ABSTRACTPreeclampsia (PE) is a heterogeneous and complex disease associated with rising morbidity and mortality in pregnant women and newborns in the US. Early recognition of patients at risk is a pressing clinical need to significantly reduce the risk of adverse pregnancy outcomes. We assessed whether information routinely collected and stored on women in their electronic medical records (EMR) could enhance the prediction of PE risk beyond what is achieved in standard of care assessments today. We developed a digital phenotyping algorithm to assemble and curate 108,557 pregnancies from EMRs across the Mount Sinai Health System (MSHS), accurately reconstructing pregnancy journeys and normalizing these journeys across different hospital EMR systems. We then applied machine learning approaches to a training dataset from Mount Sinai Hospital (MSH) (N = 60,879) to construct predictive models of PE across three major pregnancy time periods (ante-, intra-, and postpartum). The resulting models predicted PE with high accuracy across the different pregnancy periods, with areas under the receiver operating characteristic curves (AUC) of 0.92, 0.83 and 0.89 at 37 gestational weeks, intrapartum and postpartum, respectively. We observed comparable performance in two independent patient cohorts with diverse patient populations (MSH validation dataset N = 38,421 and Mount Sinai West dataset N = 9,257). While our machine learning approach identified known risk factors of PE (such as blood pressure, weight and maternal age), it also identified novel PE risk factors, such as complete blood count related characteristics for the antepartum time period and ibuprofen usage for the postpartum time period. Our model not only has utility for earlier identification of patients at risk for PE, but given the prediction accuracy substantially exceeds what is achieved today in clinical practice, our model provides a path for promoting personalized precision therapeutic strategies for patients at risk.