Automated risk assessment tool for pregnancy care

Clinical decision support systems augment the quality of medical care by aiding healthcare workers in the evaluation and management of complicated cases. Clinical decision support systems are especially instrumental in quickly assessing the criticality of pregnancy as it involves interpreting multiple maternal and fetal parameters. We propose a machine learning approach for early determination of the risk category of pregnancy based on patterns gleaned from profiles of known clinical parameters. In particular, we demonstrate the usefulness of classification and regression trees in solving multivariate problems in obstetric care since the decision making process and the importance of specific parameters are clearly illustrated in the tree. As proof of concept, an application use case has been presented.