EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Identifying Predictors of Utilization of Skilled Birth Attendance in Uganda Through Interpretable Machine Learning

Shaheen M Z Memon iD, Robert Wamala, Ignace H Kabano

International Journal of Environmental Research and Public Health · 2025

DOI: 10.3390/ijerph22111691 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Environmental Research and Public Health, 2025. Verfasst von Shaheen M Z Memon und 2 weiteren Autor:innen. Beteiligte Einrichtung: African Centre of Excellence in Data Science, College of Business and Economics, University of Rwanda, Kigali P.O. Box 4285, Rwanda. Hauptthemen laut MEDLINE: Machine Learning, Delivery, Obstetric. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: African Centre of Excellence in Data Science (ACE-DS), University of Rwanda.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skilled Birth Attendance (SBA) is essential for reducing maternal and neonatal mortality, yet access remains limited in many low- and middle-income countries. This study used machine learning to predict SBA use among Ugandan women and identify key influencing factors. We analyzed data from the 2016 Uganda Demographic and Health Survey, focusing on women aged 15 to 49 who had given birth in the preceding five years. After preparing and selecting relevant features, six tree-based models (decision tree, random forest, gradient boosting, XGBoost, LightGBM, CatBoost) and logistic regression were applied. Class imbalance was addressed using cost-sensitive learning, and hyperparameters were tuned via Bayesian optimization. XGBoost performed best (F1-score: 0.52; recall: 0.73; AUC: 0.75). SHapley Additive Explanations (SHAP) were used to interpret model predictions. Key predictors of SBA use included education level, antenatal care visits, region (especially Northern Uganda), perceived distance to a healthcare facility, and urban or rural residence. The results demonstrate the value of interpretable machine learning for identifying at-risk populations and guiding targeted maternal health interventions in Uganda.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningDelivery, ObstetricUgandaHumansFemaleAdultAdolescentYoung AdultMiddle AgedPregnancyPrenatal Care

Stichwörter der Autor:innen

SHAP explainabilityclass imbalanceclass weightsmachine learningmaternal healthcareskilled birth attendance

Autor:innen und Institutionen

  • African Centre of Excellence in Data Science, College of Business and Economics, University of Rwanda, Kigali P.O. Box 4285, Rwanda.
  • Department of Planning and Applied Statistics, College of Business and Management Sciences, Makerere University, Kampala P.O. Box 7062, Uganda.

ORCID-Profile: Shaheen M Z Memon

Förderung

  • African Centre of Excellence in Data Science (ACE-DS), University of Rwanda

Zitieren

APA

Memon, S. M. Z., Wamala, R., & Kabano, I. H. (2025). Identifying Predictors of Utilization of Skilled Birth Attendance in Uganda Through Interpretable Machine Learning. International Journal of Environmental Research and Public Health. https://doi.org/10.3390/ijerph22111691

Vancouver

Memon SMZ, Wamala R, Kabano IH. Identifying Predictors of Utilization of Skilled Birth Attendance in Uganda Through Interpretable Machine Learning. International Journal of Environmental Research and Public Health. 2025. doi:10.3390/ijerph22111691

BibTeX
@article{Memon2025,
  author = {Memon, Shaheen M Z and Wamala, Robert and Kabano, Ignace H},
  title = {Identifying Predictors of Utilization of Skilled Birth Attendance in Uganda Through Interpretable Machine Learning},
  journal = {International Journal of Environmental Research and Public Health},
  year = {2025},
  doi = {10.3390/ijerph22111691}
}
Kostenlos starten →