Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jan 24;25(1):302.
doi: 10.1186/s12889-025-21334-1.

Predicting home delivery and identifying its determinants among women aged 15-49 years in sub-Saharan African countries using a Demographic and Health Surveys 2016-2023: a machine learning algorithm

Adem Tsegaw Zegeye  1 , Binyam Chaklu Tilahun  2 , Makida Fekadie  2 , Eliyas Addisu  2 , Birhan Wassie  2 , Berihun Alelign  2 , Mequannet Sharew  2 , Nebebe Demis Baykemagn  2 , Abdulaziz Kebede  3 , Tirualem Zeleke Yehuala  2
Affiliations

Predicting home delivery and identifying its determinants among women aged 15-49 years in sub-Saharan African countries using a Demographic and Health Surveys 2016-2023: a machine learning algorithm

Adem Tsegaw Zegeye et al. BMC Public Health. .

Abstract

Background: Birth-related mortality is significantly increased by home births without skilled medical assistance during delivery, presenting a major risk to the public's health. The objective of this study is to predict home delivery and identify the determinants using machine learning algorithm in sub-Saharan African.

Methods: This study used design science approaches. The data set obtained from demographic health survey in sub-Saharan African weighted sample of 299,759 women was included in the stud. Machine learning models such as Random Forest, Decision Tree, K-Nearest Neighbor, Logistic Regression, Extreme Gradient Boosting, AdaBoost, Artificial Neural Network, and Naive Bayes were used. The predictive model was evaluated by area under the curve, accuracy, precision, recall, and F-measure.

Results: The final experimentation results indicated that random forest model performed the best to predict home delivery with accuracy (83%) and, ROC curve (89%). The Shapley additive explanation features an importance plot optimized for random forest model to identifying the most predictors of home delivery. Association rules findings showed that inadequate antenatal care visits, marital status married, no education, mobile phone, television, electricity, poor wealth index, infrequent television viewing, and rural residence were predictor of home delivery.

Conclusion: The random forest machine learning model provides greater predictive power for estimating home delivery risk factors. To reduce the prevalence of home delivery, this finding recommends to emphasis on improving antenatal care services, education, and awareness about health facility delivery.

Keywords: Demographic and health survey; Home delivery; Machine learning; Python; Sub-Saharan Africa.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: This study was based on secondary data analysis, and we obtained permission from the MEASURE DHS program to download and use the data for our research purposes. As a result, ethical approval and participant consent are not required for this study. The dataset is publicly available in the MEASURE DHS program’s official database, with no personal identifiers. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Map of study of the area of Sub-Saharan Africa
Fig. 2
Fig. 2
Sample size determination
Fig. 3
Fig. 3
A schematic representation of the sampling procedure of the sub-Saharan African countries
Fig. 4
Fig. 4
Overview of the machine learning framework used for predicting home delivery
Fig. 5
Fig. 5
Class distribution before SMOTE
Fig. 6
Fig. 6
Class distribution after SMOTE
Fig. 7
Fig. 7
Confusion matrices for random forest classifier
Fig. 8
Fig. 8
Model comparison balanced dataset by accuracy and AUC chart
Fig. 9
Fig. 9
ROC curve analysis
Fig. 10
Fig. 10
Random forest accuracy chart
Fig. 11
Fig. 11
Mean SHAP values feature important predictors of home delivery
Fig. 12
Fig. 12
Waterfall plot displaying prediction of home delivery
Fig. 13
Fig. 13
Beeswarm (summary) plot by optimized random forest model
Fig. 14
Fig. 14
Association rule mining by using apriori algorithms
See this image and copyright information in PMC

References

    1. Ou C-Y, et al. Maternal delivery at home: issues in India. Adv Therapy. 2021;38:386–98. - PMC - PubMed
    1. Chernet AG, Dumga KT, Cherie KT. Home delivery practices and associated factors in Ethiopia. J Reprod Infertility. 2019;20(2):102. - PMC - PubMed
    1. Gultie T, et al. Home delivery and associated factors among reproductive age women in Shashemene town, Ethiopia. J Women’s Health Care. 2016;5(300):2167–420.
    1. Kucho B, Mekonnen N. Delivery at home and associated factors among women in child bearing age, who gave birth in the preceding two years in Zala Woreda, southern Ethiopia. J Public Health Epidemiol. 2017;9(6):177–88.
    1. Mrisho M, et al. Factors affecting home delivery in rural Tanzania. Tropical Med Int Health. 2007;12(7):862–72. - PubMed

LinkOut - more resources