Wearable Devices for Real-time Monitoring the Labor: A Potential Predictor of Preterm Labor
Published:
Preterm labor, occurring prior to 37 weeks of gestation, is a significant global health issue closely related to neonatal mortality and morbidity. Despite medical advancements, preterm labor statistics have not significantly decreased, partly due to inadequate monitoring techniques. Biosignals, including electrocardiography (ECG), electromyography (EMG), and electroencephalography (EEG), can provide critical information regarding the health of both mother and infant. However, the lack of accessibility, continuity, and real-time monitoring in current methods renders them insufficient for timely interventions.
A wearable device capable of constant, real-time, and precise monitoring of these biosignals would mark a breakthrough in obstetrics. This paper explores the limitations of existing preterm labor prediction methods, the potential of fetal heart rate monitoring through non-stress tests, the utility of EMG in diagnosing preterm labor, and the promising use of uterine electrical signals via electrohysterography (EHG). Additionally, the literature review section critically evaluates three recent studies on real-time biosignal monitoring approaches during pregnancy, assessing their merits and shortcomings.
The core of this research is the development of a machine learning-based model to predict preterm labor using EMG signals. The approach encompasses data collection, preprocessing, analysis, and the creation of a user-friendly interface for displaying real-time predictions. Ultimately, this study aims to develop a novel, wearable technology for the early detection of preterm labor, potentially transforming prenatal care and significantly reducing neonatal risks associated with preterm births.