Advancing Knowledge on Machine Learning Algorithms for Predicting Childhood Vaccination Defaulters in Ghana: A Comparative Performance Analysis
High rates of childhood vaccination defaulting remain a significant barrier to achieving full vaccination coverage in sub-Saharan Africa, contributing to preventable morbidity and mortality. This study evaluated the utility of machine learning algorithms for predicting childhood vaccination defaulte...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/15/8198 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849405928028241920 |
|---|---|
| author | Eliezer Ofori Odei-Lartey Stephaney Gyaase Dominic Asamoah Thomas Gyan Kwaku Poku Asante Michael Asante |
| author_facet | Eliezer Ofori Odei-Lartey Stephaney Gyaase Dominic Asamoah Thomas Gyan Kwaku Poku Asante Michael Asante |
| author_sort | Eliezer Ofori Odei-Lartey |
| collection | DOAJ |
| description | High rates of childhood vaccination defaulting remain a significant barrier to achieving full vaccination coverage in sub-Saharan Africa, contributing to preventable morbidity and mortality. This study evaluated the utility of machine learning algorithms for predicting childhood vaccination defaulters in Ghana, addressing the limitations of traditional statistical methods when handling complex, high-dimensional health data. Using a merged dataset from two malaria vaccine pilot surveys, we engineered novel temporal features, including vaccination timing windows and birth seasonality. Six algorithms, namely logistic regression, support vector machine, random forest, gradient boosting machine, extreme gradient boosting, and artificial neural networks, were compared. Models were trained and validated on both original and synthetically balanced and augmented data. The results showed higher performance across the ensemble tree classifiers. The random forest and extreme gradient boosting models reported the highest F1 scores (0.92) and AUCs (0.95) on augmented unseen data. The key predictors identified include timely receipt of birth and week six vaccines, the child’s age, household wealth index, and maternal education. The findings demonstrate that robust machine learning frameworks, combined with temporal and contextual feature engineering, can improve defaulter risk prediction accuracy. Integrating such models into routine immunization programs could enable data-driven targeting of high-risk groups, supporting policymakers in strategies to close vaccination coverage gaps. |
| format | Article |
| id | doaj-art-82cc050c55f74e56b69d39aed7222e82 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-82cc050c55f74e56b69d39aed7222e822025-08-20T03:36:33ZengMDPI AGApplied Sciences2076-34172025-07-011515819810.3390/app15158198Advancing Knowledge on Machine Learning Algorithms for Predicting Childhood Vaccination Defaulters in Ghana: A Comparative Performance AnalysisEliezer Ofori Odei-Lartey0Stephaney Gyaase1Dominic Asamoah2Thomas Gyan3Kwaku Poku Asante4Michael Asante5Department of Computer Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ashanti Region, GhanaKintampo Health Research Centre, Research and Development Division of Ghana Health Service, Kintampo P.O. Box 200, Bono East Region, GhanaDepartment of Computer Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ashanti Region, GhanaKintampo Health Research Centre, Research and Development Division of Ghana Health Service, Kintampo P.O. Box 200, Bono East Region, GhanaKintampo Health Research Centre, Research and Development Division of Ghana Health Service, Kintampo P.O. Box 200, Bono East Region, GhanaDepartment of Computer Science, Kwame Nkrumah University of Science and Technology, Kumasi, Ashanti Region, GhanaHigh rates of childhood vaccination defaulting remain a significant barrier to achieving full vaccination coverage in sub-Saharan Africa, contributing to preventable morbidity and mortality. This study evaluated the utility of machine learning algorithms for predicting childhood vaccination defaulters in Ghana, addressing the limitations of traditional statistical methods when handling complex, high-dimensional health data. Using a merged dataset from two malaria vaccine pilot surveys, we engineered novel temporal features, including vaccination timing windows and birth seasonality. Six algorithms, namely logistic regression, support vector machine, random forest, gradient boosting machine, extreme gradient boosting, and artificial neural networks, were compared. Models were trained and validated on both original and synthetically balanced and augmented data. The results showed higher performance across the ensemble tree classifiers. The random forest and extreme gradient boosting models reported the highest F1 scores (0.92) and AUCs (0.95) on augmented unseen data. The key predictors identified include timely receipt of birth and week six vaccines, the child’s age, household wealth index, and maternal education. The findings demonstrate that robust machine learning frameworks, combined with temporal and contextual feature engineering, can improve defaulter risk prediction accuracy. Integrating such models into routine immunization programs could enable data-driven targeting of high-risk groups, supporting policymakers in strategies to close vaccination coverage gaps.https://www.mdpi.com/2076-3417/15/15/8198childhood vaccinationdefaultersmachine learningpredictive modellingensemble classifiersdata augmentation |
| spellingShingle | Eliezer Ofori Odei-Lartey Stephaney Gyaase Dominic Asamoah Thomas Gyan Kwaku Poku Asante Michael Asante Advancing Knowledge on Machine Learning Algorithms for Predicting Childhood Vaccination Defaulters in Ghana: A Comparative Performance Analysis Applied Sciences childhood vaccination defaulters machine learning predictive modelling ensemble classifiers data augmentation |
| title | Advancing Knowledge on Machine Learning Algorithms for Predicting Childhood Vaccination Defaulters in Ghana: A Comparative Performance Analysis |
| title_full | Advancing Knowledge on Machine Learning Algorithms for Predicting Childhood Vaccination Defaulters in Ghana: A Comparative Performance Analysis |
| title_fullStr | Advancing Knowledge on Machine Learning Algorithms for Predicting Childhood Vaccination Defaulters in Ghana: A Comparative Performance Analysis |
| title_full_unstemmed | Advancing Knowledge on Machine Learning Algorithms for Predicting Childhood Vaccination Defaulters in Ghana: A Comparative Performance Analysis |
| title_short | Advancing Knowledge on Machine Learning Algorithms for Predicting Childhood Vaccination Defaulters in Ghana: A Comparative Performance Analysis |
| title_sort | advancing knowledge on machine learning algorithms for predicting childhood vaccination defaulters in ghana a comparative performance analysis |
| topic | childhood vaccination defaulters machine learning predictive modelling ensemble classifiers data augmentation |
| url | https://www.mdpi.com/2076-3417/15/15/8198 |
| work_keys_str_mv | AT eliezeroforiodeilartey advancingknowledgeonmachinelearningalgorithmsforpredictingchildhoodvaccinationdefaultersinghanaacomparativeperformanceanalysis AT stephaneygyaase advancingknowledgeonmachinelearningalgorithmsforpredictingchildhoodvaccinationdefaultersinghanaacomparativeperformanceanalysis AT dominicasamoah advancingknowledgeonmachinelearningalgorithmsforpredictingchildhoodvaccinationdefaultersinghanaacomparativeperformanceanalysis AT thomasgyan advancingknowledgeonmachinelearningalgorithmsforpredictingchildhoodvaccinationdefaultersinghanaacomparativeperformanceanalysis AT kwakupokuasante advancingknowledgeonmachinelearningalgorithmsforpredictingchildhoodvaccinationdefaultersinghanaacomparativeperformanceanalysis AT michaelasante advancingknowledgeonmachinelearningalgorithmsforpredictingchildhoodvaccinationdefaultersinghanaacomparativeperformanceanalysis |