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
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 algor...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Public Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12889-025-21334-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585384743141376 |
|---|---|
| author | Adem Tsegaw Zegeye Binyam Chaklu Tilahun Makida Fekadie Eliyas Addisu Birhan Wassie Berihun Alelign Mequannet Sharew Nebebe Demis Baykemagn Abdulaziz Kebede Tirualem Zeleke Yehuala |
| author_facet | Adem Tsegaw Zegeye Binyam Chaklu Tilahun Makida Fekadie Eliyas Addisu Birhan Wassie Berihun Alelign Mequannet Sharew Nebebe Demis Baykemagn Abdulaziz Kebede Tirualem Zeleke Yehuala |
| author_sort | Adem Tsegaw Zegeye |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-cd6d18de83714f01a500f1b424792f78 |
| institution | Kabale University |
| issn | 1471-2458 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Public Health |
| spelling | doaj-art-cd6d18de83714f01a500f1b424792f782025-01-26T12:55:29ZengBMCBMC Public Health1471-24582025-01-0125112510.1186/s12889-025-21334-1Predicting 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 algorithmAdem Tsegaw Zegeye0Binyam Chaklu Tilahun1Makida Fekadie2Eliyas Addisu3Birhan Wassie4Berihun Alelign5Mequannet Sharew6Nebebe Demis Baykemagn7Abdulaziz Kebede8Tirualem Zeleke Yehuala9Department of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarDepartment of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarDepartment of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarDepartment of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarDepartment of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarDepartment of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarDepartment of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarDepartment of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarDepartment of Health Informatics, School of Public Health, College of Medicine and Health Sciences, Wollo UniversityDepartment of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of GondarAbstract 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.https://doi.org/10.1186/s12889-025-21334-1Home deliverySub-Saharan AfricaMachine learningDemographic and health surveyPython |
| spellingShingle | Adem Tsegaw Zegeye Binyam Chaklu Tilahun Makida Fekadie Eliyas Addisu Birhan Wassie Berihun Alelign Mequannet Sharew Nebebe Demis Baykemagn Abdulaziz Kebede Tirualem Zeleke Yehuala 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 BMC Public Health Home delivery Sub-Saharan Africa Machine learning Demographic and health survey Python |
| title | 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 |
| title_full | 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 |
| title_fullStr | 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 |
| title_full_unstemmed | 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 |
| title_short | 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 |
| title_sort | 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 |
| topic | Home delivery Sub-Saharan Africa Machine learning Demographic and health survey Python |
| url | https://doi.org/10.1186/s12889-025-21334-1 |
| work_keys_str_mv | AT ademtsegawzegeye predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT binyamchaklutilahun predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT makidafekadie predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT eliyasaddisu predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT birhanwassie predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT berihunalelign predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT mequannetsharew predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT nebebedemisbaykemagn predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT abdulazizkebede predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm AT tirualemzelekeyehuala predictinghomedeliveryandidentifyingitsdeterminantsamongwomenaged1549yearsinsubsaharanafricancountriesusingademographicandhealthsurveys20162023amachinelearningalgorithm |