(HealthDay News) — A model including 9 urine metabolites can predict preeclampsia early in pregnancy, according to a study published in Patterns.
Ivana Marić, PhD, from the Stanford University School of Medicine in California, and colleagues analyzed 6 omics datasets from a longitudinal cohort of pregnant women to develop machine-learning models for early prediction of preeclampsia (first 16 weeks of pregnancy) and during gestation.
The researchers identified a prediction model using 9 urine metabolites, which had the highest accuracy and was validated in an independent cohort (area under the receiver operating characteristic curve [AUC], 0.88 and 0.83 in the discovery and validation cohorts, respectively). The statistical significance of identified metabolites was demonstrated in a univariate analysis. Accuracy was further improved in an integrated multiomics model (AUC, 0.94). Tryptophan, caffeine, and arachidonic acid metabolisms were biological pathways identified. On integration with immune cytometry data, novel associations were suggested between immune and proteomic dynamics.
“If the results prove generalizable, our findings demonstrating high predictive power from a small number of urine metabolites and proteins could lead to a simple prediction test based on a small number of urine metabolites, suitable for use in both developed and developing parts of the world,” the authors write.
Several authors disclosed financial ties to the biotechnology industry.