Predicting women’s intention to use contraceptives in East Africa: a machine learning analysis of predictors
7 affiliations
- 1Department of Health Informatics, College of Medicine and Health Science, Samara University
- 2Department of Health Informatics, Arba Minch Health Science College
- 3Department of Health Informatics, School of Public Health, College of Medicine and Health Science, Wachemo University
- 4Department of Epidemiology and Biostatistics, School of Public Health, College of Medicine and Health Sciences, Wollo University
- 5Department of Biomedical Science, College of Medicine and Health Science, Wollo University
- 6Department of Health Informatics, School of Public Health, College of Medicine and Health Science, Wollo University
- 7Department of Health Informatics, School of Public Health, Institute of Health, Bule Hora University
Abstract
Introduction Intention to use contraceptives reflects an individual’s or couple’s plan to adopt contraceptive methods, supporting women’s reproductive autonomy. It is associated with reduced unintended pregnancies, unsafe abortions, and high fertility rates, thereby improving maternal and infant health outcomes. Machine learning approaches can strengthen prediction accuracy and support evidence-based reproductive health planning. This study aimed to predict women’s intention to use contraceptives in East Africa using machine-learning methods. Methods We analyzed Demographic and Health Survey (DHS) data from 11 East African countries (2015–2024) in a community-based cross-sectional design. Country-specific sampling weights, stratification, and clustering were applied to account for the complex survey design. Missing data were imputed using the KNNImputer, and predictors were harmonized across surveys. Data preprocessing included cleaning, transformation, integration, and one-hot encoding, with an 80/20 train-test split. Seven machine learning algorithms were evaluated: adaptive boosting, CatBoost, random forest, light gradient boosting, extreme gradient boosting, logistic regression, and decision tree. Hyperparameters for CatBoost were tuned using Bayesian optimization under stratified 10-fold cross-validation. Model transportability was assessed using leave-one-country-out cross-validation. Results Among 123,290 reproductive-age women in East Africa, 51.23% reported intention to use contraceptives. Boosted tree algorithms performed best, particularly CatBoost achieving the highest discrimination with an AUC of 80.09% and an accuracy of 73.48%. Leave-one-country-out cross-validation confirmed moderate transportability with an AUC 74%, while calibration analysis showed reliable probability estimates (Brier score 0.179). SHAP feature importance identified employment, education, age, hearing about family planning, pregnancy, breastfeeding, barriers to healthcare access, and fertility preference as the most influential predictors of contraceptive intention. Conclusion This study provides a transparent, reproducible framework for pooled DHS prediction modeling, offering actionable insights for policymakers and health planners while serving as a methodological foundation for future applied work.
Related
- Development of a machine learning model to predict venous thromboembolism risk in women using combined oral contraceptives
- Double machine learning analysis identifies heterogeneous patterns in Ethiopian fertility intention: cross-sectional study
- Biomechanical and movement-quality predictors of lower-limb load-related injury in collegiate athletes: a prospective cohort study using functional movement screening, wearable inertial sensing, and explainable machine learning
- Explainable machine learning and deep learning models for predicting in-hospital mortality in burn patients
- Predicting MCI-to-Alzheimer’s Conversion: A Systematic Benchmark of Classical, Machine Learning, and Deep Survival Models
BibTeX
@article{birlie2026predicting,
title = {{Predicting women’s intention to use contraceptives in East Africa: a machine learning analysis of predictors}},
author = {Andualem Addisu Birlie and Tamir Wondim Desta and Biruktawit Lelisa Eticha and Adisu Meles Kabtyimer and Altaseb Beyene Kassaw and Halid Worku Jemil and Tesfaye Deribe Bedada},
journal = {BMC Women's Health},
year = {2026},
month = jul,
doi = {10.1186/s12905-026-04705-7},
url = {https://doi.org/10.1186/s12905-026-04705-7},
note = {CC BY},
}
RIS
TY - JOUR
TI - Predicting women’s intention to use contraceptives in East Africa: a machine learning analysis of predictors
AU - Andualem Addisu Birlie
AU - Tamir Wondim Desta
AU - Biruktawit Lelisa Eticha
AU - Adisu Meles Kabtyimer
AU - Altaseb Beyene Kassaw
AU - Halid Worku Jemil
AU - Tesfaye Deribe Bedada
PY - 2026
DA - 2026/07/01
JO - BMC Women's Health
DO - 10.1186/s12905-026-04705-7
UR - https://doi.org/10.1186/s12905-026-04705-7
AB - Introduction Intention to use contraceptives reflects an individual’s or couple’s plan to adopt contraceptive methods, supporting women’s reproductive autonomy. It is associated with reduced unintended pregnancies, unsafe abortions, and high fertility rates, thereby improving maternal and infant health outcomes. Machine learning approaches can strengthen prediction accuracy and support evidence-based reproductive health planning. This study aimed to predict women’s intention to use contraceptives in East Africa using machine-learning methods. Methods We analyzed Demographic and Health Survey (DHS) data from 11 East African countries (2015–2024) in a community-based cross-sectional design. Country-specific sampling weights, stratification, and clustering were applied to account for the complex survey design. Missing data were imputed using the KNNImputer, and predictors were harmonized across surveys. Data preprocessing included cleaning, transformation, integration, and one-hot encoding, with an 80/20 train-test split. Seven machine learning algorithms were evaluated: adaptive boosting, CatBoost, random forest, light gradient boosting, extreme gradient boosting, logistic regression, and decision tree. Hyperparameters for CatBoost were tuned using Bayesian optimization under stratified 10-fold cross-validation. Model transportability was assessed using leave-one-country-out cross-validation. Results Among 123,290 reproductive-age women in East Africa, 51.23% reported intention to use contraceptives. Boosted tree algorithms performed best, particularly CatBoost achieving the highest discrimination with an AUC of 80.09% and an accuracy of 73.48%. Leave-one-country-out cross-validation confirmed moderate transportability with an AUC 74%, while calibration analysis showed reliable probability estimates (Brier score 0.179). SHAP feature importance identified employment, education, age, hearing about family planning, pregnancy, breastfeeding, barriers to healthcare access, and fertility preference as the most influential predictors of contraceptive intention. Conclusion This study provides a transparent, reproducible framework for pooled DHS prediction modeling, offering actionable insights for policymakers and health planners while serving as a methodological foundation for future applied work.
SN - 1472-6874
ER -