Cardiotocogram Data Analysis for Obstetric Risk Stratification

Abstract

In order to improve obstetric risk categorization, this study employs a thorough machine learning approach that makes use of cardiotocogram data. The goal is to find patterns and correlations that are relevant for forecasting fetal well-being by evaluating a dataset that includes several fetal health indicators, such as baseline fetal heart rates, uterine contractions, fetal movements, and decelerations. To lay the groundwork for feature selection and model construction, the authors conducted exploratory data analysis, which yielded important insights into the distributions and correlations of these clinical variables. The authors provide a predictive model for foetal health status classification that makes use of state-of-the-art machine learning methods. With this approach, they can better comprehend fetal distress signals and make more informed clinical decisions, which in turn can help reduce rates of neonatal and perinatal morbidity and mortality. The revolutionary effect of machine learning on improving healthcare efficiency and patient outcomes is highlighted by the results, which stress the need of incorporating data-driven methods into obstetric care.