Maternal risk prediction by early detection of Pre-Eclampsia and high-risk pregnancies using machine learning

After 20 weeks of pregnancy, pre-eclampsia, a severe pregnancy syndrome, usually manifests as increased blood pressure and injury to other organs. In order to prevent adverse consequences for both the mother and the fetus, early detection and forecasting are essential for prompt intervention and therapy. Machine learning techniques are highly effective tools for predictive analytics in the healthcare industry, with the ability to identify high-risk pregnancies and enhance clinical decision-making. In this study, it has been suggested that machine learning be used to forecast pre-eclampsia by utilizing clinical and perinatal demographic information. We use a dataset containing information on maternal age, blood pressure readings, and other relevant parameters to train and evaluate predictive models. Artificial neural networks were found to be the most effective approach, achieving an accuracy of 75%, demonstrating their potential in accurately predicting pre-eclampsia and supporting timely medical interventions.