IOT-based wearable uterine contraction and fetal monitoringsystem with artificial intelligence for prevention of pretermlabour and obstetric nursing management

Abstract

Preterm labour remains one of the leading causes of neonatal morbidity and mortality worldwide, accounting for significant healthcare expenditures and long-term developmental disabilities among surviving infants. Early identification of uterine activity and fetal compromise is essential for timely clinical intervention, yet conventional antenatal monitoring methods rely predominantly on intermittent hospital visits, limiting continuous surveillance of high-risk pregnancies. Recent advances in the Internet of Things (IoT), wearable biosensors, artificial intelligence (AI), cloud computing, and mobile health technologies have transformed maternal healthcare by enabling continuous, remote, and personalized monitoring throughout pregnancy. IoT-based wearable maternal monitoring systems integrate physiological sensors capable of measuring uterine contractions, fetal heart rate, maternal heart rate, body temperature, oxygen saturation, respiratory rate, and physical activity. These devices transmit real-time physiological data to cloud platforms, where AI algorithms analyse patterns to identify early indicators of preterm labour and fetal distress. Intelligent decision-support systems subsequently generate automated alerts for healthcare professionals and pregnant women, facilitating rapid clinical assessment and intervention. Artificial intelligence techniques, including machine learning, deep learning, ensemble learning, and predictive analytics, significantly improve diagnostic accuracy by identifying subtle physiological changes that are difficult to recognize through conventional monitoring. Such technologies support individualized risk assessment, reduce unnecessary hospital admissions, optimize obstetric nursing management, and enhance maternal–fetal outcomes through continuous surveillance and timely clinical decision-making. Obstetric nurses play a pivotal role in implementing AI-assisted monitoring systems by interpreting alerts, educating patients, coordinating multidisciplinary care, and ensuring adherence to evidence-based interventions. Despite promising clinical applications, challenges remain regarding sensor accuracy, cybersecurity, interoperability, ethical considerations, data privacy, and equitable access in lowresource settings. Continued technological innovation, rigorous clinical validation, and integration into routine obstetric practice are essential for maximizing the benefits of AI-enabled maternal monitoring systems. This article reviews the principles, technological components, clinical applications, nursing implications, benefits, challenges, and future prospects of IoT-based wearable uterine contraction and fetal monitoring systems for preventing preterm labour and improving obstetric nursing management