Shaheen M. Z. Memon

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.

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 analysed 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.

Purpose: Preterm Birth (PTB) is one of the leading causes of neonatal mortality in Uganda. Machine Learning (ML) can be used to identify women at risk of PTB in time for medical intervention and adequate preparation by mothers. Methods: We utilized data from paper-based maternal health records at Kawempe National Referral Hospital, Uganda. A case-control method was employed, where for every woman who experienced a PTB, a woman without PTB and delivered in the same day was selected as a control. Treatment of missing data was done using Random Forest imputation. Variable Importance was analyzed using Random Forest. The following classification methods were applied in the prediction of PTB: Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB). Performance of methods was investigated using prediction accuracy, sensitivity, and specificity. Results: 1,540 women were included in the study, where 770 women had experienced PTB, and 770 women formed the controls. According to variable importance analysis, number of antenatal care visits had the biggest impact on PTB. SVM had the highest accuracy in predicting PTB at 64% (sensitivity 64% and sensitivity 63%). Conclusions: Prediction of PTB using paper-based records in a developing country yielded similar results to studies done using electronic health records in developed countries. The predictive power could be low in this study due to fewer variables available from routinely collected ANC data. The inclusion of significant variables in the maternal records could potentially increase predictive power.