Koos BJ, et al. - Researchers conducted a metabolomics study investigating whether accurate predictors of gestational diabetes mellitus in early pregnancy could be identified with advanced analytical methods. In this nested observational case-control study, they included 92 gravidas (46 in the gestational diabetes mellitus group and 46 in the control group) in early pregnancy, who were matched by maternal age, BMI, and gestational age at urine collection. Consensus multivariate analysis led to identification of 11 metabolites independently correlated with gestational diabetes mellitus. Via classification tree analysis, they selected a 7-metabolite subset that predicted gestational diabetes mellitus with an accuracy of 96.7%, independent of maternal age, BMI, and time of urine collection.