residence in rural areas, the Somali region, being a daughter in the household, and Protestant religion were positively associated with zero maternal care utilization. Conversely, secondary or higher education, being married, higher wealth status, and having multiple children were associated with lower likelihoods of zero care utilization. The findings highlight the critical role of socioeconomic, demographic, and regional factors in maternal care utilization in Ethiopia. Targeted interventions, particularly in rural and underserved areas, are necessary to reduce barriers and promote equitable access to maternal healthcare services across Ethiopia. These insights can inform policies aimed at expanding female education, strengthening community-based maternal health programs, and prioritizing resource allocation to regions such as Somali where zero utilization is highest.

Fig 1. ROC Curve showing the performance of tuned and un-tuned lightGBM model on the test data.

Fig 2. Confusion matrix for prediction of tuned lightGBM model on the test data.

Fig 3. SHAP summary plot of the top predictor variables for zero maternal continuum of care.