Machine Learning in Electronic Health Records: Identifying High-Risk Obstetric Patients Pre and during Labor

Our goal is to apply artificial intelligence (AI) and statistical analysis to understand the relationship between various factors and outcomes during pregnancy and labor and delivery, in order to personalize birth management and reduce complications for both mothers and newborns. We use a structured electronic health records database with data from approximately 130,000 births to train, test and validate our models. We apply machine learning (ML) methods to predict various obstetrical outcomes before and during labor, with the aim of improving patient care management in the delivery ward. Using a large cohort of data (∼180 million data points), we then demonstrated that ML models can predict successful vaginal delivery, in the general population as well as a sub-cohort of women attempting trial of labor after a cesarean delivery. The real-time dynamic model showed increasing rates of accuracy as the delivery process progressed and more data became available for analysis. Additionally, we developed a cross-facilities application of an AI model that predicts the need for an unplanned cesarean delivery, illuminating the challenges associated with inter-facility variation in reporting practices. Overall, these studies combine novel technologies with currently available data to predict and assist safe deliveries for mothers and babies, both locally and globally.