Abstract
Preeclampsia (PE) is a leading cause of maternal and perinatal death globally and can lead to unplanned preterm birth. Predicting risk for preterm or early-onset PE, has been investigated primarily after conception, and particularly in the early and mid-gestational periods. However, there is a distinct clinical advantage in identifying individuals at risk for PE prior to conception, when a wider array of preventive interventions are available. In this work, we leverage machine learning techniques to identify potential pre-pregnancy biomarkers of PE in a sample of 80 women, 10 of whom were diagnosed with preterm preeclampsia during their subsequent pregnancy. We explore biomarkers derived from hemodynamic, biophysical, and biochemical measurements and several modeling approaches. A support vector machine (SVM) optimized with stochastic gradient descent yields the highest overall performance with ROC AUC and detection rates up to .88 and .70, respectively on subject-wise cross validation. The best performing models leverage biophysical and hemodynamic biomarkers. While preliminary, these results indicate the promise of a machine learning based approach for detecting individuals who are at risk for developing preterm PE before they become pregnant. These efforts may inform gestational planning and care, reducing risk for adverse PE-related outcomes.