Related Experiment Video
Updated: Mar 11, 2026
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Machine learning/AI for early neonatal complication detection in rural Ethiopia: A retrospective cohort study in the
Amanuel Yoseph1, Yohannes Seifu Berego2, Mehretu Belayneh1
1School of Public Health, College of Medicine and Health Sciences, Hawassa University, Hawassa, Ethiopia.
Insights
Neonatal complications are common, especially in rural areas. Machine learning models, particularly XGBoost, accurately predict high-risk neonates using routine data, enabling timely interventions to reduce mortality.
Area of Science:
- Neonatal health
- Machine learning in healthcare
- Public health interventions
Background:
- Neonatal complications are a major cause of mortality in low- and middle-income countries, particularly in rural settings.
- Early identification of high-risk neonates is critical for effective intervention and improved outcomes.
- Existing risk assessment methods may not fully capture the complexity of neonatal complications.
Purpose of the Study:
- To assess the incidence and determinants of neonatal complications.
- To evaluate the predictive performance of machine learning algorithms for early risk identification.
- To develop a unified risk framework for adverse birth and early postnatal outcomes.
Main Methods:
- A retrospective cohort study utilizing routinely collected maternal and neonatal records.
- Development and comparison of five supervised machine learning models: logistic regression (LR), support vector machine (SVM), random forest (RF), artificial neural network (ANN), and extreme gradient boosting (XGBoost).
- Model performance evaluated using area under the curve (AUC), sensitivity, specificity, F1 score, and calibration, with SHapley Additive Explanations (SHAP) for predictor identification.
Main Results:
- 15.2% of neonates experienced complications, with higher incidence in rural (17.1%) versus urban areas (11.2%).
- XGBoost demonstrated the highest predictive performance (AUC = 0.85), identifying maternal age <20, previous neonatal complications, low education, unplanned pregnancy, <4 antenatal visits, anemia, and rural residence as key predictors.
- Sensitivity analyses confirmed robust model performance when analyzing birth outcomes and postnatal complications separately.
Conclusions:
- Neonatal complications and rural-urban disparities persist, underscoring the need for targeted interventions.
- Machine learning models, especially XGBoost, provide accurate and interpretable early risk prediction using readily available maternal and antenatal data.
- Strengthening prenatal care, anemia management, and rural health services can significantly reduce neonatal morbidity and mortality.
Introduction:
Neonatal complications remain a leading cause of illness and death in low- and middle-income countries, particularly in rural areas. Early identification of high-risk neonates is crucial for timely interventions. This study assessed the incidence and determinants of neonatal complications and evaluated the predictive performance of machine learning algorithms using a unified risk framework encompassing both adverse birth outcomes and early postnatal complications.
Methods:
We conducted a retrospective cohort study using routinely collected maternal and neonatal records. Five supervised machine learning models - logistic regression (LR), support vector machine (SVM), random forest (RF), artificial neural network (ANN), and extreme gradient boosting (XGBoost) were developed in R. Model performance was assessed with area under the curve (AUC), sensitivity, specificity, F1 score, and calibration. SHapley Additive Explanations (SHAP) identified key predictors. Sensitivity analyses evaluated the robustness of results by examining birth outcomes and postnatal complications separately.
Results:
Of the neonates studied, 15.2% (95% CI: 14.0-16.5) experienced complications, with higher rates in rural (17.1%) than urban areas (11.2%, p < 0.01). Preterm birth occurred in 12.7% and low birth weight in 9.4%, while 4.1% developed postnatal complications. XGBoost achieved the highest predictive performance [AUC = 0.85; sensitivity = 78%; specificity = 80%; F1 = 0.76], followed by RF and ANN. LR and SVM showed moderate accuracy. SHAP analysis highlighted maternal age <20, previous neonatal complications, low education, unplanned pregnancy, <4 antenatal visits, anemia, and rural residence as significant predictors. Sensitivity analyses confirmed stable performance across separate outcomes.
Conclusion:
Neonatal complications remain prevalent, with pronounced rural-urban disparities. XGBoost offers accurate and interpretable early risk prediction using routine maternal and antenatal data. Targeted interventions including expanded prenatal care, anemia management, and strengthened rural health services could reduce neonatal morbidity and mortality.
