Pre-eclampsia risk monitoring and alert system using machine learning and IoT

Abstract

After 20◦weeks of gestation, pre-eclampsia is characterized by newly developing hypertension. Preventative interventions only moderately lower a woman’s risk of pre-eclampsia due to its prevalence, the risk variables that have been found to be accurate in predicting its beginning, and the occurrence of pre-eclampsia. The signs and symptoms typically become visible toward the end of pregnancy (late second to early third trimester). Some of these tests are straightforward, while others are invasive; some have undergone significant research, while others are still being investigated in clinical settings. Pre-eclampsia has been linked, in particular, to cardiovascular sequelae in the fetus, such as hypertension and impaired vascular function. In our project, a system and an algorithm for evaluating the health status of pregnant women are proposed. Pre-eclampsia can cause major diseases and issues during pregnancy; thus, the system’s goal is to diagnose the condition early and monitor its risk. Our research examines the diagnostic options for early risk assessment to identify pregnant women at high risk for pre-eclampsia and the possible advantages for the women, the unborn child, and health-care systems. A system like this will be widely used in clinical obstetric practice. It is designed to be implemented to monitor pregnant women’s status updates through the Internet of Things based on machine learning.