Conference Abstract | Volume 9 (ConfPro8): Abstract 24 | Published: 05 Oct 2026
Eyob Akalewold Alemu1,&, Fetlework Gubena Aragie1, Lidetu demewoze2, Gelila Yitageasu2, Habtamu Shimels Hailemeskel3, Tigist Kiflie Tsegaw1
1Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia; 2Department of Environmental and Occupational Health and Safety, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia; 3Department of Nursing, College of Health Sciences, Debre Tabor University, Debre Tabor, Ethiopia
&Corresponding author: Eyob Akalewold Alemu, Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia, Email: eyob.akalewold@uog.edu.et
Received: 11 Mar 2026, Accepted: 29 Aug 2026, Published: 05 Oct 2026
Domain: Reproductive Health
Keywords: Facility-based abortion, machine learning, awareness
©Eyob Akalewold Alemu et al. Journal of Interventional Epidemiology and Public Health (ISSN: 2664-2824). This is an Open Access article distributed under the terms of the Creative Commons Attribution International 4.0 License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Cite this article: Eyob Akalewold Alemu et al., Predicting awareness of facility-based abortion services in Ethiopia using machine learning: A cross-sectional study. Journal of Interventional Epidemiology and Public Health. 2026;9(ConfPro8):24. https://doi.org/10.37432/JIEPH-CONFPRO8-0024
Unsafe abortion remains a major contributor to maternal morbidity and mortality in low- and middle-income countries. In Ethiopia, although safe abortion services are legally available under specific conditions and provided in health facilities, awareness of where to access these services remains limited. This gap in awareness undermines timely utilization of safe care and perpetuates preventable health risks. This study aimed to apply machine learning techniques to identify key predictors of women’s awareness of facility-based abortion services in Ethiopia.
A cross-sectional analysis was conducted using data from 8,894 women in the 2019 Performance Monitoring for Action (PMA) Ethiopia dataset. Data preprocessing, descriptive analysis, and machine learning modelling were performed in Python 3.12. The analytical pipeline included feature encoding and Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance. The dataset was split into 80% training and 20% testing sets. Eight supervised machine learning algorithms were trained and optimized using hyperparameter tuning. Model performance was assessed using accuracy, ROC-AUC, precision, recall, and F1-score. Model interpretability was evaluated using SHAP values.
The XGBoost model achieved the best performance, with an ROC-AUC of 0.952 and an accuracy of 0.912. Key predictors of awareness included knowledge of legally permitted abortion conditions (rape, risk to the mother’s life, and severe fetal anomalies), socioeconomic status (highest wealth quintile), reproductive health service utilization (family planning use), exposure to reproductive health information through media, and sociodemographic factors such as education level, age, and parity.
Machine learning models effectively predict women’s awareness of facility-based abortion services in Ethiopia. Strengthening legal awareness, improving access to reproductive health information, and addressing socioeconomic disparities may enhance awareness and improve access to safe abortion services, thereby reducing unsafe abortion practices.
Menu