Predicting Cervical Cancer Screening Utilization Among Women of Reproductive Age in Ethiopia Using Supervised Machine Learning: A Nationally Representative 2024/25 EDHS Study
- 1University of Gondar College of Medicine and Health Sciences
Abstract
BackgroundCervical cancer is a leading malignancy and mortality cause among Ethiopian women. Despite screening expansions coverage remains low. Traditional models miss complex determinants. This study aimed to develop machine learning models to predict cervical cancer screening utilization and identify drivers using the 2024 to 2025 Ethiopian Demographic and Health Survey.
MethodsA secondary analysis of the 2024 to 2025 Ethiopian Demographic and Health Survey was conducted among women aged 15 to 49. Six algorithms Logistic Regression, Decision Tree, Support Vector Machine, Random Forest, Gradient Boosting Machine and Extreme Gradient Boosting were trained. Synthetic Minority Over-sampling Technique handled class imbalance with a 4.2 percent screening prevalence. Models were evaluated on a holdout set using Area Under the Receiver Operating Characteristic curve, Area Under the Precision-Recall Curve, Brier score and Decision Curve Analysis. SHapley Additive exPlanations explained model predictions.
ResultsExtreme Gradient Boosting achieved superior discrimination with an Area Under the Receiver Operating Characteristic curve of 0.896 and Area Under the Precision-Recall Curve of 0.781 outperforming baseline Logistic Regression at 0.772. Isotonic calibration optimized prediction loss with a Brier score of 0.038. Decision Curve Analysis confirmed clinical net benefit across thresholds from 5 percent to 55 percent. Explanatory analysis identified cancer awareness, education, autonomy, wealth quintile, recent health visits and urban residence as primary screening drivers.
ConclusionsProbability-calibrated Extreme Gradient Boosting with explainability provides an accurate tool for identifying un-screened women in Ethiopia. Public health programs can deploy these tools in primary care applications to target outreach, optimize community engagement and accelerate World Health Organization elimination targets.
Related
- Estimated cardiorespiratory fitness and incident cardiometabolic multimorbidity: findings from three nationally representative cohorts
- Association of Korean Healthy Eating Index with Phase Angle and Extracellular Water-to-Total Body Water Ratio: Findings from a Nationally Representative Study
- Coexisting low bone mass and low muscle phenotype in relation to falls and depressive symptoms among Korean adults: a nationally representative cross-sectional study
- Depression, functional disability, and cardiovascular disease in adults with cardiovascular-kidney-metabolic syndrome stages 0–3: a nationally representative cohort study
- Dietary vitamin B1 intake and stroke risk in U.S. adults : Insights from a nationally representative health examination survey
BibTeX
@misc{gebiru2026predicting,
title = {{Predicting Cervical Cancer Screening Utilization Among Women of Reproductive Age in Ethiopia Using Supervised Machine Learning: A Nationally Representative 2024/25 EDHS Study}},
author = {A. M. Gebiru and N. B. Gelaw and D. K. Mekonen and A. A. Agazie and M. M. Kelkay and Y. D. Gelaw and T. N. Godana},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.02.26364565},
url = {https://www.medrxiv.org/content/10.64898/2026.10.02.26364565v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Predicting Cervical Cancer Screening Utilization Among Women of Reproductive Age in Ethiopia Using Supervised Machine Learning: A Nationally Representative 2024/25 EDHS Study
AU - A. M. Gebiru
AU - N. B. Gelaw
AU - D. K. Mekonen
AU - A. A. Agazie
AU - M. M. Kelkay
AU - Y. D. Gelaw
AU - T. N. Godana
PY - 2026
DA - 2026/10/02
PB - medRxiv
DO - 10.64898/2026.10.02.26364565
UR - https://www.medrxiv.org/content/10.64898/2026.10.02.26364565v1
AB - BackgroundCervical cancer is a leading malignancy and mortality cause among Ethiopian women. Despite screening expansions coverage remains low. Traditional models miss complex determinants. This study aimed to develop machine learning models to predict cervical cancer screening utilization and identify drivers using the 2024 to 2025 Ethiopian Demographic and Health Survey. MethodsA secondary analysis of the 2024 to 2025 Ethiopian Demographic and Health Survey was conducted among women aged 15 to 49. Six algorithms Logistic Regression, Decision Tree, Support Vector Machine, Random Forest, Gradient Boosting Machine and Extreme Gradient Boosting were trained. Synthetic Minority Over-sampling Technique handled class imbalance with a 4.2 percent screening prevalence. Models were evaluated on a holdout set using Area Under the Receiver Operating Characteristic curve, Area Under the Precision-Recall Curve, Brier score and Decision Curve Analysis. SHapley Additive exPlanations explained model predictions. ResultsExtreme Gradient Boosting achieved superior discrimination with an Area Under the Receiver Operating Characteristic curve of 0.896 and Area Under the Precision-Recall Curve of 0.781 outperforming baseline Logistic Regression at 0.772. Isotonic calibration optimized prediction loss with a Brier score of 0.038. Decision Curve Analysis confirmed clinical net benefit across thresholds from 5 percent to 55 percent. Explanatory analysis identified cancer awareness, education, autonomy, wealth quintile, recent health visits and urban residence as primary screening drivers. ConclusionsProbability-calibrated Extreme Gradient Boosting with explainability provides an accurate tool for identifying un-screened women in Ethiopia. Public health programs can deploy these tools in primary care applications to target outreach, optimize community engagement and accelerate World Health Organization elimination targets.
ER -