Wearable Devices for Real-time Monitoring the Labor: A Potential Predictor of Preterm Labor

Abstract

This research addresses preterm labor prediction using wearable devices for real-time monitoring. Preterm labor is a global health issue linked to neonatal mortality and morbidity. Current methods for detecting preterm labor, such as cervical length measurement and fetal fibronectin testing, have limitations. This study explores the application of biosignals like EMG and EHG for uterine activity analysis. Using machine learning techniques such as Logistic Regression, Support Vector Machines (SVC), and clustering methods, the research leverages the "Term-Preterm EHG Database" to develop predictive models. These models are integrated into a wearable device prototype, which provides a user-friendly interface for real-time predictions, offering significant potential to improve obstetric care and neonatal outcomes.