Beyond Traditional Prenatal Monitoring: An Intelligent IoT-Based Pre-eclampsia Detection

Abstract

Globally, pre-eclampsia is becoming a leading cause of maternal and fetal death, mainly due to late diagnosis and insufficient monitoring. The study proposes an advanced IoT and Machine Learning (ML) system to ensure timely medical intervention through a real-time monitoring system to detect pre-eclampsia in an early stage. The proposed system consists of a wearable pre-eclampsia watch and fetal kick sensor, which consistently monitors the major maternal and fetal critical indicators, like fetal heart rate, oxygen saturation, uterine contractions, and blood pressure. The data collected through LoRa and Bluetooth technology is safely sent to a cloud platform, where ML algorithms predict the eclampsia risk based on real-time trends. System forecast analysis and intelligent alert mechanisms strengthen healthcare providers with timely insights, reduce complications, and increase pregnancy results, especially in resource-limited settings. Unlike existing models, this solution provides end-to-end monitoring, increased data security, and future risk evaluation, while reducing the difference between maternal health requirements and technological signs of progress. By integrating TinyML for on-device processing and safe cloud analytics, the study lays a scalable, cost-effective, and data-driven approach to maternal healthcare. The novel IoT-ML Framework can bring a revolution in prenatal care, which significantly reduces pre-eclampsia-related mortality.