Abstract
<jats:p>The rapid expansion of IoT devices in maternal health monitoring enables continuous data collection and improved clinical assessment; however, it also introduces significant security and privacy concerns due to the sensitivity of maternal health information. This study investigates how artificial intelligence (AI) and machine learning (ML) can enhance both analytical performance and data protection in IoT-based maternal monitoring systems. The proposed framework employs Random Forest, Decision Tree, Support Vector Machine, and a stacking–bagging ensemble to improve maternal risk prediction and anomaly detection. Privacy-preserving techniques are integrated to secure physiological parameters: homomorphic encryption ensures data confidentiality during processing, while differential privacy limits information leakage from model outputs. Experimental results show that the stacking classifier combined with Random Forest achieved the highest accuracy of 82.3%, demonstrating greater robustness than traditional algorithms. Although differential privacy strengthened data protection, it reduced precision and F1-score, highlighting a trade-off between privacy and accuracy. Overall, integrating ensemble learning with privacy-preserving methods improves the security, accuracy, and reliability of IoT-driven maternal health monitoring systems.</jats:p>