Predicting Utilization of Emergency Contraceptive Usage in Ethiopia and Identifying Its Predictors Using Machine Learning
Mengistu, A. K.
Show abstract
Despite policy support, inappropriate use of emergency contraception (EC) in Ethiopia contributes to high rates of unintended pregnancy and maternal mortality. Traditional analyses have struggled to identify complex predictors. This study used machine learning (ML) and Explainable AI (XAI) to improve the prediction and interpretability of EC use. We analyzed data from 2,334 women in the PMA Ethiopia 2023 survey. Eight ML algorithms were tested to predict past-year EC use (4.4% prevalence), with SMOTE used to address class imbalance and SHAP values for interpretation. Logistic Regression on SMOTE data achieved the best performance (AUC-ROC: 0.848; Recall: 0.85). The most important predictor was EC awareness ("heard_emergency"), followed by media exposure and family planning discussions at health facilities. Conversely, recent reproductive events such as unintended pregnancy were linked to non-use. Static demographic factors showed poor predictive value. Findings highlight that knowledge gaps, not poverty or access, are key barriers to EC use. Tailored media campaigns and routine health counseling could enhance EC uptake. ML and XAI offer powerful tools for guiding targeted reproductive health interventions.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Determinants of Modern Contraceptive Use among Married and Sexually Active Unmarried Women aged 15-49 years old in Cambodia: How are geographical and socio-demographic factors associated with access? 94%
- Predictors of voluntary uptake of modern contraceptive methods in rural Sindh, Pakistan 94%
- Family planning uptake and its associated factors among women of reproductive age in Uganda: an insight from the Uganda Demographic and Health Survey 2016 94%
Similar papers in this journal
- Digital Health Technologies for Accessing Contraceptive Services among Young People in Sub-Saharan Africa: A Scoping Review Protocol 94%
- Impact of a pilot mHealth intervention on treatment outcomes of TB patients seeking care in the private sector using Propensity Scores Matching – Evidence collated from New Delhi, India 93%
- An AI-based approach to predict delivery outcome based on measurable factors of pregnant mothers 93%
Similar papers in this journal
- The aggregate effect of implementation strength of family planning programs on modern contraceptive use at the health systems level in rural Malawi 95%
- Effects of lower tiers of government healthcare facilities on unmet need for contraception and contraception use in Bangladesh 94%
- Spatial and hierarchical Bayesian analysis to identify factors associated with caesarean delivery use in Ethiopia: evidence from national population and health facility data 94%
Similar papers in this journal
- Maternal Factors Promoting Normal Linear Growth of Children from Impoverished Rwandan Households 93%
- Hair salons as a promising space to provide HIV and sexual and reproductive health services for young women in Lesotho: A citizen scientist mixed-methods study 93%
- "We have our reasons": Exploring the acceptability of pre-exposure prophylaxis among gay, bisexual, and other men who have sex with men in Ghana 93%
Similar papers in this journal
- Spatial inequities in access to medications for treatment of opioid use disorder highlight scarcity of methadone providers under counterfactual scenarios 91%
- Fusing a Bayesian case velocity model with random forest for predicting COVID-19 in the U.S. 91%
- A model-based evaluation of the efficacy of COVID-19 social distancing, testing and hospital triage policies 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.