Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1153
version: 2
kind: revised
reason: Direction audit: filed as a problem but describes a gain.
timestamp: 2026-10-26T06:38:42.863655Z
status: published
lens: g_space
sector: education
headline: Predicting zero-dose vaccination status in 27 sub-Saharan African countries: a machine learning approach
dek: To develop a machine learning (ML)-based predictive model for assessing the risk of zero-dose children using Demographic Health Survey data in sub-Saharan Africa. This study analysed pooled Demographic and Health Survey data from 27 countries in sub-Saharan Africa collected between 2016 and 2024. Data preprocessing included imputation, balancing of unequal classes and systematic feature selection. Seven ML models were trained and evaluated using performance metrics such as accuracy, recall and F1-score. Feature…
gain_title: A LightGBM model predicted zero-dose vaccination risk in children across 27 African countries with 80% accuracy and 91% sensitivity, moderately effective.
problem_title: (none)
trace_subject: (none)
gain_reading: A LightGBM model predicted zero-dose vaccination risk in children across 27 African countries with 80% accuracy and 91% sensitivity, moderately effective.
gain_evidence: (none)
problem_reading: (none)
problem_evidence: (none)
quick_read: To develop a machine learning (ML)-based predictive model for assessing the risk of zero-dose children using Demographic Health Survey data in sub-Saharan Africa. This study analysed pooled Demographic and Health Survey data from 27 countries in sub-Saharan Africa collected between 2016 and 2024.

Among the seven models evaluated, LightGBM demonstrated the best overall performance, achieving the highest accuracy (80%), sensitivity (91%), and area under the receiver operating characteristic curve (AUROC = 0.78). Our findings suggest that machine learning, particularly LightGBM and XGBoost, is moderately effective in predicting the risk of zero-dose vaccination among children.
limitation: 
tag: Evidence-backed gain
key_points: To develop a machine learning (ML)-based predictive model for assessing the risk of zero-dose children using Demographic Health Survey data in sub-Saharan Africa. | This study analysed pooled Demographic and Health Survey data from 27 countries in sub-Saharan Africa collected between 2016 and 2024. | Data preprocessing included imputation, balancing of unequal classes and systematic feature selection.
rundown: To develop a machine learning (ML)-based predictive model for assessing the risk of zero-dose children using Demographic Health Survey data in sub-Saharan Africa. This study analysed pooled Demographic and Health Survey data from 27 countries in sub-Saharan Africa collected between 2016 and 2024.

Data preprocessing included imputation, balancing of unequal classes and systematic feature selection. Seven ML models were trained and evaluated using performance metrics such as accuracy, recall and F1-score.
sources:
- peer_reviewed | BMJ Health & Care Informatics | https://doi.org/10.1136/bmjhci-2026-102188 | 2026-09-18
prev: 967f3d422bf8d2b22402245a750dcc186ef9bcbd8f81995c1d5ac1f913e69d2c

sha256

d10a1c11900fdc2c067125f1569f60f92ea8612e26db11fe8f6d91e8c44294c5

previous

967f3d422bf8d2b22402245a750dcc186ef9bcbd8f81995c1d5ac1f913e69d2c