Wireless sensor network nodes are small, non-rechargeable devices powered by batteries with limited energy supplies. When using multi-hop communication, data is sent over numerous hops before reaching the cluster head that is farthest from the base station. To minimize power consumption and maximize network lifetimes, this study integrates Multi-Hop communication into the Centralized Energy Efficient Clustering Routing Protocol to determine the optimal path for inter-cluster multi-hop communication between a source (cluster head) and a destination (base station). According to the simulation findings, the suggested algorithm outperforms both the Multi-Hop Technique for the Improvement of Low-Energy Adaptive Clustering Hierarchy Protocol and Energy Efficient Multi-Hop Routing using Genetic Algorithm. The proposed algorithm performs somewhat better than both Energy Efficient Multi-Hop Routing using Genetic Algorithm and Multi-Hop Technique for the Improvement of Low-Energy Adaptive Clustering Hierarchy Protocol in terms of normalized average energy consumption, network lifetime, and packet delivery ratio. The suggested approach is assessed using a MATLAB simulator and contrasted with other similar approaches. Simulations were conducted in a 300 × 300 m² area with 200 nodes, a base station at (100,100), a round length of 500 s, and an initial node energy of 100 J. Key energy parameters include ETX = ERX = 30 nJ/bit, Efs = 10 nJ/bit/m², and Emp = 30 nJ/bit/m⁴. In comparison with Multi-Hop Transmission, the simulation results demonstrated that Energy-Efficient Hierarchical Multi-Hop Routing using Genetic Algorithm improved normalized average energy usage by an average of 5.5 percent and 2.5 percent, packet delivery ratio by an average of 4.1 percent and 2.5 percent, and 3.5 percent and 4.2 percent, respectively.

Wireless Sensor Networks comprise low-cost, low-power, lightweight, and multifunctional sensor nodes capable of sensing and transmitting data from remote or hazardous environments to a central base station. These networks are widely deployed across various domains, including environmental monitoring, healthcare, and military applications. However, designing energy-efficient routing protocols remains a challenge due to limited battery capacity, constrained computational resources, absence of global addressing, and the dynamic topology of self-organizing nodes. The Low-Energy Adaptive Clustering Hierarchy (LEACH) protocol, a widely used cluster-based routing scheme, organizes nodes into clusters where cluster heads (CHs) manage intra-cluster communication using a Time Division Multiple Access (TDMA) schedule. Despite its advantages, LEACH’s TDMA mechanism becomes inefficient under unbalanced clustering, resulting in increased energy consumption at CHs. To overcome this issue, the Modified TDMA (MTDMA) approach was introduced, which adapts scheduling to the largest cluster size. However, MTDMA increases energy usage due to frequent inter-CH communication for determining cluster capacities. This study proposes the Energy-Efficient Modified Time Division Multiple Access (EEMTDMA) algorithm, where the base station centrally determines maximum cluster capacity, eliminating CH-to-CH communication and significantly reducing energy consumption. The algorithm was implemented using the Castalia 3.3 simulator in the OMNeT + + framework. Simulation results show that EEMTDMA outperforms both LEACH with MTDMA and LEACH with standard TDMA, achieving an average energy consumption of 48.4 J and delivering 4.75 packets per node to the base station. These results represent improvements of 7.9 J and 1.62 packets compared to LEACH with MTDMA, and 13.29 J and 2.33 packets compared to LEACH with TDMA.

Introduction Preterm birth remains a leading contributor to neonatal mortality and long-term morbidity worldwide, with Sub-Saharan Africa bearing a disproportionate share of the burden. Structural inequities, limited maternal healthcare access, and socioeconomic vulnerabilities are associated with higher model-predicted probability of preterm birth. Despite its significance, large-scale predictive modeling of preterm birth in this region remains limited. This study aimed to develop robust machine-learning–based prediction models and identify key factors associated with preterm birth using recent multi-country Demographic and Health Survey (DHS) data from (2019–2024). Methods A pooled cross-sectional analysis was conducted using nationally representative DHS data from eleven Sub-Saharan African countries, including 411,863 women aged 15–49 years. Four supervised machine learning algorithms were trained and tested using an 80/20 train–test split. Model performance was evaluated using accuracy, precision, recall, F1-score, and ROC-AUC. Model interpretability was assessed using SHapley Additive exPlanations (SHAP). Result The Random Forest model demonstrated the highest predictive performance for preterm birth, achieving an accuracy of 90.20% and ROC-AUC of 96.92%, outperforming the Decision Tree (accuracy of 89.2% and ROC-AUC of 92.19%), and other classifiers. The use of SMOTE for class imbalance handling and evaluation with precision–recall metrics improved model robustness in identifying minority class outcomes. SHAP-based feature importance analysis identified key predictors of the outcome,including low maternal educational attainment,unmarried marital status, lack of media exposure, lower household wealth index, and advanced maternal age (≥ 35 years). Additional important predictors were substance use,rural residence,employed women,anemia, abnormal maternal body mass index, insufficient antenatal care attendance (< 4 visits), and short birth interval. Overall, all these factors were associated with an increased predicted probability of preterm birth. Conclusion Machine learning models, particularly ensemble methods, demonstrated strong predictive performance for preterm birth in Sub-Saharan Africa. Random Forest performed best, highlighting the effectiveness of ensemble learning in handling complex and imbalanced datasets. Key socio-demographic and maternal health factors were consistently associated with preterm birth in a predictive (non-causal) framework. The integration of explainable artificial intelligence enhances model transparency and supports interpretation of predictive patterns in maternal health data. Findings should be interpreted as predictive associations rather than causal relationships, and caution is required when generalizing across heterogeneous country contexts.

Introduction One significant public health issue that impedes children’s growth and development is stunting. It is still very common in low-income nations. Reducing the impact of stunting requires early detection and determination of its factors. The purpose of this study was to forecast stunting in Ethiopian children under five and pinpoint its major contributing factors. Methods This study used secondary data from the Ethiopia Demographic and Health Survey (EDHS). Machine learning algorithms, including logistic regression, random forest, decision trees, and XGBoost, were applied to identify determinants of stunting. Model performance was evaluated using accuracy, precision, recall, F1 score, balanced accuracy, Matthews Correlation Coefficient (MCC), and AUROC. Results The experimental findings revealed that the random forest model demonstrated robust predictive performance for stunting, achieving an accuracy of 95.3 ± 0.6%, precision of 93.9 ± 0.8%, recall of 96.6 ± 0.9%, F1-score of 90.5 ± 1.1%, balanced accuracy of 93.2 ± 0.7%, MCC of 0.90 ± 0.01, and AUC of 98.3 ± 0.5% across fivefold cross-validation, indicating high reliability and stability of the predictions. The most important predictors of stunting were underweight status, region, household wealth status, child’s age, mother’s age, place of delivery, birth order, maternal education, source of drinking water, and child’s sex. Conclusion The Random Forest model proved to be the most successful in predicting stunting, according to the study. The frequency of stunting in low-income nations can be significantly decreased by enhancing maternal education, institutional delivery services, and availability to clean drinking water. To reduce childhood stunting, policymakers and program implementers should collaborate with important sectors like education, health, and agriculture.

Introduction The rising rates of Cesarean Sections deliveries globally pose significant challenges to maternal and neonatal health. Accurate prediction of Cesarean Sections delivery is critical for timely clinical decision-making, especially in resource-limited settings such as Ethiopia. This study leverages machine learning classification techniques to predict cesarean section deliveries among Ethiopian women, aiming to identify key risk factors and support interventions that improve maternal and neonatal outcomes. Methods A cross-sectional study was conducted using data from the 2019 Ethiopian Demographic and Health Survey (EDHS). Data processing and analysis were performed using Python (version 3.9). Machine learning algorithms including Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN), were implemented. Model performance was evaluated using standard metrics such as area under the ROC curve (AUC), accuracy, precision, recall, and F1-score. Results Among the developed models, Random Forest (RF) demonstrated the best performance, achieving an accuracy of 94.44% and an AUC of 97.99%. Overall, Random Forest proved to be the most reliable model for predicting cesarean section deliveries in this dataset. Conclusion Random Forest demonstrated superior predictive performance in identifying women at risk of Cesarean Sections delivery in Ethiopia. These findings highlight the potential of machine learning techniques to support data-driven decision-making in maternal healthcare and to guide interventions aimed at optimizing delivery outcomes.