Early prediction and longitudinal modeling of preeclampsia from multiomics

Preeclampsia is a complex disease of pregnancy whose physiopathology remains unclear. We developed machine-learning models for early prediction of preeclampsia (first 16 weeks of pregnancy) and over gestation by analyzing six omics datasets from a longitudinal cohort of pregnant women. For early pregnancy, a prediction model using nine urine metabolites had the highest accuracy and was validated on an independent cohort (area under the receiver-operating characteristic curve [AUC] = 0.88, 95% confidence interval [CI] [0.76, 0.99] cross-validated; AUC = 0.83, 95% CI [0.62,1] validated). Univariate analysis demonstrated statistical significance of identified metabolites. An integrated multiomics model further improved accuracy (AUC = 0.94). Several biological pathways were identified including tryptophan, caffeine, and arachidonic acid metabolisms. Integration with immune cytometry data suggested novel associations between immune and proteomic dynamics. While further validation in a larger population is necessary, these encouraging results can serve as a basis for a simple, early diagnostic test for preeclampsia. •Machine-learning models for prediction of preeclampsia were developed•Six omics datasets from a longitudinal cohort of pregnant women were analyzed•Prediction models from urine metabolome and from proteome had the best accuracy•The prediction model from urine metabolites was validated on an independent cohort The World Health Organization estimates that more than 800 women worldwide die from pregnancy-related causes every day. One of the main causes is a hypertensive disorder, preeclampsia, for which the only treatment is to deliver, often too early. Preeclampsia affects 3%–5% of pregnancies in the United States and up to 8% globally. Machine-learning analyses of high-dimensional multiomics data could potentially capture complex dynamics involved in the preeclampsia pathogenesis. We developed machine-learning models for early prediction of preeclampsia (first 16 weeks of pregnancy) and over gestation by analyzing six omics datasets from a longitudinal cohort of pregnant women. A prediction model using nine urine metabolites had high accuracy and was validated on an independent cohort. While encouraging, our results need to be validated on a larger cohort. If generalizable, our findings could lead to a simple prediction test for use in both developed and developing parts of the world. Preeclampsia is one of the main complications of pregnancy, posin